CN109077746B

CN109077746B - Method, system and device for determining radiation dose modulation line

Info

Publication number: CN109077746B
Application number: CN201810715092.XA
Authority: CN
Inventors: 彭维礼
Original assignee: Shanghai United Imaging Healthcare Co Ltd
Current assignee: Shanghai United Imaging Healthcare Co Ltd
Priority date: 2018-06-29
Filing date: 2018-06-29
Publication date: 2022-08-02
Anticipated expiration: 2038-06-29
Also published as: CN109077746A

Abstract

A method, system, apparatus, and computer-readable storage medium for determining a radiation dose modulation line are provided. The method comprises the steps of obtaining a positioning image of an object to be scanned; segmenting the scout image to determine at least one region of interest on the scout image; determining at least one regional dose modulation line, each of the at least one regional dose modulation lines corresponding to one of the at least one region of interest; and determining a dose modulation line associated with a CT scan of the object to be scanned based on the at least one region dose modulation line. By adopting the method, the accuracy of determining the dose modulation line can be improved, and timely reminding can be realized when the scanning protocol is inaccurate.

Description

Method, system and device for determining radiation dose modulation line

Technical Field

The present application relates generally to methods and systems for adjusting radiation Dose in Computed Tomography (CT) scans, and more particularly to methods and systems for determining Dose of Modulation (DOM) lines during CT scans.

Background

In CT scanning, Tube Current Modulation (TCM) has become an effective method to reduce the CT radiation dose while maintaining the desired image quality. Before CT scanning is executed on a formal object to be scanned, a scanning protocol needs to be set, and positioning scanning is executed to obtain a positioning image of the object to be scanned. The scan protocol and scout image may be used to determine a dose modulation line, and the dose modulation line may be used as a reference for adjusting the tube current of the CT apparatus during a formal CT scan. However, in practical applications, particularly when CT scanning is required for a plurality of body parts of a subject to be scanned, there may be a case where a set scanning protocol is not accurate and does not conform to the part to be scanned. This can lead to inaccurate dose modulation lines based on scan protocols and scout image estimates, which in turn can affect the quality of subsequently reconstructed CT images. Therefore, there is a need for a more reliable method of determining dose modulation lines that improves the accuracy of the CT system in determining the dose modulation lines and that can alert the operator of the CT system (e.g., nurse, radiologist) when the scan protocol is inaccurate.

Disclosure of Invention

In view of the above problems, the present invention discloses a method, system, apparatus and computer readable storage medium for determining a radiation dose modulation line, which solve the above problems in the prior art.

In order to achieve the purpose of the invention, the technical scheme provided by the invention is as follows:

a first aspect of the present application provides a method of determining a radiation dose modulation line, the method comprising: acquiring a positioning image of an object to be scanned; segmenting the scout image to determine at least one region of interest on the scout image; determining at least one regional dose modulation line, each of the at least one regional dose modulation lines corresponding to one of the at least one region of interest; and determining a dose modulation line associated with a CT scan of the object to be scanned based on the at least one region dose modulation line.

In some embodiments, the determining at least one regional dose modulation line comprises: extracting features of each of the at least one region of interest; determining a reference scout image corresponding to each of the at least one region of interest based on the extracted features; and determining a regional dose modulation line for each of the at least one region of interest based on the reference scout image.

In some embodiments, said determining a regional dose modulation line for each of said at least one region of interest based on said reference scout image comprises: for each of the at least one region of interest, acquiring a scan protocol associated with a reference scout image; and determining a regional dose modulation line for the region of interest based on at least one parameter in the scan protocol.

In some embodiments, the determining a regional dose modulation line for the region of interest based on at least one parameter in the scan protocol comprises: acquiring at least one image parameter associated with the region of interest in a scout image of the object to be scanned; and determining a regional dose modulation line for the region of interest based on at least one parameter in the scanning protocol and at least one image parameter associated with the region of interest in the scout image of the object to be scanned.

In some embodiments, said determining a dose modulation line for each of said at least one region of interest based on said reference scout image comprises: for each of the at least one region of interest, acquiring a reference three-dimensional image corresponding to the reference scout image; and generating a model using a dose modulation line to generate a regional dose modulation line corresponding to the region of interest based on the reference scout image and the reference three-dimensional image.

In some embodiments, the dose modulation line generation model comprises a neural network model.

In some embodiments, the method of determining a radiation dose modulation line further comprises: setting an initial scanning protocol; determining an initial dose modulation line based on the initial scanning protocol and the scout image of the object to be scanned; comparing the initial dose modulation line with a dose modulation line associated with a CT scan of the object to be scanned; and modifying the initial scan protocol based on the comparison.

A second aspect of the present application provides a system for determining a radiation dose modulation line, the system comprising: an acquisition unit configured to acquire a scout image of an object to be scanned; a segmentation unit configured to segment the scout image to determine at least one region of interest on the scout image; and a dose modulation line generation unit configured to: determining at least one regional dose modulation line, each of the at least one regional dose modulation lines corresponding to one of the at least one region of interest; and determining a dose modulation line associated with a CT scan of the object to be scanned based on the at least one region dose modulation line.

A third aspect of the present application provides an apparatus for determining a radiation dose modulation line. The apparatus includes a storage medium and at least one processor; the storage medium includes computer instructions; and the at least one processor is configured to execute at least some of the computer instructions to implement the operations in the above methods.

A fourth aspect of the present application provides a computer-readable medium. The storage medium stores computer instructions that, when executed by a processor, implement the operations of the above method.

Drawings

The present application will be described in conjunction with embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These embodiments are non-limiting exemplary embodiments in which like reference numerals represent similar structures throughout the several views of the drawings and wherein:

FIG. 1 is a schematic illustration of an exemplary imaging system according to some embodiments of the present application;

FIG. 2 is a schematic diagram of exemplary hardware and software components of a computing device according to some embodiments of the present application;

FIG. 3 is a diagram illustrating hardware and/or software components of an exemplary mobile device that may implement the particular systems disclosed herein, according to some embodiments of the present application;

FIG. 4 is a schematic block diagram of an exemplary processing device, shown in accordance with some embodiments of the present application;

FIG. 5 is an exemplary flow chart for determining a dose modulation line according to some embodiments of the present application;

FIG. 6 is a schematic block diagram of a processing module shown in accordance with some embodiments of the present application;

FIG. 7 is an exemplary flow chart for determining a dose modulation line based on a Three-Dimensional (3D) image and a scout image according to some embodiments of the present application;

8-A and 8-B are an exemplary flow chart for training a dose modulation line generation model according to some embodiments of the present application;

FIG. 9 is a schematic diagram of an architecture of a dose modulation line generation model according to some embodiments of the present application;

FIG. 10 is a schematic block diagram of a processing module shown in accordance with some embodiments of the present application;

FIG. 11 is an exemplary flow chart for determining a dose modulation line based on a 3D image according to some embodiments of the present application;

FIG. 12 is a schematic block diagram of a processing module shown in accordance with some embodiments of the present application;

FIG. 13 is an exemplary flow chart for determining a dose modulation line based on a scout image according to some embodiments of the present application;

FIG. 14 is an exemplary flow chart for determining a regional dose modulation line according to some embodiments of the present application; and

fig. 15 is a schematic view of an exemplary human body and an exemplary dose modulation line according to some embodiments of the present application.

Detailed Description

The following description is presented to enable one of ordinary skill in the art to make and use the invention and is provided in the context of a particular application and its requirements. It will be apparent to those of ordinary skill in the art that various modifications to the embodiments disclosed herein are possible, and that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the present application. Therefore, the present application is not limited to the disclosed embodiments, but is to be accorded the widest scope consistent with the claims.

It will be appreciated that the terms "system," "engine," "unit," "module," and/or "block" as used herein are a way of distinguishing, in ascending order, different components, elements, components, sections, or assemblies at different levels. However, other expressions may be used instead of the above terms which may achieve the same purpose.

Generally, a "module," "unit," and/or "block" in this application refers to logic or a set of software instructions stored in hardware, firmware. The modules, units, or blocks described herein can be implemented in software and/or hardware and may be stored on any non-transitory computer-readable medium or other storage device. In some embodiments, software modules/units/blocks may be compiled and linked into an executable program. The software modules herein may respond to information conveyed by themselves or other modules/units/blocks and/or may respond when certain events or interrupts are detected. Software modules/units/blocks configured for execution on a computing device (e.g., processor 220 as shown in fig. 2) may be provided by a computer-readable medium, which may be a compact disc, a digital compact disc, a flash drive, a magnetic disk, or any other tangible medium, as a digital download (and may be initially stored in a compressed or installable format, requiring installation, decompression, or decryption prior to execution). The software code herein may be stored in part or in whole in a memory device of a computing device performing the operations and employed in the operations of the computing device. The software instructions may be embedded in firmware, such as an Erasable Programmable Read Only Memory (EPROM). It will be appreciated that the hardware modules/units/blocks include logic units, such as gates, flip-flops, connected together and/or are embodied in a programmable unit, such as a programmable gate array or a processor. The modules/units/blocks or computing device functions described herein may be implemented as software modules/units/blocks, but may be represented in hardware or firmware. Generally, a module/unit/block referred to herein is a logical module/unit/block that can be combined with other modules/units/blocks or divided into sub-modules/sub-units/sub-blocks, regardless of their physical organization or storage. The description may be applied to a system, an engine, or a portion thereof.

The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to limit the scope of the present application. As used in this application, the terms "a," "an," and "the" are not intended to be inclusive in the singular, but rather are inclusive in the plural, unless the context clearly dictates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this application, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of at least one other feature, integer, step, operation, element, component, and/or group thereof.

The features and characteristics of the present application, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description of the drawings, which form a part hereof. It is to be expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the application. It should be understood that the drawings are not to scale.

Flowcharts are used herein to illustrate the operations performed by systems according to embodiments of the present application. It should be understood that the operations in the flow diagrams are not necessarily performed in order. Rather, various steps may be processed in reverse order or simultaneously. In addition, at least one other operation may be added to the flowchart. At least one operation may also be deleted from the flowchart.

The present application relates to methods and systems for determining a dose modulation line. In some embodiments, the method involves determining a dose modulation line based on an image of an object to be scanned. In some embodiments, the scout image may be used to estimate the shape size (e.g., 3D contour) of the object to be scanned. For example, the shape and size of the object may be estimated from attenuation data of the object in the scout image. However, since the scout image is a Two-Dimensional (2D) image corresponding to a fixed scan angle (generally vertically downward), the shape or size of the object to be scanned cannot be accurately estimated, especially in the lateral and oblique directions. To address this issue, 3D images may be used to generate more accurate object shapes or 3D contours. The radiation dose on each slice of the object to be scanned (each slice corresponding to a particular scan angle) may be determined based on the properties (e.g., thickness, width) of the 3D contour. A dose modulation line is determined based on the determined radiation dose.

In some embodiments, the method involves determining a dose modulation line based on the scout image. For example, a scout image of an object to be scanned may be segmented into at least one region of interest. For each of the at least one region of interest, a reference scout image is identified. Regional dose modulation lines are determined for each reference scout image and combined to generate a dose modulation line for the entire object to be scanned.

In some embodiments, the method involves determining a dose modulation line based on the scout image and the 3D image of the object to be scanned. For example, a model may be generated by acquiring dose modulation lines to determine the dose modulation lines of the object to be scanned. The dose modulation line generating model may be trained on a training data set comprising a plurality of sample CT images, a plurality of sample scout images and a plurality of 3D images of a plurality of objects to be scanned. And (3) taking the positioning image and the 3D image of the object to be scanned as the input of the trained dose modulation line generation model, so as to generate the personalized dose modulation line.

FIG. 1 is a schematic view of an exemplary imaging system according to some embodiments of the present application. In some embodiments, the imaging system 100 may scan an object to be scanned and acquire corresponding scan data. The imaging system 100 may generate an image based on the scan data. The imaging system 100 may pre-process the scan data or the generated image. Preprocessing of the scan data or generated image includes noise reduction, smoothing, correction, etc., or any combination thereof.

In some embodiments, the imaging system 100 may be a medical imaging system. The medical imaging system may be a single modality imaging system or a multi-modality imaging system. The Single mode Imaging system includes a PET (Positron Emission Tomography) device, a SPECT (Single Photon Emission Computed Tomography) device, a CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, a DR (Digital Radiography) device, and the like. The multi-mode imaging system comprises a PET-CT device, a PET-MRI device, a SPECT-MRI device and the like.

As shown in fig. 1, imaging system 100 includes a scanning device 110, a network 120, at least one terminal 130, a processing device 140, and a memory 150.

The scanning device 110 includes a gantry 111, a 3D depth camera 112, a radioactive scanning source 113, a detector 114 and a table 115. A three-dimensional cartesian coordinate system is shown in fig. 1. The table 115 may support an object to be scanned (e.g., a patient). The Z-axis (also referred to as Z-direction) corresponds to the long axis direction of the object to be scanned. The X-Y plane (also referred to as the cross-section or axial plane) corresponds to a plane perpendicular to the Z-axis. During a CT scan, the radioactive scanning source 113 and the detector 114 can be rotated while maintaining their relative positions in the X-Y plane.

The gantry 111 supports a 3D depth camera 112, a radioactive scanning source 113 and a detector 114. In some embodiments, the stage 115 may move along the Z-axis. The moving speed of the stage 115 may be adjusted according to the scanning time, the scanning area, and the like.

The 3D depth camera 112 may capture a three-dimensional (3D) image (also referred to as a depth image) of an object to be scanned. The 3D depth camera 112 may take 3D images from a variety of angles, including but not limited to from the front, top, side, and the like. In some embodiments, the 3D depth camera may generate the 3D image based on stereoscopic vision techniques, structured light techniques, Time-of-Flight (ToF) techniques, or the like, or any combination thereof. In some embodiments, a 3D contour of the object to be scanned may be estimated based on the 3D image.

The radioactive scanning source 113 may emit radiation toward the subject to be scanned. The radiation includes a corpuscular ray, a photon ray, and the like. The particle radiation includes neutrons, protons, electrons, muitimedia, heavy ions, etc., or any combination thereof. Photon radiation includes X-rays, gamma rays, alpha rays, beta rays, ultraviolet rays, laser light, and the like, or any combination thereof. In some embodiments, the radioactive scanning source 113 can be rotated in the X-Y plane during a CT scan. In some embodiments, during a scout scan, the radioactive scanning source 113 is in a stationary position.

The detector 114 may detect radiation. At least a portion of the detected radiation may be detected by penetrating the scanned object. Read data (also referred to as scan data) is generated in response to the detected radiation. In some embodiments, the detector 114 includes a scintillation detector (e.g., a cesium iodide detector), a gas detector, a circular detector, a square detector, an arcuate detector, or the like, or any combination thereof. In some embodiments, the detectors may be single row detectors or multiple row detectors.

Network 120 may include a network capable of facilitating information exchange and/or data exchange in imaging system 100. In some embodiments, at least one component of imaging system 100 (e.g., scanner 110, terminal 130, processing device 140, memory 150, image acquisition device 160, etc.) may be in information and/or data communication with at least one other component of imaging system 100 via network 120. For example, the processing device 140 may acquire image data from the scanner 110 via the network 120. As another example, processing device 140 may obtain user instructions from terminal 130 via network 120. Network 120 may be and/or include one or a combination of public networks (e.g., the internet), Private networks (e.g., Local Area Networks (LANs), Wide Area Networks (WANs), etc.), wired networks (e.g., ethernet), wireless networks (e.g., 802.11 networks, Wi-Fi networks), cellular networks (e.g., Long Term Evolution (LTE) networks), frame relay networks, Virtual Private Networks (VPNs), satellite networks, telephone networks, routers, hubs, switches, server computers, etc. For example, Network 120 may include one or a combination of cable networks, wired networks, fiber optic networks, telecommunication networks, intranets, Wireless Local Area Networks (WLANs), Metropolitan Area Networks (MANs), Public Switched Telephone Networks (PSTN), bluetooth, Zigbee networks, Near Field Communication (NFC) networks, and the like. In some embodiments, network 120 may include at least one network access point. For example, network 120 may include wired and/or wireless network access points such as base stations and/or internet switching points. At least one component of the imaging system 100 may be connected to the network 120 through the base station and/or internet exchange point to enable the exchange of data and/or information.

The terminal 130 may include one or a combination of mobile devices 130-1, a tablet computer 130-2, a laptop computer 130-3, and the like. In some embodiments, the mobile device 130-1 may include one or a combination of smart home devices, wearable devices, mobile devices, virtual reality devices, augmented reality devices, and the like. In some embodiments, the smart home device may include one or a combination of several of a smart lighting device, a control device of a smart electronic device, a smart monitoring device, a smart television, a smart camera, an interphone, and the like. In some embodiments, the wearable device may include one or a combination of a bracelet, footwear, glasses, helmet, watch, clothing, backpack, smart accessory, and the like. In some embodiments, the mobile device may include one or a combination of a mobile phone, a Personal Digital Assistant (PDA), a gaming device, a navigation device, a Point of Sale (POS) device, a laptop, a tablet, a desktop, and the like. In some embodiments, the virtual reality device and/or the augmented reality device may include one or a combination of virtual reality helmets, virtual reality glasses, virtual reality eyeshields, augmented reality helmets, augmented reality glasses, augmented reality eyeshields, and the like. For example, the virtual reality device and/or the augmented reality device may include Google glasses, Oculus Rift, Hololens, Gear VR, and the like. In some embodiments, the terminal 130 may be part of the processing device 140.

Processing device 140 may process data and/or information retrieved from scanning device 110, terminal 130, and/or memory 150. For example, the processing device 140 may process the image data (e.g., 3D images and/or scout images) and determine a dose modulation line that may be used as a reference to adjust the tube current of the radioactive scanning source 113. In some embodiments, the processing device 140 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, the processing device 140 may be local or remote. For example, the processing device 140 may access information and/or data stored in the scanning device 110, the terminal 130, and/or the memory 150 via the network 120. As another example, the processing device 140 may be directly connected to the scanning device 110, the terminal 130, and/or the memory 150 to access stored information and/or data. In some embodiments, the processing device 140 may be implemented on a cloud platform. By way of example only, cloud platforms include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, internal clouds, multiple clouds, the like, or any combination thereof. In some embodiments, the processing device 140 may be implemented by a computing device 200 that includes at least one of the components described in fig. 2.

Memory 150 may store data, instructions, and/or other information. In some embodiments, memory 150 may store data retrieved from terminal 130 and/or processing device 140. In some embodiments, memory 150 may store data and/or instructions that may be used or executed by processing device 140 to implement the exemplary methods described in this disclosure. In some embodiments, the Memory 150 may include one or a combination of mass storage, removable storage, volatile Read-write Memory, Read-Only Memory (ROM), and the like. The mass storage may include magnetic disks, optical disks, solid state drives, and the like. The removable memory may include a flash memory drive, a floppy disk, an optical disk, a memory card, a compact disk, a magnetic tape, etc. The volatile read-write Memory may include Random Access Memory (RAM). The RAM comprises a Dynamic random access memory (Dynamic RAM, DRAM), a Double-Rate Synchronous Dynamic random access memory (Double data Rate Synchronous Dynamic RAM, DDR SDRAM), a Static random access memory (Static RAM, SRAM), a Thyristor random access memory (Thyristor RAM, T-RAM), a Zero-capacitance random access memory (Zero-capacitor RAM, Z-RAM) and the like. The ROM may include Mask read only memory (Mask ROM, MROM), Programmable Read Only Memory (PROM), Erasable Programmable random access memory (EPROM), Electrically Erasable Programmable Read Only Memory (EEPROM), optical disc (Compact disc ROM, CD-ROM), digital versatile disc ROM, and the like. In some embodiments, the functionality of the memory 150 may be implemented on a cloud platform. For example, the cloud platform may include one or a combination of private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, interconnected cloud, multiple clouds, and the like.

In some embodiments, the memory 150 may be coupled to the network 120 to communicate with at least one other component (e.g., the processing device 140, the terminal 130, etc.) in the imaging system 100. At least one component in imaging system 100 may retrieve data or instructions stored by memory 150 via network 120. In some embodiments, the memory 150 may be directly connected or in communication with at least one other component in the imaging system 100 (e.g., the processing device 140, the terminal 130, etc.). In some embodiments, the memory 150 may be part of the processing device 140.

FIG. 2 is a schematic diagram of exemplary hardware and software components of a computing device according to some embodiments of the present application.

The computing device 200 may be a general purpose computer or a special purpose computer, both of which may be used to implement the imaging system of the present application. In some embodiments, the processing device 140 may be implemented on the computing device 200 via its hardware, software programs, firmware, or a combination thereof. For example, the computing device 200 may obtain a three-dimensional (3D) image (also referred to as a depth image) and/or a scout image and generate a dose modulation line based on the 3D image and/or scout image. The computing device 200 may also adjust the tube current of the radioactive scanning source 113 based on the dose modulation line.

For example, the computing device 200 includes a Communication (COM) port 250 that connects to a network and facilitates data transfer. Computing device 200 also includes a processor 220 (e.g., a Central Processing Unit (CPU)) in the form of at least one processor for executing program instructions. The exemplary computer platform includes an internal communication bus 210, various forms of program memory and data storage, such as a magnetic disk 270 and Read Only Memory (ROM)230 or Random Access Memory (RAM)240 for storing various data files that are processed and/or transmitted by the computer. The exemplary computer platform also includes program instructions stored in ROM230, RAM 240, and/or other forms of non-transitory storage that can be executed by processor 220. The methods and/or processes disclosed herein may be implemented as program instructions. The computing device also includes input/output devices 260 for supporting input/output with computers and other components, such as a user interface 280. Computing device 200 may also receive programs and data via network communications.

The computing device 200 also includes a hard disk controller in communication with the hard disk, a keyboard controller in communication with the keyboard, a serial interface controller in communication with the serial peripheral device, a parallel interface controller in communication with the parallel peripheral device, a display controller in communication with the display, and the like, or any combination thereof.

By way of example only, only one processor is depicted in computing device 200. However, it should be noted that the computing device 200 in the present application may also include multiple processors. Thus, operations and/or method steps described herein as being performed by one processor may also be performed jointly or separately by multiple processors. For example, in the present application, if a processor of computing device 200 needs to perform operations a and B, it is understood that operations a and B may be performed jointly or separately by two different processors of computing device 200 (e.g., a first processor performing operation a, a second processor performing operation B, or a first processor and a second processor performing operations a and B jointly).

FIG. 3 is a diagram illustrating hardware and/or software components of an exemplary mobile device 300 that may implement certain systems disclosed herein, according to some embodiments of the present application. The functions of the terminal 130 may be implemented on the mobile device 300. As shown in FIG. 3, mobile device 300 includes a communication platform 310, a display 320, a Graphics Processing Unit (GPU) 330, a Central Processing Unit (CPU) 340, I/O350, memory 360, and storage 390. In some embodiments, any other suitable component, including but not limited to a system bus or a controller (not shown), may also be included in mobile device 300. In some embodiments, a mobile operating system 370 (e.g., an iOS system, an Android system, a Windows system, a Phone system, etc.) and at least one application 380 may be loaded from storage 390 into memory 360 for execution by CPU 340. The application 380 includes a browser or any other suitable mobile application software for receiving and rendering image processing-related or other information from the processing device 140. User interaction with the information stream may be enabled through I/O350 and provided to processing device 140 and/or other components of imaging system 100 via network 120.

In the present invention, a computer hardware platform may be used as a hardware platform of at least one element, implementing various modules, units and their functions. The Computer with the user interface may be a Personal Computer (PC), other workstation or terminal device, or a suitably programmed Computer may be a server.

FIG. 4 is a schematic block diagram of an exemplary processing device, shown in accordance with some embodiments of the present application. The processing device 140 includes an acquisition module 410, a processing module 420, and a storage module 430.

The acquisition module 410 is configured to acquire a three-dimensional (3D) image (also referred to as a depth image) and/or a scout image of the object to be scanned. The object to be scanned may be a patient, or a tissue or organ of a patient (e.g., head, neck, chest, abdomen, pelvis, etc.).

In some embodiments, the acquisition module 410 may acquire a 3D image of the object to be scanned from a storage device (e.g., the storage 150, the disk 270, the memory 360, the storage module 430, a storage device external to the imaging system 100 (or referred to as an external storage device)). In some embodiments, the acquisition module 410 may acquire a 3D image of the object to be scanned from a 3D depth camera (e.g., 3D depth camera 112). In some embodiments, the 3D depth camera may take 3D images of the object to be scanned from multiple angles, including but not limited to from the front, top, side, and the like. The 3D depth camera may generate 3D images based on stereo vision techniques, structured light techniques, Time-of-Flight (ToF) techniques, or the like, or any combination thereof. In some embodiments, the acquisition module 410 may send the 3D image to the processing module 420 for processing.

In some embodiments, the acquisition module 410 may acquire a scout image of the object to be scanned from a storage device (e.g., storage 150, disk 270, memory 360, storage module 430, external storage device). In some embodiments, the acquisition module 410 may acquire scout image data from the detector 114 and transmit the scout image data to the processing module 420. The processing module 420 may perform a one-step process (e.g., reconstruct) the scout image data to generate a scout image. In some embodiments, a scout image may be associated with a scout scan. While the radioactive scanning source 113 is in a stationary position and the table 115 is moved along the Z-axis (as shown in fig. 1), a scout scan may be performed by the scanning apparatus 110. For example, if the radioactive scanning source 113 is positioned above the object to be scanned, an anterior-posterior (AP) scout image may be obtained in a scout scan. As another example, if the radioactive scanning source 113 is located on one side of the object, a lateral scout image may be obtained in a scout scan. In some embodiments, the acquisition module 410 may acquire an AP scout image, a lateral scout image, or both. The acquisition module 410 may then transmit the scout image to a processing module for processing.

The processing module 420 is configured to generate a dose modulation line based on the 3D image and/or the scout image. In some embodiments, the processing module 420 may generate a dose modulation line based on both the 3D image and the scout image. As shown in fig. 7 and its description. In some embodiments, the processing module 420 may generate the dose modulation lines based only on the 3D image. As shown in fig. 11 and its description. In some embodiments, the processing module 420 may generate the dose modulation line based only on the scout image. As shown in fig. 13 and its description.

In some embodiments, the dose modulation line or the regional dose modulation line may be a continuous curve, representing a continuous variation of the radiation dose over time or angle. In some embodiments, the dose modulation line or the regional dose modulation line may be discrete, comprising at least one discrete point, each discrete point corresponding to a radiation dose at a particular time or angle. In some embodiments, the dose modulation line or the regional dose modulation line may be a combination of at least one piecewise continuous curve, or a combination of at least one piecewise continuous curve and at least one discrete point. When CT scanning an object to be scanned, the data points of the dose modulation line or the region dose modulation line may represent the degree of modulation of the radiation dose (also referred to as radiation dose modulation, dose modulation or tube current modulation). Radiation dose modulation may be achieved by adjusting the tube current of the radioactive scanning source 113 during a CT scan based on the dose modulation line. For example, during a helical CT scan, the radioactive scanning source 113 may be rotated in the X-Y plane as the table 115 is moved along the Z-axis. Radiation dose modulation may be achieved by adjusting the tube current of the radioactive scanning source 113 in the X-Y plane and along the Z-axis based on the dose modulation line during the helical CT scan.

In some embodiments, the dose modulation line may display the relationship between radiation dose and time during a scan. The radiation dose may be associated with parameters in the scanning device 110 such as tube current-time product, tube current, tube voltage, pitch, effective dose, absorbed dose, etc. In the present application, the tube current-time product refers to the product of the X-ray tube current (e.g., in milliamps) of the radioactive scanning source 113 and the exposure time (e.g., in seconds) per revolution of the CT scanner. In this application, tube voltage refers to the peak energy of an X-ray photon in the X-ray energy spectrum (e.g., in kilovolts). In this application, pitch refers to the ratio of stage translation (in centimeters, stage feed for a 360 gantry rotation) in helical CT to the total nominal collimated X-ray beam width in the Z direction. In the present application, absorbed dose refers to the radiation energy absorbed in a specific region of the object to be scanned in a CT scan. In the present application, the effective dose represents the long-term influence of the radiation energy absorbed by the object to be scanned in the CT scan on the object to be scanned. The time point corresponds to a particular scan angle (e.g., a particular configuration or location of radioactive scanning source 113 in the X-Y plane). During the scanning process, the time points also correspond to a particular slice of the object to be scanned at the respective scanning angle.

In some embodiments, the object to be scanned may be divided into a plurality of slices along the Z-axis. The individual slices are parallel to each other. The thickness of each slice may vary according to at least one different scanning parameter. The thickness of the slice may be set by an operator (e.g., a nurse, radiologist) or imaging system 100. In some embodiments, the radioactive scanning source 113 may be rotated 360 ° around the object to be scanned to acquire CT image data corresponding to each slice of the object to be scanned. As the table 115 is moved along the Z-axis and the radioactive scanning source 113 is rotated around the object, CT image data for a plurality of slices may be acquired.

The storage module 430 is configured to store 3D images, scout images, dose modulation lines, and the like, or any combination thereof. In some embodiments, the storage module 430 may store at least one program and/or instructions that are executed by a processor of the processing device 140 to implement the exemplary methods described herein. For example, the storage module 430 may store programs and/or instructions that are executed by a processor of the processing device 140 to obtain a 3D image and/or a scout image of the object to be scanned, generate dose modulation lines based on the 3D image and/or the scout image, and/or adjust tube currents of the radioactive scanning source 113 based on the dose modulation lines when performing a CT scan on the object to be scanned.

It should be noted that the above description is exemplary only and is not intended to limit the application to the scope of the embodiments illustrated. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, the obtaining module 410 and the processing module 420 may each include separate storage units.

Fig. 5 is an exemplary flow chart for determining a dose modulation line according to some embodiments of the present application.

In 510, the acquisition module 410 may acquire a 3D image (also referred to as a depth image) of the object to be scanned. The object to be scanned may be a patient, or a tissue or organ of a patient (e.g., head, neck, chest, abdomen, pelvis, etc.). The acquisition module 410 may acquire a 3D image of the object to be scanned from a 3D depth camera (e.g., 3D depth camera 112) or a storage device (e.g., memory 150, disk 270, memory 360, storage module 430, external storage device). In some embodiments, the 3D depth camera may take 3D images of the object to be scanned from multiple angles, including but not limited to from the front, top, side, and the like. The 3D depth camera may generate 3D images based on stereo vision techniques, structured light techniques, Time-of-Flight (ToF) techniques, or the like, or any combination thereof.

In some embodiments, the 3D image includes pixels. A certain pixel in the 3D image contains information about a certain corresponding point on the object to be scanned. For example, a certain pixel in the 3D image contains information related to the distance from the 3D depth camera to a certain corresponding point on the object to be scanned, the grey value or color of the corresponding point, etc., or any combination thereof. The distance information of the pixels in the 3D image can be used to determine the 3D contour of the object to be scanned. In some embodiments, the 3D contour comprises a cylinder, an elliptical cylinder, a cuboid, or the like. The 3D contour contains surface structure or shape dimension information of the object to be scanned, such as width, thickness, etc., or any combination thereof.

In some embodiments, the 3D contour of the object to be scanned relates to the radiation dose modulation when performing a CT scan of the object to be scanned. For example, for two patients with different 3D contours, a patient with a larger 3D contour may require a higher radiation dose (or higher tube current) during a CT scan than a patient with a smaller 3D contour in order to obtain two CT images of substantially the same quality for diagnostic purposes.

In some embodiments, prior to performing a CT scan of an object to be scanned, radiation doses corresponding to different points in time (or scan angles) during the scan may be determined. Based on the 3D images described herein, radiation doses corresponding to different points in time during the scan can be determined and modulated.

In 520, the acquisition module 410 acquires a scout image of the object to be scanned. The acquisition module 410 may acquire a scout image of the object to be scanned from a storage device (e.g., storage 150, disk 270, memory 360, storage module 430, an external storage device). The scout image may be an AP scout image or a lateral scout image. In some embodiments, in operation 520, the acquisition module 410 may acquire an AP scout image and a lateral scout image of the object to be scanned.

In some embodiments, the scout image contains attenuation data of the object to be scanned. The attenuation data in the scout image can be used to estimate the attenuation characteristics of the object to be scanned. The attenuation properties of the object to be scanned relate to the radiation dose modulation when performing a CT scan of the object to be scanned. For example, hard tissue (e.g., bone) that appears as a brighter area in the scout image has a higher attenuation coefficient and requires a higher radiation dose (corresponding to a higher tube current) than soft tissue (e.g., lung) that appears as a darker area in the scout image.

In some embodiments, the scout image corresponds to a scanning protocol. The scanning protocol is associated with an anatomical region of the subject to be scanned, such as the head, neck, chest, etc. For example, the scanning protocol may include a head scanning protocol, a neck scanning protocol, a chest scanning protocol, and the like. In some embodiments, the scan protocol includes scan parameters such as voltage of the radioactive scan source 113, tube current-time product, beam width, gantry rotation time, reconstruction kernel, etc., or any combination thereof. In some embodiments, the scan protocol contains a radiation dose parameter and whether the dose modulation line parameter is used to adjust the radiation dose during the scan. Different scan protocols may have the same or different scan parameters. In some embodiments, the processing module 420 may determine the radiation dose for the CT scan based on the attenuation characteristics reflected in the scout image and the scan protocol corresponding to the scout plate.

In some embodiments, the scout image may be used to estimate the shape size of the object to be scanned. For example, the AP scout can be used to estimate the width (also referred to as X-coordinate values) of each slice of the object to be scanned. For another example, the lateral scout image may be used to estimate the thickness (also referred to as Y-coordinate values) of each slice of the object to be scanned.

In some embodiments, prior to performing a CT scan of an object to be scanned, radiation doses corresponding to different points in time (or scan angles) during the scan may be determined. The radiation doses corresponding to different points in time during the scan can be determined and modulated based on the scout images described herein.

In 530, the processing module 420 may generate a dose modulation line based on the 3D image and/or the scout image. In some embodiments, the processing module 420 may generate a dose modulation line based on both the 3D image and the scout image (e.g., see fig. 7 and description thereof). In some embodiments, the processing module 420 may generate the dose modulation lines based only on the 3D image (e.g., see fig. 11 and description thereof). In some embodiments, the processing module 420 may generate a dose modulation line based only on the scout image (e.g., see fig. 13 and description thereof).

When performing a CT scan of an object to be scanned, the dose modulation line may characterize the degree of modulation of the radiation dose (also referred to as radiation dose modulation, or tube current modulation). Radiation dose modulation may be achieved by adjusting the tube current of the radioactive scanning source 113 during a CT scan based on the dose modulation line. For example, during a helical CT scan, the radioactive scanning source 113 may be rotated in the X-Y plane as the table 115 is moved along the Z-axis. Radiation dose modulation may be achieved by adjusting the tube current of the radioactive scanning source 113 in the X-Y plane and along the Z-axis based on the dose modulation line during the helical CT scan.

In some embodiments, the dose modulation line may display the relationship between radiation dose and time during a scan. The radiation dose may be associated with parameters in the scanning device 110 such as tube current-time product, tube current, tube voltage, pitch, effective dose, absorbed dose, etc. The scan time or point in time corresponds to a particular scan angle (e.g., a particular configuration or position of the radioactive scanning source 113 in the X-Y plane). The points in time during the scan may also correspond to particular slices of the object to be scanned at the respective scan angles.

It should be noted that the foregoing description is provided for illustrative purposes only, and is not intended to limit the scope of the present application. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, operation 510 may be performed after operation 520, or operation 510 and operation 520 may be performed simultaneously. As another example, either operation 510 or operation 520 may be omitted from flow 500. As another example, the process 500 includes an operation to generate a 3D image and/or a scout image based on image data associated with the 3D image and/or the scout image.

FIG. 6 is a schematic block diagram of a processing module shown in accordance with some embodiments of the present application. The processing module 420 includes an acquisition unit 610, a training unit 620, and a dose modulation line generation unit 630.

The acquisition unit 610 is configured to acquire a three-dimensional (3D) image (also referred to as a depth image) and a scout image of an object to be scanned. The acquisition unit 610 may acquire a 3D image and a scout image of an object to be scanned from a storage device (e.g., the storage 150, the disk 270, the memory 360, the storage module 430, an external storage device). .

In some embodiments, the scout image includes attenuation data of the object to be scanned. The attenuation data in the scout image can be used to estimate the attenuation characteristics of the object to be scanned. The attenuation characteristics of the object to be scanned relate to the radiation dose modulation when performing a CT scan of the object to be scanned. For example, hard tissue (e.g., bone) that appears as a brighter region in the scout image may have a higher attenuation coefficient during the CT scan and require a higher radiation dose (corresponding to higher tube current) than soft tissue (e.g., lung) that appears as a darker region in the scout image.

In some embodiments, prior to performing a CT scan of an object to be scanned, radiation doses corresponding to different points in time (or scan angles) during the scan may be determined. Based on the 3D images and scout images described herein, radiation doses corresponding to different points in time during the scan can be determined and modulated.

The training unit 620 is configured to train the dose modulation line generation model. The training unit 620 may train the dose modulation line generation model based on a training data set. The training data set includes a plurality of sample CT images, a plurality of sample 3D images, and a plurality of sample scout images. The dose modulation line generation model may be an Artificial Neural Network (ANN) model, such as a Convolutional Neural Network (CNN) model, a Recurrent Neural Network (RNN) model, or the like. In some embodiments, the dose modulation line generation model may be sent to a storage device (e.g., memory 150, disk 270, memory 360, storage module 430, external storage device) for storage. In some embodiments, the dose modulation line generation model may be a generic model or a dedicated model. The generic model may be used to generate dose modulation lines corresponding to multiple types of 3D images and scout images of multiple objects to be scanned or multiple regions of objects to be scanned. The generic model may be trained based on a plurality of sample 3D images, a plurality of sample CT images, and a plurality of sample scout images associated with different regions of a certain class of objects to be scanned. In some embodiments, the plurality of sample 3D images, the plurality of sample CT images, and the plurality of sample scout images used for training may collectively cover the entire human body or the entire upper body. For example, the general model may be a general model for all ages and body types, and the general model may generate a dose modulation line for any at least one body region (e.g., part, chest, neck, abdomen, pelvis, legs, etc.) of the subject to be scanned based on a 3D image and scout image of the subject to be scanned at any age and in any body type. The training data for training the whole-body general model has no limitation on age, body type, and body region, and may be a plurality of sample 3D images, a plurality of sample CT images, and a plurality of sample scout images of infants, young children, adults, elderly, men, women, fatteners, and slimmers, which are associated with at least one body region. The dedicated model corresponds to a specific object or body region to be scanned. For example, a brain-specific model may be used to generate dose modulation lines for a brain region (or region dose modulation lines elsewhere in this application) based on the 3D image and the scout image. The brain-specific model may be trained by a training data set corresponding to the brain. As another example, a model specific to the brain of a child (e.g., a child aged 1-6) may be specifically adapted to generate dose modulation lines for a brain region of the child based on a 3D image and a scout image of the child. The pediatric brain specific model may be trained via a training data set corresponding to a pediatric brain.

The dose modulation line generating unit 630 is configured to generate a dose modulation line. The dose modulation line generation unit 630 may generate a dose modulation line based on the 3D image and the scout image acquired by the acquisition unit 610 and the dose modulation line generation model trained by the training unit 620.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, training unit 620 may be omitted. The dose modulation line generation unit 630 may retrieve a dose modulation line generation model from a model library. The library includes a plurality of generic and/or specific dose modulation line generation models. The model library may be stored in a storage device (e.g., storage 150, disk 270, memory 360, storage module 430, external storage device) and accessible by the data processing device 140 or components thereof via, for example, the internet 120.

Fig. 7 is an exemplary flow chart for determining a dose modulation line based on a 3D image and a scout image according to some embodiments of the present application.

In 710, an acquisition unit 610 may acquire a 3D image of an object to be scanned. The acquisition unit 610 may acquire a 3D image of an object to be scanned from a storage device (e.g., the storage 150, the disk 270, the memory 360, the storage module 430, an external storage device). In some embodiments, the acquisition unit 610 may acquire a 3D image of an object to be scanned from a 3D depth camera (e.g., 3D depth camera 112). In some embodiments, the 3D depth camera may take 3D images of the object to be scanned from multiple angles, including but not limited to from the front, bottom, sides, and the like. The 3D depth camera may generate 3D images based on stereoscopic vision techniques, structured light techniques, Time-of-Flight (ToF) techniques, or the like, or any combination thereof.

In some embodiments, the 3D image includes pixels. A certain pixel in the 3D image contains information about a certain corresponding point on the object to be scanned. For example, a certain pixel in the 3D image contains information related to the distance from the 3D depth camera to a certain corresponding point on the object to be scanned, the grey value or color of the corresponding point, etc., or any combination thereof. The distance information of the pixels in the 3D image can be used to determine the 3D contour of the object to be scanned. In some embodiments, the 3D contour comprises a cylinder, an elliptical cylinder, a cuboid, or the like. The 3D profile contains surface structure or shape dimension information of the object to be scanned, such as width, thickness, etc., or any combination thereof.

In 720, the acquisition unit 610 may acquire a scout image of the object to be scanned. The acquisition unit 610 may acquire a scout image of the object to be scanned from a storage device (e.g., the storage 150, the disk 270, the memory 360, the storage module 430, an external storage device). The scout image may be an AP scout image or a lateral scout image. In some embodiments, in operation 720, the acquisition unit 610 may acquire an AP scout image and a lateral scout image of the object to be scanned.

In some embodiments, the 3D image obtained in operation 710 and the scout image obtained in operation 720 may be derived based on data acquired in one or more scans from the same angle or different angles. It should be noted that scout images can be used to estimate the attenuation characteristics and shape size of the object to be scanned. In some embodiments, the shape size of the object to be scanned may be estimated based on the 3D image rather than the scout image.

In 730, the dose modulation line generation unit 630 may obtain a dose modulation line generation model. The dose modulation line generation unit 630 may obtain a dose modulation line generation model from a storage device (e.g., memory 150, disk 270, memory 360, storage module 430, external storage device). The dose modulation line generation model may be pre-trained by the model training unit 620. A detailed description of generating a dose modulation line generation model may be found elsewhere in this application (e.g., fig. 8 and its description).

In 740, the dose modulation line generating unit 630 may generate a model using the dose modulation lines based on the 3D image and the scout image of the object to be scanned to generate dose modulation lines related to the CT scan of the object to be scanned. More specifically, a 3D image and a scout image of the object to be scanned may be input into a pre-trained dose modulation line generation model by the dose modulation line generation unit 630. In response to the input 3D image and scout image, the dose modulation line generation model generates as output a dose modulation line.

In some embodiments, the dose modulation line may display the relationship between radiation dose and time during a scan. The radiation dose may be associated with parameters in the scanning device 110 such as tube current-time product, tube current, tube voltage, pitch, effective dose, absorbed dose, etc. The scan time or point in time corresponds to a particular scan angle (e.g., a particular configuration or position of the radioactive scanning source 113 in the X-Y plane). The points in time during the scan may also correspond to particular slices of the object to be scanned at the respective scan angles. In some embodiments, the dose modulation line is a continuous curve representing a continuous variation of radiation dose over time or angle. In some embodiments, the dose modulation line may be discrete, comprising at least one discrete point, each discrete point corresponding to a radiation dose at a particular time or angle. In some embodiments, the dose modulation line may be a combination of at least one piecewise continuous curve, or a combination of at least one piecewise continuous curve and at least one discrete point.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, operation 710 may be performed after operation 720, or operation 710 and operation 720 may be performed simultaneously. As another example, the process 700 includes an operation of generating a 3D image and/or a scout image based on image data associated with the 3D image and/or scout image.

Fig. 8-a and 8-B are an exemplary flow chart for training a dose modulation line generating model according to some embodiments of the present application.

In 810, the training unit 620 may obtain an initial model. The initial model may be an Artificial Neural Network (ANN) model, such as a Convolutional Neural Network (CNN) model, a Recurrent Neural Network (RNN) model, or the like. The initial model includes a plurality of initial parameters. In some embodiments, the initial model may be predefined. For example, the internal structure or initial parameters of the initial model may be predefined according to at least one characteristic (e.g., size, thickness, complexity) of a particular object to be scanned (e.g., chest, head) associated with the initial model.

In 820, training unit 620 may obtain a training data set. In some embodiments, training unit 620 may obtain the training data set from a storage device (e.g., storage 150, disk 270, memory 360, storage module 430, an external storage device). The training data set includes a plurality of sample CT images, a plurality of sample 3D images, and a plurality of sample scout images. One of the plurality of sample CT images corresponds to one of the plurality of sample 3D images and one of the plurality of sample scout images. Here, the correspondence between the CT image, the 3D image, and the scout image indicates that these sample images represent the same region of the object to be scanned. In short, one sample CT image and a sample 3D image and a sample scout image corresponding thereto can be specified as one sample image group. Thus, the training data set comprises a plurality of sets of sample images. In some embodiments, one set of sample images is associated with the same object to be scanned or the same region of the object to be scanned. In some embodiments, the plurality of sets of sample images are associated with the same or different objects to be scanned, or with the same or different regions of at least one object to be scanned.

In 830, the training unit 620 may train the initial model based on the training data set to generate a dose modulation line generation model. For example, in case a plurality of sets of sample images in the training dataset are associated with the same region of at least one object to be scanned (e.g. brain, head, chest, legs), a dedicated dose modulation line generating model may be generated. For another example, where multiple sets of sample images are associated with different regions of the object to be scanned, a generic dose modulation line generation model may be generated. The training unit 620 may generate the dose modulation line generation model by updating a plurality of initial parameters. In some embodiments, as shown in FIG. 8B, operation 830 may be divided into operations 831-833.

In 831, for a first sample image group of the training data set, the training unit 620 may determine a first sample dose modulation line based on a first sample CT image of the first sample image group. The first sample CT image includes attenuation data. In some embodiments, the training unit 620 may generate a first sample dose modulation line corresponding to the first sample CT image based on attenuation data contained in the first sample CT image. In some embodiments, the training unit 620 can search for and retrieve a first sample dose modulation line corresponding to a first sample CT image of the first sample image set from a storage device (e.g., the storage 150, the disk 270, the memory 360, the storage module 430, an external storage device).

At 832, the training unit 620 may generate a first predicted dose modulation line using the initial model based on the first sample 3D image and the first sample scout image of the first sample image group.

In 833, the training unit 620 may train the initial model by minimizing a difference between the first sample dose modulation line and the first predicted dose modulation line corresponding thereto. Accordingly, the training unit 620 may update at least one of the plurality of initial model parameters of the initial model and generate a first updated model based on the updated initial parameters.

Operation 831-833 may be performed repeatedly. In some embodiments, the difference between a sample dose modulation line (e.g., a first sample dose modulation line and a subsequent sample dose modulation line) and a corresponding predicted dose modulation line may be evaluated according to a loss function. The loss functions include, but are not limited to, an L1 norm loss function, an L2 norm loss function, a quadratic cost function, a cross entropy loss function, a log likelihood cost function, and the like, or any combination thereof. In some embodiments, the initial model may be updated by different strategies. For example, if the difference between the sample dose modulation line and the predicted dose modulation line in the current iteration is less than a threshold (e.g., the difference determined in the previous iteration), some or all of the parameters of the initial model may be updated. If the difference between the sample dose modulation line and the predicted dose modulation line in the current iteration is greater than the difference in the previous iteration, the initial model will not be updated in this iteration. In some embodiments, when all of the multiple sample image sets in the training data are traversed or the preset condition is satisfied, the training unit 620 may terminate the iteration of operations 831-. Exemplary preset conditions include a difference between a sample dose modulation line and a predicted dose modulation line corresponding thereto being less than a preset threshold in at least one successive iteration.

Compared with the traditional method (for example, the attenuation data in the scout image is used for estimating the shape size of the object to be scanned, and then the dosage modulation line is determined by combining the attenuation data and the shape size), the dosage modulation line generation model trained based on the method can obtain the dosage modulation line with higher accuracy. This is because, in the process of training the dose modulation line generation model using a set of sample image groups as training samples, the dose modulation line during actual scanning (i.e., the above-mentioned sample dose modulation line) can be accurately calculated based on the CT value information included in the sample CT images, and when the quality of the sample CT images is better, the dose modulation line generation model updated based on the corresponding dose modulation line is better. In addition, compared with the positioning image, the shape and size or the 3D contour of the object to be scanned can be estimated more accurately based on the 3D image, and the positioning image contains attenuation data of the object to be scanned which is not contained in the 3D image. It should be noted, however, that although in some cases it may be advantageous to combine the 3D image and the scout image as input, it is within the scope of the present application to determine the dose modulation line based on the 3D image alone or the scout image alone.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, operation 810 may be performed after operation 820, or operation 810 and operation 820 may be performed simultaneously.

FIG. 9 is a schematic diagram of an architecture of a dose modulation line generation model according to some embodiments of the present application. As shown in fig. 9, the dose modulation line generation model may be a Convolutional Neural Network (CNN) model. The CNN model includes an input layer, a hidden layer, and an output layer, and each node in fig. 9 can simulate a neuron. The hidden layers include convolutional layers, aggregate layers, and/or fully-connected layers (not shown in fig. 9). After the CNN model is trained by, for example, the process 800 shown in fig. 8, the CNN model is configured to generate a dose modulation line in response to its inputs. In some embodiments, the input to the CNN includes a scout (e.g., an AP scout or a lateral scout) and a 3D image of the object to be scanned. In some embodiments, the input to the CNN includes two scout images (e.g., AP scout image and lateral scout image, for example) and a 3D image of the object to be scanned.

In some embodiments, the dose modulation lines may be generated based on a dose modulation line generation model associated with an anatomical region of the object to be scanned. The anatomical region of the subject to be scanned includes the head, neck, chest, etc., or any combination thereof. In some embodiments, the anatomical region of the subject to be scanned may be automatically determined based on a scanning protocol set by the imaging system 100 or an operator (e.g., nurse, radiologist). In some embodiments, the anatomical region of the object to be scanned may be manually marked in the 3D image and/or scout image of the object to be scanned by an operator (e.g., a nurse, radiologist).

For example, an operator (e.g., a nurse, radiologist) may perform a scout scan of a patient to acquire AP and/or lateral scout images of the patient, take 3D images of the patient, and select a chest scan protocol. In some embodiments, the processing device 140 may automatically determine the patient's chest as the anatomical region on which CT is performed based on the selected scan protocol. In some embodiments, the operator may manually mark a region including the patient's chest in the 3D image and/or scout image as an anatomical region on which CT is performed. In some embodiments, the anatomical region on which the CT scan is performed may be determined based on the selected scan protocol and any manual adjustments or related inputs by the operator. The CNN model may generate a dose modulation line 910 associated with a chest CT scan (as shown in fig. 9) based on the AP and/or lateral scout image and the 3D image. In some embodiments, the CNN model may generate a plurality of dose parameters and their corresponding angles in the output layer, and may construct (e.g., by interpolation) a dose modulation line 910 based on the plurality of doses and angles.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, the dose modulation line generation model may be another type of model including, but not limited to, a support vector machine, a decision tree, other types of ANN models, a deep learning model, a bayesian network, etc., or any combination thereof.

FIG. 10 is a schematic block diagram of a processing module shown in accordance with some embodiments of the present application. The processing module 420 comprises an acquisition unit 1010, a 3D contour determination unit 1020 and a dose modulation line generation unit 1030.

The processing module 420 comprises an acquisition unit 1010, a 3D contour determination unit 1020 and a dose modulation line generation unit 1030.

The acquisition unit 1010 is configured to acquire a three-dimensional (3D) image (also referred to as a depth image) of an object to be scanned. In some embodiments, the acquisition unit 1010 may acquire a 3D image of the object to be scanned from a storage device (e.g., the memory 150, the disk 270, the memory 360, the storage module 430, an external storage device). In some embodiments, the acquisition unit 1010 may acquire a 3D image of an object to be scanned from an imaging device (e.g., a 3D depth camera). .

In some embodiments, the 3D image may be captured by a 3D depth camera. The 3D contour of the object to be scanned may be estimated based on the 3D image. The 3D depth camera may generate 3D images based on stereo vision techniques, structured light techniques, Time-of-Flight (ToF) techniques, or the like, or any combination thereof. In some embodiments, the 3D depth camera may take 3D images of the object to be scanned from multiple angles, including but not limited to from the front, top, side, and the like.

The 3D contour determination unit 1020 is configured to determine a 3D contour of the object to be scanned based on the 3D image. The 3D image includes pixels. A certain pixel in the 3D image contains information about a certain corresponding point on the object to be scanned. For example, a certain pixel in the 3D image contains information related to the distance from the 3D depth camera to a certain corresponding point on the object to be scanned, the grey value or color of the corresponding point, etc., or any combination thereof. The distance information of the pixels in the 3D image can be used to determine the 3D contour of the object to be scanned. In some embodiments, the 3D contour comprises a cylinder, an elliptical cylinder, a cuboid, or the like. The 3D contour contains surface structure or shape dimension information of the object to be scanned, such as width, thickness, etc., or any combination thereof. In some embodiments, an initial 3D contour may be generated. The initial 3D contour is a geometric shape with a number of default parameters. A plurality of parameters of the initial 3D contour may be determined based on a 3D image of the object to be scanned. The initial 3D contour may be updated based on the plurality of parameters to generate a 3D contour of the object to be scanned.

The dose modulation line generating unit 1030 is configured to generate dose modulation lines based on a 3D image of an object to be scanned. For each slice of the object to be scanned, the dose modulation line generation unit 1030 may first determine the radiation dose. The radiation dose may be determined based on the 3D contour (e.g., shape, thickness) of the object to be scanned and/or the organ or tissue within the slice of the object to be scanned. The dose modulation line generating unit 1030 may generate a dose modulation line based on a plurality of radiation doses corresponding to a plurality of slices of the object to be scanned. During a CT scan, the dose modulation line may be used as a reference to perform radiation dose modulation, for example, by adjusting the tube current of the radioactive scanning source 113.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, at least one unit of the processing module 420 may each include a separate storage unit.

Fig. 11 is an exemplary flow chart for determining a dose modulation line based on a 3D image according to some embodiments of the present application.

In 1110, the acquisition unit 1010 may acquire a 3D image of an object to be scanned. In some embodiments, the obtaining unit 610 may obtain a 3D image of the object to be scanned from a storage device (e.g., the storage 150, the disk 270, the memory 360, the storage module 430, an external storage device). In some embodiments, the acquisition unit 1010 may acquire a 3D image of an object to be scanned from an imaging device (e.g., a 3D depth camera).

In some embodiments, the 3D image may be captured by a 3D depth camera. The 3D contour of the object to be scanned may be estimated based on the 3D image. The 3D depth camera may generate 3D images based on stereo vision techniques, structured light techniques, Time-of-Flight (ToF) techniques, or the like, or any combination thereof. In some embodiments, the 3D depth camera may take 3D images of the object to be scanned from multiple angles, including but not limited to from the front, bottom, sides, and the like.

In 1120, the 3D contour determination unit 1020 is configured to determine a 3D contour of the object to be scanned based on the 3D image. A certain pixel in the 3D image contains information about a certain corresponding point on the object to be scanned. For example, a certain pixel in the 3D image contains information related to the distance from the 3D depth camera to a certain corresponding point on the object to be scanned, the grey value or color of the corresponding point, etc., or any combination thereof. The distance information of the pixels in the 3D image can be used to determine the 3D contour of the object to be scanned. In some embodiments, the 3D contour comprises a cylinder, an elliptical cylinder, a cuboid, or the like. The 3D contour contains surface structure or shape dimension information of the object to be scanned, such as width, thickness, etc., or any combination thereof. In some embodiments, the scout image may also be used to estimate the 3D contour of the object to be scanned. For example, a 3D profile of the object to be scanned may be estimated based on attenuation data of the object to be scanned in the scout image. However, since the scout image is a 2D image corresponding to a fixed scan angle (usually vertically downward), the shape or size of the object to be scanned cannot be accurately estimated, especially in the lateral and oblique directions. To address this issue, 3D images may be used to generate more accurate shape dimensions or 3D contours of the object to be scanned. It should be noted that although a 3D image may show a slight advantage over a scout image in some cases, it is also within the scope of the present application to determine the 3D contour based on the scout image alone or together with the 3D image.

In 1130, the dose modulation line generation unit 1030 may determine a radiation dose corresponding to each slice of the object to be scanned based on the 3D contour of the object to be scanned. For example, the object to be scanned may be divided into slices along the Z-axis. The multiple slices are parallel to each other. In some embodiments, a slice may correspond to a particular time and a particular scan angle during a scan. For each slice of the object to be scanned, the shape dimensions (e.g., thickness, width, length) of the slice may be determined based on the 3D contour of the object to be scanned. For example, if the 3D contour of the object to be scanned is an elliptical cylinder, the cross-section of each slice may be elliptical. The size or at least one other parameter of the elliptical slice may be determined based on the 3D contour of the object to be scanned.

In some embodiments, the radiation dose corresponding to each slice may be determined based on the shape size of the slice. For example, a mapping table including a relationship between radiation dose and size (e.g., thickness) of a slice may be predetermined and stored in a storage device (e.g., memory 150, disk 270, memory 360, storage module 430, external storage device). The dose modulation line generation unit 1030 may search the mapping table and determine a radiation dose corresponding to each of the plurality of slices based on the shape size of the slice.

In 1140, the dose modulation line generating unit 1030 may generate dose modulation lines based on a plurality of radiation doses corresponding to a plurality of slices of the object to be scanned. After the dose modulation line generation unit 1030 determines a plurality of radiation doses for a plurality of slices, the dose modulation line generation unit 1030 may arrange the determined plurality of radiation doses in order of the scan angle (or the direction of the Z axis) to generate a dose modulation line. During a CT scan, the dose modulation line may serve as a reference for performing radiation dose modulation, for example, by adjusting the tube current of the radioactive scanning source 113. In some embodiments, the dose modulation line is a continuous curve representing a continuous variation of radiation dose over time or angle. In some embodiments, the dose modulation line may be discrete, comprising at least one discrete point, each discrete point corresponding to a radiation dose at a particular time or angle. In some embodiments, the dose modulation line may be a combination of at least one piecewise continuous curve, or a combination of at least one piecewise continuous curve and at least one discrete point.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example,

operations

1130 and 1140 may be combined into one operation.

FIG. 12 is a schematic block diagram of a processing module shown in accordance with some embodiments of the present application. The processing module 420 comprises an acquisition unit 1210, a segmentation unit 1220 and a dose modulation line generation unit 1230.

The acquisition unit 1210 is configured to acquire a scout image of an object to be scanned. In some embodiments, the obtaining unit 1210 may obtain a scout image of the object to be scanned from a storage device (e.g., the storage 150, the disk 270, the memory 360, the storage module 430, an external storage device). In some embodiments, the acquisition unit 1210 may acquire a scout image of the object to be scanned from an imaging device (e.g., a CT scanner, a PET-CT scanner). In some embodiments, the scout image may be an AP scout image or a lateral scout image. In some embodiments, acquisition unit 610 may acquire an AP scout image and a lateral scout image of the object to be scanned.

In some embodiments, the acquisition unit 1210 is configured to acquire a reference 3D image. In some embodiments, the reference 3D image may be associated with an object to be scanned. For example, the reference 3D image may be a recent image of a reference object to be scanned (e.g., the same type or region) that is the same as or similar to the object to be scanned. More specifically, the reference object to be scanned and the object to be scanned may have the same or similar physical conditions, such as the same or similar 3D contour shape size, the same internal tissue or organ, etc., or any combination thereof.

The segmentation unit 1220 is configured to segment a scout image of the object to be scanned into at least one region of interest. Each of the at least one region of interest corresponds to an anatomical region of the subject to be scanned, such as the head, neck, chest, etc. In some embodiments, the segmentation unit 1220 may automatically segment the scout image into at least one region of interest based on an image segmentation algorithm. Exemplary image segmentation algorithms include a thresholding algorithm, a clustering algorithm, a histogram-based algorithm, a region growing algorithm, or the like, or any combination thereof. In some embodiments, an operator (e.g., a nurse, radiologist) may manually segment the scout image into at least one region of interest. In some embodiments, the scout image may be segmented into the at least one region of interest in a semi-automatic manner, for example, the segmentation unit 1220 may be roughly segmented automatically and then manually adjusted by an operator, or the operator may be manually selected initially and then accurately segmented by the segmentation unit 1220.

The dose modulation line generating unit 1230 is configured to generate a dose modulation line. The dose modulation line generation unit 1230 may determine a reference scout image corresponding to the region of interest and determine a regional dose modulation line based on the reference scout image. The dose modulation line generating unit 1230 may combine the plurality of regional dose modulation lines to generate a dose modulation line. An exemplary dose modulation line can be seen, for example, in fig. 15.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, at least one unit in the processing module 420 may each include a separate storage unit.

Fig. 13 is an exemplary flow chart for determining a dose modulation line based on a scout image according to some embodiments of the present application.

In 1310, the acquisition unit 1210 may acquire a scout image of the object to be scanned. The obtaining unit 1210 may obtain a scout image of the object to be scanned from a storage device (e.g., the storage 150, the disk 270, the memory 360, the storage module 430, an external storage device). In some embodiments, the scout image may be an AP scout image or a lateral scout image. In some embodiments, in operation 1310, the acquisition unit 1210 may acquire an AP scout image and a lateral scout image of the object to be scanned.

In 1320, the segmentation unit 1220 segments a scout image of the object to be scanned to determine at least one region of interest on the scout image. Each of the at least one region of interest corresponds to an anatomical region of the subject to be scanned, such as the head, neck, chest, etc. In some embodiments, the segmentation unit 1220 may automatically segment the scout image based on an image segmentation algorithm. Exemplary image segmentation algorithms include a thresholding algorithm, a clustering algorithm, a histogram-based algorithm, a region growing algorithm, or the like, or any combination thereof. In some embodiments, an operator (e.g., a nurse, radiologist) may manually segment the scout image. In some embodiments, the scout image may be segmented in a semi-automatic manner, for example, the segmentation unit 1220 may be roughly segmented automatically and then manually adjusted by an operator, or the operator may select the segmentation unit 1220 manually and then precisely segment the segmentation unit 1220.

At 1330, the dose modulation line generation unit 1230 may determine at least one regional dose modulation line, each of the at least one regional dose modulation line corresponding to one of the at least one region of interest of the scout image. In some embodiments, the dose modulation line or the regional dose modulation line may be a continuous curve, representing a continuous variation of the radiation dose over time or angle. In some embodiments, the dose modulation line or the regional dose modulation line may be discrete, comprising at least one discrete point, each discrete point corresponding to a radiation dose at a particular time or angle. In some embodiments, the dose modulation line or the regional dose modulation line may be a combination of at least one piecewise continuous curve, or a combination of at least one piecewise continuous curve and at least one discrete point. A detailed description of the determination of the at least one regional dose modulation line can be found elsewhere in the present application (e.g., fig. 14 and its description).

In 1340, the dose modulation line generation unit 1230 may generate a dose modulation line related to a CT scan of the object to be scanned based on the at least one region dose modulation line. In operation 1320, after determining the at least one regional dose modulation line, the dose modulation line generation unit 1230 may combine the at least one regional dose modulation line to generate a dose modulation line. In some embodiments, a smoothing process may be performed on the generated dose modulation lines to avoid abrupt changes in radiation dose corresponding to boundary points of the regional dose modulation lines.

In some embodiments, the dose modulation line determined in 1340 may serve as a reference dose modulation line for checking whether the set scan protocol is accurate. For example, an initial scan protocol may be set for the object to be scanned by an operator (e.g., a nurse, a radiologist), or automatically by the imaging system 100, prior to operation 1310. The acquisition unit 1210 may acquire a scout image of the object to be scanned based on an initial scanning protocol, and the dose modulation line generation unit 1230 may determine an initial dose modulation line based on the scout image and the initial scanning protocol. After the imaging system 100 determines the reference dose modulation line based on operations 1310-1340 described above, the initial dose modulation line and the reference dose modulation line may be compared. If the difference between the initial dose modulation line and the reference dose modulation line is greater than a preset threshold, the imaging system 100 alerts an operator (e.g., nurse, radiologist) that the initial scan protocol is inaccurate. For example, the imaging system 100 may alert the operator by voice or by displaying a prompt message on the operation interface. In some embodiments, the initial scan protocol may be modified manually by an operator or automatically by the imaging system 100 based on the comparison. For example, the imaging system 100 may automatically modify the scan protocol based on the comparison and display the modification on the operator interface for confirmation by the operator. For another example, after learning the prompt message that the scanning protocol is inaccurate, the operator may manually check and correct the scanning protocol on the operation interface. Thus, the imaging system 100 can prompt the operator in time and make corrections when the scanning protocol is inaccurate, improving the accuracy of the dose modulation line. The dose modulation line with high accuracy further ensures the quality of the subsequently reconstructed CT image, thereby providing more accurate diagnosis information.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, two scout images (e.g., an AP scout image and a lateral scout image) may be acquired in operation 1310.

Fig. 14 is an exemplary flow chart for determining a regional dose modulation line according to some embodiments of the present application.

In 1410, the dose modulation line generation unit 1230 may extract features of each of at least one region of interest of a topogram of the object to be scanned. The characteristics of the region include texture characteristics, shape dimensions, spatial characteristics, and the like, or any combination thereof. In some embodiments, different regions of the topogram of the object to be scanned have different characteristics. In some embodiments, the dose modulation line generation unit 1230 may extract features of each of the at least one region of interest based on a feature extraction technique. The texture features may be extracted according to texture feature extraction techniques, such as spatial texture feature extraction techniques and spectral texture feature extraction techniques. The shape size may be based on, for example, contour-based techniques and region-based techniques. The spatial features may be extracted according to spatial feature extraction techniques, such as absolute spatial location based techniques and relative spatial location based techniques.

In 1420, the dose modulation line generation unit 1230 may determine a reference scout image for each of the at least one region of interest based on the extracted features. Based on the features extracted in operation 1410, each of the at least one region of interest may be represented by a feature vector. In some embodiments, the plurality of candidate position images may be stored in a storage device (e.g., memory 150, disk 270, memory 360, storage module 430, external storage device), and each of the plurality of candidate position images may be represented by a feature vector. A candidate scout image for a region may be designated as a reference scout image corresponding to the region if the feature vectors of the candidate scout image match the feature vectors of the region to an acceptable degree. For example only, a scout image of the chest of the subject to be scanned may correspond to the first feature vector. The plurality of candidate scouts may correspond to a plurality of regions including a head, a chest, a neck, an abdomen, a pelvis, a leg, and the like. In some embodiments, a reference image having a second feature vector matching a first feature vector of a scout of a subject to be scanned may be selected from a plurality of candidate scouts. The reference image includes a breast that is similar to the breast in the scout image. As used herein, matching a candidate scout image to an acceptable degree with an area indicates that the difference between the candidate scout image and the area is below a threshold. The difference may be evaluated based on at least one eigenvalue of the candidate scout image and the eigenvector of the region.

In 1430, the dose modulation line generation unit 1230 may determine regional dose modulation lines for each of the at least one region of interest based on the corresponding reference scout image. The respective reference scout image may be associated with a scanning protocol, such as a head scanning protocol, a neck scanning protocol, a chest scanning protocol, and the like. In some embodiments, the scan protocol includes scan parameters such as voltage of the radioactive scanning source 113, tube current-time product, beam width, gantry rotation time, reconstruction kernel, etc., or any combination thereof. Different scan protocols may have the same or different scan parameters. For example, different scan protocols may have some of the same scan parameters and some of the different scan parameters. In some embodiments, the dose modulation line generation unit 1230 may determine the regional dose modulation lines for each of the at least one region of interest based on at least one scan parameter of the scan protocol associated with the corresponding reference scout image. In some embodiments, for each of the at least one region of interest, the dose modulation line generation unit 1230 may acquire at least one image parameter (e.g., gray value, mean gray value, contrast of pixels) of the region in the scout image of the object to be scanned, and determine a regional dose modulation line for the region based on the at least one image parameter of the region and at least one scan parameter of the scan protocol associated with the corresponding reference scout image.

In some embodiments the dose modulation line generation unit 1230 may determine a regional dose modulation line for each of the at least one region of interest based on a dose modulation line generation model (e.g., see fig. 7 and description thereof). As used herein, the corresponding reference scout image and/or reference 3D image determined in operation 1420 (e.g., the reference 3D image acquired by the acquisition unit 1210, see the associated description of the acquisition unit 1210) may be designated as an input to the dose modulation line generation model. The dose modulation line generation model may generate a regional dose modulation line for each of the at least one region of interest based on the corresponding reference scout image and the reference 3D image.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, operation 1430 may be divided into a set of sub-operations. The dose modulation line generating unit 1230 may in a sub-operation determine a scan protocol associated with the reference scout image and in another sub-operation generate regional dose modulation lines based on at least one parameter of the scan protocol. As another example, operation 1430 may be divided into different sets of sub-operations. The dose modulation line generating unit 1230 may obtain the dose modulation line generation model and the reference 3D image in the first sub-operation, and generate the region dose modulation line based on the dose modulation line generation model, the reference 3D image, and the reference scout image in the second sub-operation.

As shown in fig. 15, the scanning device 110 may perform a whole-body CT scan on a patient. Whole-body CT scanning may include scanning the neck, chest, abdomen, and pelvis of a patient. The scanning device 110 may first take a 3D image of the patient using the 3D depth camera 112 and then perform a scout scan on the patient to generate a scout image.

In some embodiments, the processing device 140 may segment the scout image into three regions of interest: the neck (region 1), the chest (region 2), and the abdomen and pelvis (region 3). The processing device 140 may determine three reference scout images: a neck-related reference scout image, a chest-related reference scout image and an abdomen-pelvis related reference scout image. For each region of interest, the processing device 140 may determine a regional dose modulation line based on the reference scout image associated with the region. For example, the processing device 140 may determine the neck-related region dose modulation line based on at least one scan parameter in a scan protocol associated with the neck-related reference scout image. For another example, the processing device 140 may determine the neck-related region dose modulation line by inputting the neck-related reference scout image and the 3D image of the patient to the dose modulation line generating model. After obtaining the neck-, chest-, and abdomen-pelvis-related region dose modulation lines, the processing device 140 may combine the region dose modulation lines to generate the dose modulation line 1510. In some embodiments, a smoothing process may be performed on the generated dose modulation lines to avoid abrupt changes in radiation dose corresponding to boundary points of the regional dose modulation lines.

It should be noted that the foregoing description is intended for purposes of illustration only and is not intended to limit the scope of the present disclosure. Various modifications or changes may occur to those skilled in the art in light of the description herein. However, such modifications and changes do not depart from the scope of the present application. For example, more than three (e.g., four, five) regional dose modulation lines are determined and then combined to generate corresponding dose modulation lines. As another example, the dose modulation line and/or the regional dose modulation line may be discrete, comprising at least one discrete point, rather than one continuous curve, each discrete point corresponding to a radiation dose at a particular time or angle.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing disclosure is by way of example only, and is not intended to limit the present application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.

Also, this application uses specific terminology to describe embodiments of the application. For example, the terms "one embodiment," "an embodiment," and/or "some embodiments" mean a certain feature, structure, or characteristic described in connection with at least one embodiment of the application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this application are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of at least one embodiment of the present application may be combined as appropriate.

Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.), or in a combination of hardware and software. The above hardware or software may be referred to as a "unit", "module", or "system". Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in at least one computer readable medium.

A computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, and the like, or any suitable combination. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code on a computer readable signal medium may be propagated over any suitable medium, including radio, electrical cable, fiber optic cable, RF, or the like, or any combination of the preceding.

Computer program code required for operation of aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB, NET, Python, and the like, or similar conventional programming languages, such as the "C" programming language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or other programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or the remote computer may be in a cloud computing environment or used as a Service, such as a Software as a Service (SaaS).

Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of at least one embodiment of the invention. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Claims

1. A method of determining a radiation dose modulation line, the method comprising:

acquiring a positioning image of an object to be scanned;

segmenting the scout image to determine at least one region of interest on the scout image;

determining at least one regional dose modulation line, each of the at least one regional dose modulation lines corresponding to one of the at least one region of interest; and

determining a dose modulation line related to a CT scan of the object to be scanned based on the at least one region dose modulation line; wherein the content of the first and second substances,

the determining at least one regional dose modulation line comprises:

extracting features of each of the at least one region of interest;

determining a reference scout image corresponding to each of the at least one region of interest based on the extracted features; and

determining a regional dose modulation line for each of the at least one region of interest based on the reference scout image.

2. The method of claim 1, wherein said determining a regional dose modulation line for each of said at least one region of interest based on said reference scout image comprises:

for each of the at least one region of interest,

acquiring a scanning protocol associated with a reference scout image; and

determining a regional dose modulation line for the region of interest based on at least one parameter in the scan protocol.

3. The method of claim 2, wherein determining a regional dose modulation line for the region of interest based on at least one parameter in the scan protocol comprises:

acquiring at least one image parameter associated with the region of interest in a scout image of the object to be scanned; and

determining a regional dose modulation line for the region of interest based on at least one parameter in the scanning protocol and at least one image parameter associated with the region of interest in a scout image of the object to be scanned.

4. The method of claim 1, wherein said determining a regional dose modulation line for each of said at least one region of interest based on said reference scout image comprises:

for each of the at least one region of interest,

acquiring a reference three-dimensional image corresponding to the reference scout image; and

based on the reference scout image and the reference three-dimensional image, a model is generated with dose modulation lines to generate regional dose modulation lines corresponding to the region of interest.

5. The method of claim 4, wherein the dose modulation line generation model comprises a neural network model.

6. The method of claim 1, further comprising:

setting an initial scanning protocol;

determining an initial dose modulation line based on the initial scanning protocol and the scout image of the object to be scanned;

comparing the initial dose modulation line with a dose modulation line associated with a CT scan of the object to be scanned; and

and modifying the initial scanning protocol based on the comparison result.

7. A system for determining a radiation dose modulation line, comprising:

an acquisition unit configured to acquire a scout image of an object to be scanned;

a segmentation unit configured to segment the scout image to determine at least one region of interest on the scout image; and

a dose modulation line generation unit configured to:

extracting features of each of the at least one region of interest;

determining a reference scout image corresponding to each of the at least one region of interest based on the extracted features;

determining at least one regional dose modulation line for the at least one region of interest based on the reference scout image, each of the at least one regional dose modulation line corresponding to one of the at least one region of interest; and

determining a dose modulation line associated with a CT scan of the object to be scanned based on the at least one region dose modulation line.

8. An apparatus to determine a radiation dose modulation line, comprising a storage medium and at least one processor;

the storage medium includes computer instructions; and

the at least one processor is configured to execute the computer instructions to implement the method of any of claims 1-6.

9. A computer-readable storage medium having stored thereon computer instructions which, when executed, implement the method of any one of claims 1-6.