CN117522845A

CN117522845A - Lung function detection method and device, electronic equipment and storage medium

Info

Publication number: CN117522845A
Application number: CN202311604509.2A
Authority: CN
Inventors: 刘长东; 许文仪; 周子捷
Original assignee: Lianren Healthcare Big Data Technology Co Ltd
Current assignee: Lianren Healthcare Big Data Technology Co Ltd
Priority date: 2023-11-28
Filing date: 2023-11-28
Publication date: 2024-02-06

Abstract

The embodiment of the invention discloses a lung function detection method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring at least two CT images to be processed corresponding to a target patient under spontaneous respiration; registering the CT images to be processed to obtain lung registration CT images of each CT image to be processed; segmenting all lung registration CT images, and respectively extracting features of lung registration CT sub-images of each segmented region to obtain a plurality of sub-image feature information; clustering the characteristic information of the plurality of sub-images to obtain a target region of interest, and extracting the imaging characteristics to obtain imaging characteristics of the CT image to be processed; the imaging features are input into the target lung function detection model to obtain a target lung function detection result of a target patient, so that the lung function of the patient can be automatically detected, the lung function detection efficiency is improved, accurate lung function detection is performed when the patient breathes spontaneously, and the universality of the lung function detection is improved.

Description

Lung function detection method and device, electronic equipment and storage medium

Technical Field

Embodiments of the present invention relate to image processing technologies, and in particular, to a method and apparatus for detecting a lung function, an electronic device, and a storage medium.

Background

The gold standard of lung function is done by patient exhalation experiments, but it is very difficult to do the exhalation experiments for many elderly patients, especially for elderly patients suffering from heart disease.

Currently, biphasic CT imaging is commonly used to detect patient lung function. However, the two-phase CT photographing mode is still divided into two phases of exhalation and inhalation, and because many elderly patients cannot normally complete breath-hold photographing after inhalation, the quality of breath-hold photographing is poor, and finally, the lung function detection result of the patients is inaccurate.

Disclosure of Invention

The embodiment of the invention provides a lung function detection method, a device, electronic equipment and a storage medium, which are used for realizing automatic detection of the lung function of a patient, do not need to be manually participated, improve the detection efficiency of the lung function, accurately detect the lung function when the patient breathes spontaneously, and improve the universality of the lung function detection.

In a first aspect, an embodiment of the present invention provides a method for detecting a lung function, including:

acquiring at least two CT images to be processed corresponding to a target patient under spontaneous respiration;

the lung registration CT image of each CT image to be processed is obtained by carrying out registration processing on the at least two CT images to be processed;

dividing all the lung registration CT images according to the same dividing mode, and respectively extracting features of lung registration CT sub-images of each divided area to obtain a plurality of sub-image feature information;

clustering the characteristic information of the plurality of sub-images to obtain a target region of interest with respiratory invariance, and extracting imaging characteristics of the target region of interest to obtain imaging characteristics of the at least two CT images to be processed;

and inputting the imaging characteristics into a target lung function detection model to obtain a target lung function detection result of the target patient.

In a second aspect, an embodiment of the present invention provides a lung function detection device, including:

the CT image acquisition module to be processed is used for acquiring at least two CT images to be processed corresponding to the target patient under spontaneous respiration;

the lung registration CT image determining module is used for obtaining a lung registration CT image of each CT image to be processed by carrying out registration processing on the at least two CT images to be processed;

the sub-image feature information determining module is used for dividing all the lung registration CT images according to the same dividing mode, and respectively extracting features of the lung registration CT sub-images of each divided area to obtain a plurality of sub-image feature information;

the imaging feature determining module is used for obtaining a target region of interest with respiratory invariance through clustering the plurality of sub-image feature information, and extracting imaging features of the target region of interest to obtain imaging features of the at least two CT images to be processed;

and the target lung function detection result determining module is used for inputting the imaging characteristics into a target lung function detection model to obtain a target lung function detection result of the target patient.

In a third aspect, an embodiment of the present invention provides an electronic device, including:

one or more processors;

a memory for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the lung function detection method as provided by any embodiment of the present invention.

In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a lung function detection method as provided by any of the embodiments of the present invention.

According to the technical scheme, at least two CT images to be processed corresponding to the target patient under spontaneous respiration are acquired; the lung registration CT image of each CT image to be processed is obtained by carrying out registration processing on the at least two CT images to be processed, so that coordinate alignment can be carried out on all CT images to be processed, namely, all CT images to be processed are unified into a unified coordinate system; dividing all the lung registration CT images according to the same dividing mode, and respectively extracting features of lung registration CT sub-images of each divided area to obtain a plurality of sub-image feature information; clustering the characteristic information of the plurality of sub-images to obtain a target region of interest with respiratory invariance, and extracting imaging characteristics of the target region of interest to obtain imaging characteristics of the at least two CT images to be processed; the imaging features are input into a target lung function detection model to obtain a target lung function detection result of the target patient, so that the lung function of the patient can be automatically detected without manual participation, the lung function detection efficiency is improved, accurate lung function detection can be performed when the patient breathes spontaneously, and the universality of the lung function detection is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a method for detecting lung function according to a first embodiment of the present invention;

fig. 2 is a flowchart of a lung function detection method according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of a lung function detection device according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device implementing a lung function detection method according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a lung function detection method according to an embodiment of the present invention, where the method may be performed by a lung function detection device, and the lung function detection device may be implemented in hardware and/or software, and the lung function detection device may be configured in an electronic device, where the lung function detection method is applicable to a case of performing lung function detection of a target patient by using at least two CT images to be processed corresponding to the target patient under spontaneous breathing. As shown in fig. 1, the method includes:

s110, acquiring at least two CT images to be processed corresponding to the target patient under spontaneous respiration.

The target patient may be a patient in need of lung function detection. For example, the target patient may refer to, inter alia, an elderly patient suffering from heart disease, or unable to hold breath or expectorate for a prolonged period of time. Spontaneous breathing may refer to natural breathing, i.e. breathing without forced manipulation. In contrast to spontaneous breathing, artificial breathing. The CT image to be processed may refer to a multi-phase CT image scan-captured in a 4DCT mode. Each corresponding CT image may refer to a CT image of the target patient acquired by scanning at a different time. The CT image to be processed contains a target detection part of a target patient. In this embodiment, the target detection site may be, but is not limited to, the lung.

Specifically, when the target patient performs 4DCT, all CT images to be processed corresponding to the target patient under spontaneous respiration are directly acquired. All the CT images to be processed corresponding to the target patient under spontaneous respiration can be obtained from the data storage after the target patient performs 4 DCT. And at least two CT images to be processed with larger differences can be selected from all CT images to be processed corresponding to the target patient under spontaneous breathing based on a preset selection mode, so that the imaging characteristics can be more accurately determined based on the CT images to be processed with larger differences, and a more accurate target lung function detection result can be finally determined.

Illustratively, the CT image to be processed is a CT image containing the target detection site corresponding to different phases of spontaneous breathing of the target patient. Wherein phase may refer to different phases in the spontaneous breathing state. For example, the phases may include, but are not limited to, an autonomous inhalation phase or an autonomous exhalation phase.

S120, performing registration processing on at least two CT images to be processed to obtain lung registration CT images of each CT image to be processed.

Wherein, the lung registration CT image may refer to CT images under the same coordinate system. Specifically, by performing image rigid registration processing on at least two CT images to be processed, a lung registration CT image of each CT image to be processed after coordinate alignment can be obtained. For example, image rigid registration processing of a plurality of CT images to be processed may be performed based on preset point markers or reference markers, and the preset point markers or reference markers in each CT image to be processed are subjected to registration processing, so as to obtain lung registration CT images of each CT image to be processed after coordinate alignment. The method can also be used for determining the invariant features in all CT images to be processed in advance, and carrying out image rigid registration processing on a plurality of CT images to be processed based on the invariant features to obtain lung registration CT images of each CT image to be processed after coordinate alignment.

S130, segmenting all the lung registration CT images according to the same segmentation mode, and extracting features of lung registration CT sub-images of each segmented region respectively to obtain a plurality of sub-image feature information.

The segmentation method may be, but is not limited to, a super-pixel segmentation method based on the SLIC algorithm. The segmented region may refer to an image region corresponding to a sub-image obtained by segmenting the lung registration CT image. The sub-image feature information may be used to characterize the feature information in the segmented sub-image.

Specifically, for each lung registration CT image, region segmentation is performed on all the lung registration CT images according to the same segmentation mode, a plurality of lung registration CT sub-images corresponding to each lung registration CT image are determined, feature extraction is performed on the lung registration CT sub-images of each segmented region respectively, and sub-image feature information corresponding to each lung registration CT sub-image is obtained.

S140, clustering the characteristic information of the plurality of sub-images to obtain a target region of interest with respiratory invariance, and extracting the imaging characteristics of the target region of interest to obtain imaging characteristics of at least two CT images to be processed.

Wherein respiratory invariance may refer to a characteristic that does not change with respiratory changes. Imaging features may refer to the features of the disease that are comprehensively revealed at different pathological stages and levels. In this embodiment, the imaging features may refer to imaging features related to lung function. The imaging features can be used to provide effective basis for judging lung function.

Specifically, for each segmented region, determining a clustering result corresponding to each segmented region by clustering sub-image feature information corresponding to lung registration CT sub-images of all phases of a target patient, determining a target region of interest with respiratory invariance based on the clustering result, and extracting imaging features of the target region of interest to obtain imaging features corresponding to the target region of interest in at least two CT images to be processed.

S150, inputting the imaging characteristics into a target lung function detection model to obtain a target lung function detection result of the target patient.

The target lung function detection model may be a pre-trained model for lung function detection. Specifically, the imaging features are input into a target lung function detection model, and lung function classification, such as COPD classification, is performed in the target lung function detection model based on the input imaging features, so as to obtain a target lung function detection result of the target patient. For example, the target pulmonary function test results may be, but are not limited to, grade I (90%), grade II (8%), grade III (2%), and grade IV (0%). Wherein, the severity of COPD is classified according to the index of lung function, and is classified into class I, class II, class III and class IV, namely from mild to moderate, severe and extremely severe.

It should be noted that, the training process of the target lung function detection model is as follows, history data is obtained, and the history data is processed based on the processing steps from S120 to S140, so as to determine the historical imaging characteristics corresponding to the history data; and establishing a preset lung function detection model to be trained based on the logistic regression model, and performing model training on the preset lung function detection model based on the historical imaging characteristics and the preset label, namely learning model parameters of parameter COPD grading, so as to obtain a target lung function detection model after training.

Wherein, the historical data comprises: a plurality of historical CT images of the plurality of phases corresponding to the historical patients under spontaneous breathing and a COPD grading standard (i.e. a preset label) corresponding to each historical patient.

According to the technical scheme, at least two CT images to be processed corresponding to the target patient under spontaneous respiration are acquired; the lung registration CT image of each CT image to be processed is obtained by carrying out registration processing on at least two CT images to be processed, so that coordinate alignment can be carried out on all CT images to be processed, namely, all CT images to be processed are unified into a unified coordinate system; dividing all lung registration CT images according to the same dividing mode, and respectively extracting features of lung registration CT sub-images of each divided area to obtain a plurality of sub-image feature information; clustering the characteristic information of the plurality of sub-images to obtain a target region of interest with respiratory invariance, and extracting the imaging characteristics of the target region of interest to obtain imaging characteristics of at least two CT images to be processed; the imaging features are input into the target lung function detection model to obtain a target lung function detection result of a target patient, so that the lung function of the patient can be automatically detected without manual participation, the lung function detection efficiency is improved, accurate lung function detection can be performed when the patient breathes spontaneously, and the universality of the lung function detection is improved.

In the above technical solution, S120 may include: extracting features of at least two CT images to be processed, and determining registration feature information corresponding to the at least two CT images to be processed; and carrying out image rigid registration processing based on each CT image to be processed and the registration feature information, and determining a lung registration CT image of each CT image to be processed.

Wherein the registration feature information may be a feature for performing image coordinate alignment. For example, the registration feature information may be feature information of a registration object other than the target patient body part set in advance. The registration feature information may also be feature information in which the position coordinates do not change in the acquired CT image to be processed.

Specifically, feature extraction is performed on at least two CT images to be processed, registration feature information corresponding to the at least two CT images to be processed is determined, the first CT image to be processed is taken as a reference image, image rigid registration processing is performed on the basis of the registration feature information of each CT image to be processed, so that coordinate alignment is performed on images except the reference image to the reference image, lung registration CT images of each CT image to be processed are determined, and therefore all CT images to be processed can be unified under the same coordinate system before features except the imaging features are filtered, accuracy and efficiency of subsequent determination of respiratory invariance features are improved, and detection efficiency and detection universality of lung functions are further improved.

In the above technical solution, the "segmenting all lung registered CT images according to the same segmentation method" in S130 may include: and carrying out image segmentation on all the lung registration CT images based on the preset segmentation quantity, and determining lung registration CT sub-images of each segmented region.

For example, if the preset number of segmentations may be 100, then feature division and/or feature combination may be performed on the lung registration CT image according to the segmentation regions of 10×10, and image segmentation may be performed on the image region where the processed features are located, so as to obtain a lung registration CT sub-image corresponding to each segmentation region. The advantage of adopting the same segmentation mode to carry out image segmentation is that the image segmentation effect can be ensured, and the detection efficiency and the detection universality of the lung function are further improved.

Example two

Fig. 2 is a flowchart of a lung function detection method according to a second embodiment of the present invention, where a process of obtaining a target region of interest with respiratory invariance by clustering a plurality of sub-image feature information is described in detail on the basis of the above embodiment. Wherein the explanation of the same or corresponding terms as those of the above embodiments is not repeated herein. As shown in fig. 2, the method includes:

s210, acquiring at least two CT images to be processed corresponding to the target patient under spontaneous respiration.

S220, performing registration processing on at least two CT images to be processed to obtain lung registration CT images of each CT image to be processed.

S230, segmenting all the lung registration CT images according to the same segmentation mode, and extracting features of lung registration CT sub-images of each segmented region respectively to obtain multiple sub-image feature information.

S240, determining a clustering center corresponding to each segmented region through clustering the characteristic information of the sub-images of the same segmented region in each lung registration CT sub-image.

The method can be understood as that all sub-image feature information corresponding to the same segmentation area is subjected to overlapping processing, and the clustering center corresponding to each segmentation area is redetermined based on the overlapped feature information. When the cluster center corresponding to each segmented region is redetermined, two similar cluster centers are combined, and meanwhile, the two cluster regions are combined, so that the radius of the original cluster region is enlarged, and the detection efficiency and the detection universality of the lung function are further improved.

S250, carrying out region screening based on the clustering center, and determining an alternative region of interest with respiratory invariance.

Wherein the alternative region of interest may refer to a region having respiratory invariance characteristics. Specifically, the segmented regions with obvious clustering centers and large clustering radii are reserved, and segmented regions without obvious clustering centers or large clustering radii are deleted, so that the characteristics in the screened regions can be guaranteed to have respiratory invariance through the steps, and the detection efficiency and the detection universality of the lung function are further improved.

Illustratively, S250 may include: if the density of the clustering centers is larger than a preset density threshold, determining the segmented region corresponding to the density of the clustering centers as a candidate region of interest; and if the radius of the cluster center corresponding to the region of interest is smaller than a preset radius threshold, determining the candidate region of interest as an alternative region of interest.

Wherein, whether the cluster center is obvious is represented by the cluster center density. In this embodiment, the order of determining the cluster center density and the cluster center radius is not required, and may be reversed or performed simultaneously, so as to improve the efficiency of determining the candidate region of interest. Only the divided regions satisfying all the conditions can be determined as the alternative interested regions, so that the determination accuracy of the alternative interested regions can be improved, and the detection efficiency and the detection universality of the lung function can be further improved.

S260, filtering interference features and particle noise based on the alternative regions of interest, and determining a target region of interest with clear respiratory invariance.

Specifically, morphological open operation is performed on the alternative region of interest to determine a target region of interest with clear respiratory invariance. The morphological open operation is similar to convolution processing and can be an advanced erosion to eliminate small and meaningless interference features and an expansion to fill some voids in the region and eliminate small particle noise contained in the region, further improving the detection efficiency and detection versatility of lung function.

S270, extracting imaging features of the target region of interest to obtain imaging features of at least two CT images to be processed.

S280, inputting the imaging characteristics into a target lung function detection model to obtain a target lung function detection result of the target patient.

According to the technical scheme, the clustering center corresponding to each segmented region is determined through clustering processing of the sub-image characteristic information of the same segmented region in each lung registration CT sub-image; based on the clustering center, carrying out region screening, and determining an alternative region of interest with respiratory invariance, so that the characteristics in the screened region can be ensured to have respiratory invariance through the step; the method comprises the steps of filtering interference features and particle noise based on alternative interested regions, namely eliminating small and nonsensical interference features, filling certain holes in the regions, and eliminating small particle noise contained in the regions, so that a target interested region with clear respiratory invariance is determined, the detection efficiency of lung function is further improved, accurate lung function detection can be performed when a patient breathes spontaneously, and the universality of lung function detection is further improved.

In the above technical solution, S270 may include: extracting imaging characteristics of a target region of interest, and determining characteristics of the target region in the target region of interest; and determining the imaging characteristics meeting the preset correlation conditions in each CT image to be processed based on the correlation degree between each target area characteristic and the preset imaging characteristics.

The target region feature may refer to feature information corresponding to the screened target region of interest. Specifically, image characteristics of a target region of interest are extracted in an image histology mode, and target region characteristics in the target region of interest are determined; the correlation between each target region feature and the preset imaging feature is determined through a preset correlation analysis mode (such as Spearman correlation analysis or Lasso regression), and the imaging feature meeting the preset correlation condition in each CT image to be processed is determined based on the correlation and a preset correlation threshold, so that the screening efficiency and accuracy of the imaging feature are improved, and the detection efficiency and the detection universality of the lung function are further improved.

The lung function detection device provided by the embodiment of the invention can execute the lung function detection method provided by any embodiment of the invention, and has the corresponding beneficial effects of executing the lung function detection method.

The following is an embodiment of a lung function detection device according to an embodiment of the present invention, which is the same inventive concept as the lung function detection method according to the above embodiments, and reference may be made to the embodiment of the lung function detection method for details that are not described in detail in the embodiment of the lung function detection device.

Example III

Fig. 3 is a schematic structural diagram of a lung function detection device according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes: a pending CT image acquisition module 310, a lung registration CT image determination module 320, a sub-image feature information determination module 330, an imaging feature determination module 340, and a target lung function detection result determination module 350.

The CT image acquisition module 310 is used for acquiring at least two CT images to be processed corresponding to the target patient under spontaneous respiration; the lung registration CT image determining module 320 is configured to obtain a lung registration CT image of each CT image to be processed by performing registration processing on at least two CT images to be processed; the sub-image feature information determining module 330 is configured to segment all the lung registration CT images according to the same segmentation method, and perform feature extraction on the lung registration CT sub-images of each segmented region, so as to obtain multiple sub-image feature information; the imaging feature determining module 340 is configured to obtain a target region of interest with respiratory invariance by clustering feature information of a plurality of sub-images, and perform imaging feature extraction on the target region of interest to obtain imaging features of at least two CT images to be processed; the target lung function detection result determining module 350 is configured to input the imaging feature into the target lung function detection model to obtain a target lung function detection result of the target patient.

Optionally, the lung registration CT image determination module 320 is specifically configured to: extracting features of at least two CT images to be processed, and determining registration feature information corresponding to the at least two CT images to be processed; and carrying out image rigid registration processing based on each CT image to be processed and the registration feature information, and determining a lung registration CT image of each CT image to be processed.

Alternatively, the sub-image feature information determining module 330 may include:

the lung registration CT sub-image determining sub-module is used for carrying out image segmentation on all lung registration CT images based on the preset segmentation quantity and determining the lung registration CT sub-image of each segmented area.

Optionally, the imaging feature determination module 340 may include:

the clustering center determining sub-module is used for determining a clustering center corresponding to each segmentation region through clustering processing of sub-image characteristic information of the same segmentation region in each lung registration CT sub-image;

the alternative interested region determining submodule is used for carrying out region screening based on the clustering center and determining an alternative interested region with respiratory invariance;

the target region of interest determination submodule is used for filtering interference features and particle noise based on the alternative regions of interest and determining the target region of interest with clear respiratory invariance.

Optionally, the alternative region of interest determination submodule is specifically configured to: if the density of the clustering centers is larger than a preset density threshold, determining the segmented region corresponding to the density of the clustering centers as a candidate region of interest; and if the radius of the cluster center corresponding to the region of interest is smaller than a preset radius threshold, determining the candidate region of interest as an alternative region of interest.

Optionally, the imaging feature determining module 340 further includes:

the target region feature determination submodule is used for extracting imaging features of a target region of interest and determining target region features in the target region of interest;

and the imaging feature determination submodule is used for determining imaging features meeting preset relevant conditions in each CT image to be processed based on the correlation degree between each target region feature and the preset imaging features.

Optionally, the CT image to be processed is a CT image including the target detection site corresponding to different phases of spontaneous breathing of the target patient.

The lung function detection device provided by the embodiment of the invention can execute the lung function detection method provided by any embodiment of the invention, and has the corresponding function modules and beneficial effects of executing the lung function detection method.

It should be noted that, in the above embodiment of lung function detection, each unit and module included are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.

Example IV

Fig. 4 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the lung function detection method.

In some embodiments, the lung function detection method may be implemented as a computer program, which is tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the lung function detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the lung function detection method in any other suitable way (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method for detecting lung function, comprising:

2. The method according to claim 1, wherein the obtaining a lung registered CT image of each CT image to be processed by performing registration processing on the at least two CT images to be processed comprises:

extracting features of the at least two CT images to be processed, and determining registration feature information corresponding to the at least two CT images to be processed;

and carrying out image rigid registration processing on the basis of each CT image to be processed and the registration feature information, and determining a lung registration CT image of each CT image to be processed.

3. The method of claim 1, wherein segmenting all of the lung registered CT images in accordance with the same segmentation method comprises:

and carrying out image segmentation on all the lung registration CT images based on the preset segmentation quantity, and determining lung registration CT sub-images of each segmented region.

4. The method according to claim 1, wherein the clustering the plurality of sub-image feature information to obtain the target region of interest with respiratory invariance includes:

determining a clustering center corresponding to each segmented region through clustering sub-image characteristic information of the same segmented region in each lung registration CT sub-image;

performing region screening based on the clustering center, and determining an alternative region of interest with respiratory invariance;

and filtering interference features and particle noise based on the alternative region of interest, and determining a target region of interest with clear respiratory invariance.

5. The method of claim 4, wherein the determining an alternative region of interest with respiratory invariance based on the region screening by the cluster center comprises:

if the density of the clustering centers is larger than a preset density threshold, determining a segmented region corresponding to the density of the clustering centers as a candidate region of interest;

and if the radius of the cluster center corresponding to the region of interest is smaller than a preset radius threshold, determining the candidate region of interest as an alternative region of interest.

6. The method according to claim 1, wherein the performing an imaging feature extraction on the target region of interest to obtain imaging features of the at least two CT images to be processed includes:

extracting imaging characteristics of the target region of interest, and determining characteristics of the target region of interest;

and determining the imaging characteristics meeting the preset correlation condition in each CT image to be processed based on the correlation degree between each target area characteristic and the preset imaging characteristics.

7. The method of claim 1, wherein the CT image to be processed is a CT image containing the target detection site corresponding to different phases of spontaneous breathing of the target patient.

8. A lung function detection device, comprising:

9. An electronic device, the electronic device comprising:

one or more processors;

a memory for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the lung function detection method of any of claims 1-7.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the lung function detection method according to any of claims 1-7.