WO2023115345A1

WO2023115345A1 - Prostate patient classification method

Info

Publication number: WO2023115345A1
Application number: PCT/CN2021/140145
Authority: WO
Inventors: 王珊珊; 郑海荣; 李龙飞
Original assignee: 深圳先进技术研究院
Priority date: 2021-12-21
Filing date: 2021-12-21
Publication date: 2023-06-29

Abstract

The present application discloses a prostate patient classification method and apparatus, a device, and a storage medium. The method comprises: obtaining multi-parameter magnetic resonance image data of a preset number of prostate patients and data category labels; obtaining prostate benignancy and malignancy classification features of PI-RADS3 from the data having a label of PI-RADS; and constructing a disease classification model of magnetic resonance data of the prostate patients according to the classification features. According to the solution provided by the present application, constructing a model by means of feature extraction for difficult samples of PI-RADS3 is more beneficial to improving the performance of the classification model, and such a technical thought of helping classification by means of feature extraction for the patients of PI-RADS3 can be suitable for common radiomics and deep learning methods for medical image analysis.

Description

Prostate Patient Classification Method

technical field

The invention relates to the technical field of medical imaging, in particular to a method, device, equipment and storage medium for classifying prostate patients based on imaging features extracted from prostate PI-RADS 3 samples.

Background technique

The classification of benign and malignant diseases in prostate patients based on magnetic resonance imaging is a hot research field at present. This non-invasive diagnosis method can reduce the need for puncture diagnosis of patients. At present, the American College of Radiology and the European Society of Urology have jointly proposed a diagnostic guideline PI-RADS (Prostate Imaging Reporting and Data System) for the classification of prostate disease patients through multi-parameter magnetic resonance imaging. High score 1-5 categories, improve the diagnosis efficiency of prostate diseases. However, this method will generate difficult samples such as PI-RADS3 that are difficult to distinguish between benign and malignant, so this method has insufficient performance for disease classification.

The effective classification features contained in difficult-to-classify samples are often more helpful to the classification task. Therefore, strengthening the feature mining of such data and building a classification model can often improve the classification performance of the model. At present, some research methods try to extract features from difficult sample data such as PI-RADS3, and build models only for difficult samples to help classify such patients. However, the existing technology cannot give full play to the value of the effective classification information contained in the difficult samples in the disease classification based on prostate multi-parameter magnetic resonance images.

Contents of the invention

In view of the above-mentioned defects or deficiencies in the prior art, it is expected to provide a method, device, equipment and storage medium for prostate patient classification based on imaging features extracted from prostate PI-RADS 3 samples.

In the first aspect, the embodiment of the present application provides a prostate patient classification method, the method comprising: obtaining multi-parameter magnetic resonance imaging data and data category labels of a preset number of prostate patients; Obtain the benign and malignant classification features of the prostate from PI-RADS 3; build a disease classification model for the magnetic resonance data of prostate patients based on the classification features.

In one of the embodiments, the acquiring multi-parameter magnetic resonance imaging data of a preset number of prostate patients includes: acquiring multi-parameter magnetic resonance images of more than 500 cases of benign and malignant prostate patients.

In one embodiment, the data category label includes: labeling the multi-parameter magnetic resonance image data as: segmentation labeling of prostate gland tissue region, labeling of benign and malignant prostate diseases of the patient, and labeling of the patient's PI-RADS score by the doctor.

In one of the embodiments, the obtaining the benign and malignant classification features of PI-RADS 3 from the data in PI-RADS includes: obtaining the classification features of PI-RADS 3 by radiomics.

In one of the embodiments, the obtaining the benign and malignant prostate classification features of PI-RADS 3 from the data in PI-RADS with the label further includes: obtaining the classification features of PI-RADS 3 by using a deep learning method.

In the second aspect, the embodiment of the present application also provides a prostate patient classification device, which includes: an acquisition unit for acquiring multi-parameter magnetic resonance image data and data category labels of a preset number of prostate patients; a classification unit for The purpose is to obtain the benign and malignant prostate classification features of PI-RADS 3 from the data in the label PI-RADS; the model unit is used to construct a disease classification model for magnetic resonance data of prostate patients according to the classification features.

In the third aspect, the embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the program, it implements the The method described in any one of the descriptions of the examples.

In a fourth aspect, the embodiment of the present application also provides a computer device, a computer-readable storage medium, on which a computer program is stored, and the computer program is used for: when the computer program is executed by a processor, the computer program according to the present application is implemented. The method described in any one of the descriptions of the examples.

Beneficial effects of the present invention:

The classification method for prostate patients provided by the present invention is more conducive to improving the performance of the classification model by constructing a model for extracting features from PI-RADS3 difficult samples, and this technical idea of extracting features for PI-RADS3 patients to help classify can be applied to medicine Image analysis commonly used in radiomics and deep learning methods.

Description of drawings

Other characteristics, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

Fig. 1 shows a schematic flow chart of the prostate patient classification method provided by the embodiment of the present application;

Fig. 2 shows an exemplary structural block diagram of a prostate patient classification device 200 according to an embodiment of the present application;

FIG. 3 shows a schematic structural diagram of a computer system suitable for implementing a terminal device according to an embodiment of the present application;

FIG. 4 shows another schematic flowchart provided by the embodiment of the present application.

Detailed ways

In order to make the above objects, features and advantages of the present invention more comprehensible, specific implementations of the present invention will be described in detail below in conjunction with the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention can be implemented in many other ways different from those described here, and those skilled in the art can make similar improvements without departing from the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

In describing the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", " Back", "Left", "Right", "Vertical", "Horizontal", "Top", "Bottom", "Inner", "Outer", "Clockwise", "Counterclockwise", "Axial" , "radial", "circumferential" and other indicated orientations or positional relationships are based on the orientations or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying the referred device or Elements must have certain orientations, be constructed and operate in certain orientations, and therefore should not be construed as limitations on the invention.

In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

In the present invention, unless otherwise clearly specified and limited, terms such as "installation", "connection", "connection" and "fixation" should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection , or integrated; it may be mechanically connected or electrically connected; it may be directly connected or indirectly connected through an intermediary, and it may be the internal communication of two components or the interaction relationship between two components, unless otherwise specified limit. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention according to specific situations.

In the present invention, unless otherwise clearly specified and limited, the first feature may be in direct contact with the first feature or the first and second feature may be in direct contact with the second feature through an intermediary. touch. Moreover, "above", "above" and "above" the first feature on the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. "Below", "beneath" and "beneath" the first feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is less horizontally than the second feature.

It should be noted that when an element is referred to as being “fixed on” or “disposed on” another element, it may be directly on the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or intervening elements may also be present. As used herein, the terms "vertical", "horizontal", "upper", "lower", "left", "right" and similar expressions are for the purpose of illustration only and are not intended to represent the only embodiments.

Please refer to FIG. 1 , which shows a schematic flowchart of a method for classifying prostate patients provided by an embodiment of the present application.

As shown in Figure 1, the method includes:

Step 110, obtaining multi-parameter magnetic resonance imaging data and data category labels of a preset number of prostate patients;

Step 120, obtaining the benign and malignant prostate classification features of PI-RADS 3 from the data in PI-RADS labeled;

Step 130, constructing a disease classification model of the magnetic resonance data of the prostate patient according to the classification features.

Using the above technical scheme, constructing a model for extracting features from PI-RADS3 difficult samples is more helpful to improve the performance of the classification model, and this technical idea of extracting features for PI-RADS3 patients to help classify can be applied to commonly used medical image analysis In radiomics and deep learning methods.

In some embodiments, the acquisition of multi-parameter magnetic resonance image data of a preset number of prostate patients in this application includes: acquisition of multi-parameter magnetic resonance images of more than 500 cases of benign and malignant prostate patients.

In some embodiments, the data category label in this application includes: labeling multi-parameter magnetic resonance image data as: segmentation labeling of prostate gland tissue region, benign and malignant labeling of prostate disease in patients, and labeling of doctors' PI-RADS scores for patients .

In some embodiments, obtaining the benign and malignant prostate classification features of PI-RADS 3 from the data labeled as PI-RADS in this application includes: obtaining the classification features of PI-RADS 3 by radiomics.

In some embodiments, obtaining the benign and malignant prostate classification features of PI-RADS 3 from the data labeled as PI-RADS in the present application further includes: obtaining the classification features of PI-RADS 3 by using a deep learning method.

The realization of the technical solution of the present invention is shown in Figure 4. The method provided by the present invention first needs to obtain the multi-parameter magnetic resonance image data of the prostate patient, and at the same time obtain the labeling of the prostate gland region of interest, the labeling of the malignancy of the patient's disease, and the patient's Whether PI-RADS is 3 points or not. Based on the current common magnetic resonance analysis methods, radiomics and deep learning, respectively strengthen the feature extraction of difficult samples. By obtaining effective disease classification features from difficult samples, a classification model is constructed to realize the classification of benign and malignant prostate diseases.

Specifically, a certain number (more than 500 cases) of multi-parameter magnetic resonance images including benign and malignant prostate patients are collected first. Then obtain the corresponding annotation of the data, such as the segmentation annotation of the prostate tissue area in the image, the benign and malignant annotation of the patient's prostate disease, and the annotation of the doctor's PI-RADS score for the patient. When using radiomics methods to obtain important features of PI-RADS3 patients, we performed feature selection for such difficult samples, and obtained effective classification features to help build a prostate cancer classification model. When using the deep learning method, we increase the loss weight of PI-RADS3 patients during the training process, strengthen the mining of effective classification information in difficult samples, and then use the obtained effective classification features to construct a classification model.

Further, referring to FIG. 2 , FIG. 2 shows an exemplary structural block diagram of a prostate patient classification apparatus 200 according to an embodiment of the present application.

As shown in Figure 2, the device includes:

An acquisition unit 210, configured to acquire multi-parameter magnetic resonance imaging data and data category labels of a preset number of prostate patients;

The classification unit 220 is used to obtain the benign and malignant prostate classification features of PI-RADS 3 from the data in PI-RADS with the label;

The model unit 230 is configured to construct a disease classification model of the magnetic resonance data of the prostate patient according to the classification features.

It should be understood that the units or modules recorded in the device 200 correspond to the steps in the method described with reference to FIG. 1 . Therefore, the operations and features described above for the method are also applicable to the device 200 and the units contained therein, and will not be repeated here. The apparatus 200 may be pre-implemented in the browser of the electronic device or other security applications, and may also be loaded into the browser of the electronic device or its security applications by downloading or other means. The corresponding units in the apparatus 200 may cooperate with the units in the electronic device to implement the solutions of the embodiments of the present application.

Referring now to FIG. 3 , it shows a schematic structural diagram of a computer system 300 suitable for implementing a terminal device or a server according to an embodiment of the present application.

As shown in FIG. 3 , a computer system 300 includes a central processing unit (CPU) 301 that can operate according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage section 308 into a random-access memory (RAM) 303 Instead, various appropriate actions and processes are performed. In the RAM 303, various programs and data required for the operation of the system 300 are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other through a bus 304. An input/output (I/O) interface 305 is also connected to the bus 304 .

The following components are connected to the I/O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 308 including a hard disk, etc. and a communication section 309 including a network interface card such as a LAN card, a modem, or the like. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I/O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 310 as necessary so that a computer program read therefrom is installed into the storage section 308 as necessary.

In particular, according to an embodiment of the present disclosure, the process described above with reference to FIG. 1 may be implemented as a computer software program. For example, embodiments of the present disclosure include a method of prostate patient classification comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method of FIG. 1 . In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 309 and/or installed from removable media 311 .

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code that includes one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

The units or modules involved in the embodiments described in the present application may be implemented by means of software or by means of hardware. The described units or modules may also be set in a processor. For example, it may be described as: a processor includes a first sub-region generating unit, a second sub-region generating unit, and a display region generating unit. Wherein, the names of these units or modules do not constitute limitations on the units or modules themselves in some cases, for example, the display area generation unit can also be described as "used to generate The cell of the display area of the text".

As another aspect, the present application also provides a computer-readable storage medium, which may be the computer-readable storage medium contained in the aforementioned devices in the above-mentioned embodiments; computer-readable storage media stored in the device. The computer-readable storage medium stores one or more programs, and the aforementioned programs are used by one or more processors to execute the text generation method applied to transparent window envelopes described in this application.

The above description is only a preferred embodiment of the present application and an illustration of the applied technical principle. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solution formed by the specific combination of the above-mentioned technical features, and should also cover the technical solutions formed by the above-mentioned technical features or without departing from the aforementioned inventive concept. Other technical solutions formed by any combination of equivalent features. For example, a technical solution formed by replacing the above-mentioned features with technical features with similar functions disclosed in (but not limited to) this application.

Claims

A prostate patient classification method is characterized in that the method comprises:

Obtain multi-parameter magnetic resonance imaging data and data category labels of a preset number of prostate patients;

Obtain the benign and malignant prostate classification features of PI-RADS 3 from the data labeled as PI-RADS;

Constructing a Disease Classification Model from Magnetic Resonance Data of Prostate Patients Based on Classification Features.
The method for classifying prostate patients according to claim 1, wherein said acquiring multi-parameter magnetic resonance imaging data of a preset number of prostate patients comprises:

Obtain multi-parameter magnetic resonance images of more than 500 cases of benign and malignant prostate patients.
Prostate patient classification method according to claim 2, is characterized in that, described data category label comprises:

The multi-parameter magnetic resonance imaging data is marked as: the segmentation and labeling of prostate gland tissue, the benign and malignant labels of the patient's prostate disease, and the scoring and labeling of the patient's PI-RADS by the doctor.
The prostate patient classification method according to claim 3, wherein said obtaining the benign and malignant prostate classification features of PI-RADS 3 from the data in PI-RADS whose label includes:

The classification features of PI-RADS 3 were obtained by radiomics method.
The prostate patient classification method according to claim 4, wherein said obtaining the benign and malignant classification features of the prostate of PI-RADS 3 from the data in the PI-RADS with the label also includes:

The classification features of PI-RADS 3 are obtained by deep learning method.
A prostate patient classification device, characterized in that the device comprises:

An acquisition unit, configured to acquire multi-parameter magnetic resonance imaging data and data category labels of a preset number of prostate patients;

A taxonomic unit used to obtain the benign and malignant classification features of PI-RADS 3 from the data labeled as PI-RADS;

A model unit for constructing a disease classification model for magnetic resonance data of prostate patients based on classification features.
The prostate patient classification device according to claim 6, wherein said acquisition of multi-parameter magnetic resonance image data of a preset number of prostate patients comprises:

Obtain multi-parameter magnetic resonance images of more than 500 cases of benign and malignant prostate patients.
Prostate patient classification device according to claim 7, is characterized in that, described data category label comprises:

The multi-parameter magnetic resonance imaging data is marked as: the segmentation and labeling of prostate gland tissue, the benign and malignant labels of the patient's prostate disease, and the scoring and labeling of the patient's PI-RADS by the doctor.
A computer device, comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, characterized in that, when the processor executes the program, it implements any of claims 1-5 described method.
A computer-readable storage medium having stored thereon a computer program for:

When the computer program is executed by the processor, the method according to any one of claims 1-5 is realized.