CN113298758A

CN113298758A - Auxiliary diagnosis system for Alzheimer's disease, data processing method and terminal thereof

Info

Publication number: CN113298758A
Application number: CN202110475204.0A
Authority: CN
Inventors: 王思伦; 南雅诗; 肖焕辉
Original assignee: Shenzhen Yiwei Medical Technology Co Ltd
Current assignee: Shenzhen Yiwei Medical Technology Co Ltd
Priority date: 2021-04-29
Filing date: 2021-04-29
Publication date: 2021-08-24

Abstract

The invention discloses an assistant diagnosis system for Alzheimer's disease, comprising: the preprocessing module preprocesses the original MRI structural image to obtain a preprocessed image, converts the preprocessed image into an MNI space to obtain a preprocessed image, and resamples the image to have isotropic resolution; the ROI positioning module is used for carrying out rigid registration on the image obtained after preprocessing and a standard brain template to obtain a non-rigid registration deformation field, and a plurality of ROIs are selected on the preprocessed individual image according to the deformation field; the analysis module constructs, trains, verifies and tests a deep learning model, calculates the feature map and the probability value of each ROI in the individuals by adopting the deep learning model, and judges whether the subject is the Alzheimer's disease patient according to the probability value. The system adopts a deep learning technology to learn the characteristics of brain structure change, predicts whether the testee has the Alzheimer's disease, has high prediction accuracy and provides an auxiliary function for diagnosis of doctors.

Description

Auxiliary diagnosis system for Alzheimer's disease, data processing method and terminal thereof

Technical Field

The invention relates to the technical field of software, in particular to an assistant diagnosis system for Alzheimer's disease, a data processing method, a terminal and a medium thereof.

Background

Alzheimer's disease is a progressive degenerative disease of the nervous system with hidden disease, and the medical industry focuses on early detection and subsequent treatment because there is no drug cure or treatment to reverse the progression of the disease. Research shows that the brain changes 20 years before dementia symptoms appear, and the existing detection for the Alzheimer disease can be performed through hematology examination, neuroimaging examination, cerebrospinal fluid detection, gene detection and the like. These methods all require professional equipment and medical personnel, are expensive to detect, take a long time, and are not suitable for screening large sample volumes.

Disclosure of Invention

Aiming at the defects in the prior art, the Alzheimer's disease auxiliary diagnosis system, the data processing method, the terminal and the medium thereof provided by the embodiment of the invention adopt a deep learning technology to learn the characteristics of brain structure change, predict whether a subject suffers from Alzheimer's disease or not and provide an auxiliary function for diagnosis of doctors.

In a first aspect, an auxiliary diagnostic system for alzheimer's disease provided in an embodiment of the present invention includes: a data acquisition module, a preprocessing module, an ROI positioning module and an analysis module,

the data acquisition module is used for acquiring an original MRI structural image of a subject;

the preprocessing module is used for preprocessing an original MRI structural image to obtain a preprocessed image, converting the preprocessed image into an MNI space to obtain a preprocessed image, and resampling the preprocessed image to have isotropic resolution;

the ROI positioning module is used for carrying out rigid registration on the image obtained after the preprocessing and a standard brain template to obtain a non-rigid registration deformation field, and selecting a plurality of ROIs on the preprocessed individual image according to the deformation field;

the analysis module is used for constructing, training, verifying and testing a deep learning model, calculating a feature map and a probability value of each ROI in an individual by adopting the deep learning model, and judging whether the subject is the Alzheimer's disease patient according to the probability value.

In a second aspect, a data processing method of an assisted diagnosis system for alzheimer's disease provided in an embodiment of the present invention includes the following steps:

acquiring an original MRI structural image of a subject;

preprocessing an original MRI structural image, converting the preprocessed image into an MNI space to obtain a preprocessed image, and resampling the preprocessed image to obtain isotropic resolution;

carrying out rigid registration on the image obtained after the pretreatment and a standard brain template to obtain a non-rigid registration deformation field, and selecting a plurality of ROI (regions of interest) on the individual image subjected to pretreatment according to the deformation field;

and constructing a deep learning model, calculating a feature map and a probability value of each ROI in the individuals by adopting the deep learning model, and judging whether the subject is the Alzheimer's disease patient according to the probability value.

In a third aspect, an auxiliary diagnostic terminal provided in an embodiment of the present invention includes a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method described in the foregoing embodiment.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, the computer program including program instructions, which, when executed by a processor, cause the processor to execute the method described in the above embodiment

The invention has the beneficial effects that:

the Alzheimer disease auxiliary diagnosis system, the data processing method, the terminal and the medium thereof provided by the embodiment of the invention adopt the deep learning technology to learn the characteristics of brain structure change, predict whether the subject suffers from Alzheimer disease or not, have high prediction accuracy and provide auxiliary functions for diagnosis of doctors.

Drawings

In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.

Fig. 1 is a block diagram illustrating a diagnosis assisting system for alzheimer's disease according to a first embodiment of the present invention;

FIG. 2 shows a raw MRI structural image and a pre-processed image in a first embodiment of the present invention;

FIG. 3 is a diagram illustrating ROIs selected based on brain templates in a first embodiment of the invention;

FIG. 4 is a diagram illustrating ROIs mask in individual space in a first embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a deep learning model in the first embodiment of the present invention;

fig. 6 is a flowchart illustrating a data processing method of an alzheimer's disease auxiliary diagnosis system according to a second embodiment of the present invention;

fig. 7 is a block diagram illustrating a diagnosis assisting terminal according to a third embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".

It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.

Fig. 1 shows a block diagram of an assisted alzheimer's disease diagnosis system according to a first embodiment of the present invention, which includes: the device comprises a data acquisition module, a preprocessing module, an ROI (region of interest) positioning module and an analysis module, wherein the data acquisition module is used for acquiring an original MRI structural image of a subject; the preprocessing module is used for preprocessing an original MRI structural image to obtain a preprocessed image, converting the preprocessed image into an MNI space to obtain a preprocessed image, and resampling the preprocessed image to have isotropic resolution; the ROI positioning module is used for carrying out rigid registration on the image obtained after the preprocessing and a standard brain template to obtain a non-rigid registration deformation field, and selecting a plurality of ROIs on the preprocessed individual image according to the deformation field; the analysis module is used for constructing a deep learning model, calculating a feature map and a probability value of each ROI in the individuals by adopting the deep learning model, and judging whether the subject is the Alzheimer's disease patient according to the probability value.

As shown in FIG. 2, the data acquisition module acquires an original MRI structural image of a subject, the preprocessing module performs skull removal on the original MRI structural image, converts the original MRI structural image into MNI space to obtain a preprocessed image, and the resampled image has isotropic resolution (1 × 1 × 1 mm)³). And carrying out non-rigid registration on the preprocessed image and a standard brain template to obtain a non-rigid registered deformation field, and selecting 500 corresponding ROIs on the preprocessed individual image according to the deformation field, as shown in figure 3. As shown in FIG. 4, which shows individual brain cross sectional ROI masks, a size of 25X 25mm is extracted on an individual image according to the geometric center of each ROI on the individual brain cross sectional ROI mask³As input to the deep learning model.

The constructed deep learning model is shown in fig. 5, and comprises a full convolution network, 2 classification layers and 2 sigmoid activation functions. After the model is built, the brain image data of public healthy people (NC) and patients with Alzheimer's Disease (AD) are used as a database for training, verifying and testing the deep learning model. There were 295 samples in the brain image database, and the test samples were selected to the extent that individuals included in the training data were excluded. The final average accuracy reaches 87.95%, and the area under the curve (AUC) of the ROC curve reaches 96.34%.

The training process is divided into forward propagation and backward propagation: inputting each ROI image into a deep learning model for prediction, wherein each ROI passes through a full convolution network which comprises a convolution layer and a maximum pooling layer, after convolution and pooling operations are carried out on the ROI, a characteristic map (1 x 64) based on the ROI is obtained, and the characteristic map is calculated through a classification layer and a sigmoid activation function to obtain a prediction score (1 x 2) based on the ROI; and then, splicing the feature maps and the prediction scores of all the ROIs, performing convolution calculation, obtaining a probability value based on an individual through a last classification layer and a sigmoid activation function, wherein the probability value is the probability of whether the subject is an AD patient, setting a probability threshold value to be 0.5, and performing NC and AD two-classification according to the 0.5 as the threshold value. And evaluating the error between the prediction result obtained by the forward propagation and the gold standard by using a cross entropy loss function, and updating the weight of each layer according to the error to finish the backward propagation. All the image data of the data set have a judgment result corresponding to the Alzheimer disease, and the judgment result is the gold standard. And recalculating after the weight is updated, and repeating the iteration continuously until the set iteration times are finished, thus finishing the training.

And during testing, the ROI of the test data is selected, and the ROI is input into the trained network to obtain a classification result. The test results of the test set data are compared with the gold standard, the number of true positive, false positive, true negative and false negative results is counted, the average accuracy is calculated to obtain 87.95%, and the AUC is calculated to obtain 96.34%.

According to the aided diagnosis system for the Alzheimer's disease, provided by the embodiment of the invention, the characteristics of brain structure change are learned by adopting a deep learning technology, whether a subject suffers from the Alzheimer's disease is predicted, the prediction accuracy is high, and an aided function is provided for diagnosis of a doctor.

As shown in fig. 6, a data processing method of an alzheimer's disease auxiliary diagnosis system according to a second embodiment of the present invention is shown, which includes the following steps:

s1, acquiring the original MRI structure image of the subject.

And S2, preprocessing the original MRI structural image to obtain a preprocessed image, converting the preprocessed image into an MNI space, and resampling the image to an isotropic resolution.

Specifically, skull removal is carried out on an original MRI structural image, the original MRI structural image is converted into MNI space to obtain a preprocessed image, and a resampled image is isotropic resolution (1 multiplied by 1 mm)³)。

And S3, carrying out rigid registration on the image obtained after the pretreatment and a standard brain template to obtain a non-rigid registration deformation field, and selecting a plurality of ROIs on the individual image subjected to pretreatment according to the deformation field.

Non-rigid registration is carried out on the preprocessed image and a standard brain template to obtain a non-rigid registered deformation field, corresponding 500 ROIs are selected from the preprocessed individual image according to the deformation field, and the size of each ROI on an ROI mask of the cross section of the brain of an individual is 25 multiplied by 25mm on the individual image according to the geometric center of each ROI³As input to the deep learning model.

S4, constructing a deep learning model, training, verifying and testing the deep learning model, calculating a feature map and a probability value of each ROI in the individuals by adopting the deep learning model, and judging whether the subject is the Alzheimer' S disease patient according to the probability values.

And constructing a deep learning model, wherein the deep learning model comprises a full convolution network, 2 classification layers and 2 sigmoid activation functions. After the model is built, the brain image data of public healthy people (NC) and patients with Alzheimer's Disease (AD) are used as a database for training, verifying and testing the deep learning model. There were 295 samples in the brain image database, and the test samples were selected to the extent that individuals included in the training data were excluded. The final average accuracy reaches 87.95%, and the area under the curve (AUC) of the ROC curve reaches 96.34%.

The training process is divided into forward propagation and backward propagation: inputting each ROI image into a deep learning model, wherein each ROI passes through a full convolution network which comprises a convolution layer and a maximum pooling layer, after the ROI is subjected to convolution and pooling operation, a characteristic map (1 x 64) based on the ROI is obtained, and the characteristic map is calculated through a classification layer and a sigmoid activation function to obtain a prediction score (1 x 2) based on the ROI; and then, splicing the feature maps and the prediction scores of all the ROIs, performing convolution calculation, obtaining a probability value based on an individual through a last classification layer and a sigmoid activation function, wherein the probability value is the probability of whether the subject is an AD patient, and classifying whether the subject is Alzheimer disease or not by using a threshold value of 0.5. And evaluating the error between the prediction result obtained by the forward propagation and the gold standard by using a cross entropy loss function, and updating the weight of each layer according to the error to finish the backward propagation. And recalculating after the weight is updated, and repeating the iteration continuously until the set iteration times are finished, thus finishing the training.

According to the data processing method of the Alzheimer disease auxiliary diagnosis system, provided by the embodiment of the invention, the characteristics of brain structure change are learned by adopting a deep learning technology, whether the subject suffers from Alzheimer disease is predicted, the prediction accuracy is high, and an auxiliary function is provided for diagnosis of doctors.

As shown in fig. 7, a block diagram of a diagnosis assisting terminal provided in a third embodiment of the present invention is shown, the terminal includes a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory are connected to each other, the memory is used for storing a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method described in the above embodiment.

It should be understood that in the embodiments of the present invention, the Processor may be a Central Processing Unit (CPU), and the Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The input device may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of the fingerprint), a microphone, etc., and the output device may include a display (LCD, etc.), a speaker, etc.

The memory may include both read-only memory and random access memory, and provides instructions and data to the processor. The portion of memory may also include non-volatile random access memory. For example, the memory may also store device type information.

In a specific implementation, the processor, the input device, and the output device described in the embodiments of the present invention may execute the implementation described in the method embodiments provided in the embodiments of the present invention, and may also execute the implementation described in the system embodiments in the embodiments of the present invention, which is not described herein again.

The invention also provides an embodiment of a computer-readable storage medium, in which a computer program is stored, which computer program comprises program instructions that, when executed by a processor, cause the processor to carry out the method described in the above embodiment.

The computer readable storage medium may be an internal storage unit of the terminal described in the foregoing embodiment, for example, a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the terminal. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the terminal and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed terminal and method can be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.

Claims

1. An assistant diagnosis system for alzheimer's disease, comprising: a data acquisition module, a preprocessing module, an ROI positioning module and an analysis module,

2. The aided diagnosis system of Alzheimer's disease of claim 1, wherein the analysis module comprises a deep learning model construction unit, the deep learning model construction unit is used for constructing a deep learning model, and the deep learning model comprises a full convolution network, 2 classification layers and 2 sigmoid activation functions.

3. The assistant diagnosis system for alzheimer's disease as claimed in claim 2, wherein the deep learning model unit is configured to obtain a feature map based on the ROIs after each ROI passes through a full convolution network, the feature map is calculated by a first classification layer and a first activation function to obtain prediction scores based on the ROIs, the feature maps and the prediction scores of all the ROIs are spliced to perform convolution calculation, a probability value based on an individual is obtained by a second classification layer and a second activation function, and the probability value is compared with a set threshold to determine whether the subject is a patient with alzheimer's disease.

4. The aided diagnosis system of Alzheimer's disease of claim 3, wherein the threshold value is 0.5.

5. A data processing method of an assistant diagnosis system for Alzheimer's disease is characterized by comprising the following steps:

acquiring an original MRI structural image of a subject;

and constructing a deep learning model, training, verifying and testing the deep learning model, calculating a feature map and a probability value of each ROI in the individual by adopting the deep learning model, and judging whether the subject is the Alzheimer's disease patient according to the probability value.

6. The data processing method of claim 5, wherein the deep learning model comprises a full convolutional network, 2 classification layers, and 2 sigmoid activation functions.

7. The data processing method of claim 6, wherein the calculating a feature map and a probability value of each ROI in the individual by using the deep learning model, and the determining whether the subject is the Alzheimer's disease patient according to the probability values comprises:

and (3) enabling each ROI to pass through a full convolution network to obtain a characteristic map based on the ROI, calculating the characteristic map through a first classification layer and a first activation function to obtain a prediction score based on the ROI, splicing the characteristic maps and the prediction scores of all the ROIs to perform convolution calculation, obtaining a probability value based on an individual through a second classification layer and a second activation function, comparing the probability value with a set threshold value, and judging whether the subject is the Alzheimer's disease patient.

8. The data processing method of claim 7, wherein the threshold is 0.5.

9. A diagnostic assistance terminal comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, the memory being adapted to store a computer program comprising program instructions, characterized in that the processor is configured to invoke the program instructions to perform the method according to any one of claims 5 to 8.

10. A computer-readable storage medium, characterized in that the computer storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method according to any of claims 5-8.