CN-121999261-A - Disease detection method based on brain iron deposition, computing device and computer storage medium

CN121999261ACN 121999261 ACN121999261 ACN 121999261ACN-121999261-A

Abstract

The embodiment of the application provides a disease detection method, a computing device, a computer storage medium and a computer program product based on brain iron deposition. The brain iron deposition-based disease detection method comprises the steps of obtaining target brain medical image data to be detected, and inputting the target brain medical image data into a detection model which is generated in advance in a training mode so that the detection model outputs a detection result which is determined based on iron deposition information extracted from the target brain medical image data. The technical scheme provided by the embodiment of the application provides an accurate detection method for chronic kidney disease.

Inventors

WANG HAO
WANG JIXIANG
WANG ZHENCHANG
BAI XIAOYAN
SONG LIJUN
YANG WENBO
REN PENGLING
LIU YAWEN

Assignees

首都医科大学附属北京友谊医院

Dates

Publication Date: 20260508
Application Date: 20241107

Claims (10)

1. A method for detecting a disease based on brain iron deposition, comprising: acquiring medical image data of a target brain to be detected; The method comprises the steps of inputting target brain medical image data into a detection model which is generated through pre-training, so that the detection model outputs a detection result which is determined based on iron deposition information extracted from the target brain medical image data, wherein the iron deposition information comprises iron deposition information of a target area of the target brain medical image data, the detection model comprises a convolution layer and a spatial attention module which are alternately stacked, the convolution layer is used for carrying out feature extraction on the target brain medical image data, generating feature data, and inputting the feature data into the spatial attention module, and the spatial attention module is used for determining the target area in the target brain medical image data based on the feature data, determining a sensing field matched with the target area and acquiring the iron deposition information of the target area by utilizing the sensing field.
2. The method of claim 1, wherein the acquiring medical image data of the target brain to be detected comprises: Acquiring first brain medical image data and a brain region dividing template; and correcting the original brain medical image data by using the brain region dividing template to generate the target brain medical image data.
3. The method of claim 2, wherein the correcting the first brain medical image data using the brain region segmentation template to generate the target brain medical image data comprises: correcting the original brain medical image data by using the brain region dividing template to generate second brain medical image data; Cutting the second brain medical image data according to a preset cutting size to generate third brain medical image data; Normalizing the third brain medical image data to generate the target brain medical image data.
4. The method of claim 2, wherein the inputting the target brain medical image data into a pre-training generated detection model such that the detection model outputs detection results determined based on iron deposition information extracted from the target brain medical image data comprises: Inputting the target brain medical image data into a first convolution layer and outputting first characteristic data; Inputting the first feature data into a first spatial attention module, so that the first spatial attention module determines the target region from a plurality of regions of the target brain medical image data, and outputs fourth brain medical image data; outputting the fourth brain medical image data to a second convolution layer and outputting second characteristic data; And inputting the second characteristic data into a second spatial attention module, so that the second spatial attention module determines the receptive field matched with the target area based on the second characteristic data, acquires the iron deposition information of the target area by utilizing the receptive field, and outputs the detection result based on the iron deposition information.
5. The method of claim 4, wherein the inputting the first feature data into a first spatial attention module such that the first spatial attention module determines the target region from a plurality of regions of the target brain medical image data, outputting fourth brain medical image data comprises: The first feature data is input into a first spatial attention module, so that the first spatial attention module respectively distributes attention weights to a plurality of areas of the target brain medical image data based on the first feature data, determines the target area from the plurality of areas based on the attention weights, and outputs fourth brain medical image data.
6. The method according to claim 4, wherein the method further comprises: Determining gradient information of the detection result and the convolution layer; Generating a brain attention map based on the gradient information and the target brain medical image data, wherein the brain attention map is used for displaying the attention of each region in the target brain medical image data; Outputting the brain attention heat map.
7. The method of claim 6, wherein the determining gradient information for the detection result and the convolutional layer comprises: Determining first gradient information of the detection result and the first convolution layer and second gradient information of the detection result and the second convolution layer; the generating a brain attention heat map based on the gradient information and the target brain medical image data comprises: And carrying out weighted summation on the first gradient information and the second gradient information in a channel dimension to generate the brain attention heat map.
8. A computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions for execution by the processing component to implement the brain iron deposition-based disease detection method of any one of claims 1 to 7.
9. A computer storage medium, characterized in that a computer program is stored, which, when being executed by a computer, implements the method for detecting a disease based on brain iron deposition according to any one of claims 1 to 7.
10. A computer program product, characterized in that the computer program product comprises computer program code which, when executed by a computer, implements the method for detecting a disease based on brain iron deposition according to any one of claims 1 to 7.

Description

Disease detection method based on brain iron deposition, computing device and computer storage medium Technical Field Embodiments of the present application relate to the field of artificial intelligence, and in particular, to a method for detecting a disease based on brain iron deposition, a computing device, a computer storage medium, and a computer program product. Background Chronic kidney disease (Chronic KIDNEY DISEASE, CKD) is a global public health problem, and its incidence is continuously rising, which constitutes a serious threat to human health. Early diagnosis is made very difficult by the lack of obvious symptoms of CKD at an early stage, and patients are often diagnosed at a later stage of disease progression, missing the best treatment opportunity. Therefore, how to provide an accurate detection method for chronic kidney disease is a technical problem to be solved. Disclosure of Invention The embodiment of the application provides a disease detection method, a computing device, a computer storage medium and a computer program product based on brain iron deposition. In a first aspect, an embodiment of the present application provides a method for detecting a disease based on brain iron deposition, including: acquiring medical image data of a target brain to be detected; The method comprises the steps of inputting target brain medical image data into a detection model which is generated through pre-training, so that the detection model outputs a detection result which is determined based on iron deposition information extracted from the target brain medical image data, wherein the iron deposition information comprises iron deposition information of a target area of the target brain medical image data, the detection model comprises a convolution layer and a spatial attention module which are alternately stacked, the convolution layer is used for carrying out feature extraction on the target brain medical image data, generating feature data, and inputting the feature data into the spatial attention module, and the spatial attention module is used for determining the target area in the target brain medical image data based on the feature data, determining a sensing field matched with the target area and acquiring the iron deposition information of the target area by utilizing the sensing field. In a second aspect, an embodiment of the present application provides a disease detection device based on brain iron deposition, including: The first acquisition module is used for acquiring medical image data of a target brain to be detected; the detection module is used for inputting the target brain medical image data into a detection model which is generated through pre-training, so that the detection model outputs a detection result which is determined based on iron deposition information extracted from the target brain medical image data, the iron deposition information comprises iron deposition information of a target area of the target brain medical image data, the detection model comprises a convolution layer and a spatial attention module which are alternately stacked, the convolution layer is used for carrying out feature extraction on the target brain medical image data, generating feature data and inputting the feature data into the spatial attention module, and the spatial attention module is used for determining the target area in the target brain medical image data based on the feature data, determining a receptive field matched with the target area and acquiring the iron deposition information of the target area by utilizing the receptive field. In a third aspect, embodiments of the present application provide a computing device, including a processing component and a storage component; The storage component stores one or more computer instructions, and the one or more computer instructions are used for being called and executed by the processing component to realize the disease detection method provided by the embodiment of the application. In a fourth aspect, in an embodiment of the present application, there is provided a computer storage medium storing a computer program, where the computer program, when executed by a computer, implements the disease detection method provided in the embodiment of the present application. In a fifth aspect, in an embodiment of the present application, there is provided a computer program product, where the computer program product includes computer program code, and when the computer program code is executed by a computer, the method for detecting a disease provided in the embodiment of the present application is implemented. In the embodiment of the application, the detection method and the detection system detect target brain medical image data by adopting a detection model with alternately stacked convolution layers and spatial attention modes, wherein the convolution layers can perform feature extraction on the image, extract valuable features such