Epileptic focus three-dimensional automatic positioning system based on deep learning

Abstract

The invention discloses an epileptic lesion three-dimensional automatic positioning system based on deep learning. The system comprises: a PET image acquisition and marking module; a PET image and standard symmetrical brain template registration module; a PET image data preprocessing module wich is used for generating mirror image pairs of the left and right brain image blocks; a twin network SiameseNet training module which comprises two deep residual convolutional neural networks sharing weight parameters, wherein an output layer is connected with a multi-layer perceptron and a softmax layer, and the networks are trained by using a training set carrying images of epileptic lesions and normal images to obtain a network model; and a classification module and an epileptic focus positioningmodule which are used for generating a probability heat map from a newly input PET image by utilizing the trained network model, judging whether the image is normal or carries an epileptic focus sample through a classifier, and then predicting the position of an epileptic focus area. According to the system, the epileptic focus of the PET image is automatically positioned by introducing the mirrorimage pair of the image block and the twin network SiameseNet, so that the positioning accuracy and efficiency of the epileptic focus can be effectively improved, and the robustness is relatively high.

Description

technical field [0001] The invention relates to the technical field of medical imaging engineering, in particular to a three-dimensional automatic positioning system for epileptogenic focus based on deep learning. Background technique [0002] With the development of medical imaging technology and artificial intelligence technology, automatic and semi-automatic computer-aided diagnosis systems are widely used in precise diagnosis and treatment to improve diagnostic accuracy and prognosis. Currently, detection systems for epilepsy include positron emission tomography (PET), magnetic resonance imaging (MRI), single photon emission computed tomography (SPECT) and electroencephalography (EEG). and prognosis with higher sensitivity. For the determination of the type of epilepsy and the surgical treatment of refractory epilepsy, it is necessary to use a diagnostic system to accurately locate the location of the epileptogenic focus. However, conventional routine clinical diagnosi...

AI Technical Summary

Problems solved by technology

Because the area is often much larger than the lesion area, the method will ignore subtle changes, resulting in a decrease in its detection sensitivity

Voxelwise statistical methods typically use Statistical Parametric Mapping (SPM) software to compare data from individual cases and control groups, however, voxelwise statistical methods are highly sensitive to registration errors and are prone to false positives in misaligned regions

2. Most of the existing algorithms are only suitable for 2D natural image processing, and since PET imaging is a 3D structure composed of parallel scanning image frames, 2D localization algorithms will ignore important inter-frame information

3. Due to the small amount of medical image data, the lack of high-quality labeled data and training samples, and the large difference in the number of positive and negative samples resulting in sample imbalance, the trained model may be overfitting or the model generalization ability is not high.

Images