A Multimodal Glioma Image Segmentation Method with Adaptive Attention Gate

Abstract

The invention discloses a multimodal brain glioma image segmentation method based on an adaptive attention gate. The method includes: S1, preprocessing the MRI glioma image data to obtain a data sample set; S2, building a multi-level feature The segmentation network model of the self-adaptive attention gate and the segmentation model training; S3, utilize the segmentation network model that has been trained to carry out lesion segmentation prediction; The attention gate of the present invention can automatically learn a set of weights to represent the characteristics of each layer in the physical feature Importance, adaptively suppresses non-pathological noise of shallow features, and attaches lesion details to deep features; tumor segmentation network uses a hybrid loss function combining binary cross-entropy loss function and dice loss function to train the model. The invention fully excavates the semantic information and detailed features of different levels of deep full convolutional networks. Under the action of attention gate, the best glioma segmentation effect is achieved by fusing features of different levels.

Description

technical field [0001] The present invention relates to a technology for glioma image segmentation based on a fully convolutional deep neural network, in particular to a multimodal glioma image segmentation method with an adaptive attention gate with multi-level features. Background technique [0002] Glioma has the highest mortality rate among brain tumors. These tumors can be divided into low-grade gliomas (LGG) and high-grade gliomas (HGG), with the former being less aggressive and aggressive than the latter. In clinical practice, further informative MRI sequences are particularly useful in the assessment of gliomas. Accurately segmenting gliomas and their internal structures is important not only for treatment planning, but also for subsequent evaluations. However, manual segmentation is time-consuming and subject to internal and internal scoring errors that are difficult to represent. For these reasons, precise semi-automatic or automatic methods are required. Howev...

AI Technical Summary

Problems solved by technology

In the full convolution structure of the existing technical standard, the sampling amount of the feature map is gradually reduced to obtain a sufficiently large receptive field, so as to obtain semantic context information; in this way, the deep feature map presents abstract semantics and global position correlation However, due to the high heterogeneity of glioma images and blurred partition boundaries, it is still difficult to reduce false positives only through rough integration of semantic features and appearance features (such as U-Net and FCN-Net). In order to improve the accuracy, the current The segmentation method of [4] relies on object localization and a multi-stage global segmentation model, reducing the task to a single localization and subsequent fine segmentation steps

Images