Intestinal tract lesion segmentation method combining multi-scale U-shaped residual encoder and overall reverse attention mechanism

Abstract

The invention discloses an intestinal tract lesion segmentation method combining a multi-scale U-shaped residual encoder and an overall reverse attention mechanism, and the method comprises the steps of taking the multi-scale U-shaped residual encoder as a backbone network to extract the features of an inputted intestinal tract lesion image, and introducing a multi-scale residual block for improving the segmentation reliability to generate an initial prediction image, wherein the U-shaped residual block filled in each stage of the backbone network can directly extract multi-scale features step by step under the condition of keeping a high-resolution feature map and reducing memory and calculation cost; enhancing the shallow features by using an overall attention mechanism which contributes to segmentation of the whole significant intestinal tract focus and refinement of more accurate boundaries to obtain an enhanced initial prediction graph; introducing a reverse attention mechanism for establishing the relationship between the region and the boundary clues to mine more boundary clues and make up the possible error part of an overall attention mechanism refining boundary. According to the invention, better intestinal tract lesion segmentation precision is achieved.

Description

technical field

[0001] The invention relates to the technical field of medical image processing, in particular to an intestinal lesion segmentation method combining a multi-scale U-shaped residual encoder and an overall reverse attention mechanism. Background technique

[0002] Medical image segmentation is an indispensable means to accurately extract specific tissues or regions in images. Segmentation of intestinal lesion images is used for quantitative analysis and research of intestinal diseased areas, which is beneficial to assist doctors in accurate diagnosis. Traditional manual segmentation is time-consuming and inaccurate, so automatic segmentation of intestinal lesions is of great value. Early learning-based methods rely on extracted handcrafted features, which are usually trained as a classifier to distinguish a lesion from its surrounding environment, however, these methods suffer from high miss rates. In recent years, deep learning methods have achieved great suc...

Examples

Embodiment Construction

[0025] In order to clarify the purpose, technical solutions and advantages of the present invention, the present invention will be further described in detail below in conjunction with specific embodiments and accompanying drawings.

[0026] refer to Figure 1 to Figure 6 , an intestinal lesion segmentation method based on the combination of a multi-scale U-shaped residual encoder and an overall reverse attention mechanism, including the following steps:

[0027] Step 1, input data set X={x 1 ,x 2 ,...,x n}, where X represents the input samples in the data set, and x n ∈R 352 ×352 , n represents the number of samples, and the multi-scale U-shaped residual encoder is used as the backbone network to encode the input intestinal lesion image and extract image features. Each level of the backbone network is filled with RSU. By configuring the depth L parameter of RSU, multi-scale features of any spatial resolution can be extracted from the input feature map. RSU extracts mult...

technical field

[0001] The invention relates to the technical field of medical image processing, in particular to an intestinal lesion segmentation method combining a multi-scale U-shaped residual encoder and an overall reverse attention mechanism. Background technique

[0002] Medical image segmentation is an indispensable means to accurately extract specific tissues or regions in images. Segmentation of intestinal lesion images is used for quantitative analysis and research of intestinal diseased areas, which is beneficial to assist doctors in accurate diagnosis. Traditional manual segmentation is time-consuming and inaccurate, so automatic segmentation of intestinal lesions is of great value. Early learning-based methods rely on extracted handcrafted features, which are usually trained as a classifier to distinguish a lesion from its surrounding environment, however, these methods suffer from high miss rates. In recent years, deep learning methods have achieved great suc...

Examples

Embodiment Construction

[0025] In order to clarify the purpose, technical solutions and advantages of the present invention, the present invention will be further described in detail below in conjunction with specific embodiments and accompanying drawings.

[0026] refer to Figure 1 to Figure 6 , an intestinal lesion segmentation method based on the combination of a multi-scale U-shaped residual encoder and an overall reverse attention mechanism, including the following steps:

[0027] Step 1, input data set X={x 1 ,x 2 ,...,x n}, where X represents the input samples in the data set, and x n ∈R 352 ×352 , n represents the number of samples, and the multi-scale U-shaped residual encoder is used as the backbone network to encode the input intestinal lesion image and extract image features. Each level of the backbone network is filled with RSU. By configuring the depth L parameter of RSU, multi-scale features of any spatial resolution can be extracted from the input feature map. RSU extracts mult...

Images