Thoracic cavity multi-organ segmentation method based on cascade residual full convolutional network

Abstract

The invention discloses a thoracic cavity multi-organ segmentation method based on a cascade residual full convolutional network. The method comprises the following steps: roughly segmenting each organ by using a rough segmentation model for positioning the range of each organ, then using the single fine segmentation model of each organ for carrying out fine segmentation on the coarsely segmentedand positioned region to obtain a fine segmentation result of each organ, finally, combining the results to obtain a final multi-organ segmentation result, and reserving more details in the segmentation result. The method is improved on the basis of u-net, and residual connection and an attention mechanism of a feature dimension are introduced into a down-sampling module in u-net, so that the network is easier to train, and has an automatic feature selection capability. Besides, a cascading strategy is introduced, and a staged segmentation network is used, so that rapid and accurate segmentation of multiple organs of the thoracic cavity CT is realized.

Description

technical field [0001] The invention belongs to the field of medical CT image processing, and in particular relates to a multi-organ segmentation method of the thoracic cavity based on a cascaded residual full convolution network. Background technique [0002] Radiation therapy is a common option for treating lung and esophageal cancer. During radiation therapy planning, physicians will manually delineate the target tumor and nearby organs (known as organs at risk OARs), which is often time-consuming and plagued by large subjective variability. To make matters worse, certain organs, such as the esophagus and trachea, are difficult to delineate due to large variations in position and contour, small size, and low contrast in CT scans. [0003] CT is the most commonly used detection method in disease diagnosis. It uses X-ray beams to scan a layer of a certain thickness of the human body, and the detector receives the X-rays that pass through this layer, converts them into visi...

AI Technical Summary

Problems solved by technology

One is a method based on a 2D model. This method cuts a 3D CT image into a 2D image, and uses a 2D segmentation network, such as u-net, to perform segmentation, and superimposes the obtained multiple 2D segmentation results to obtain a 3D image. Segmentation results. The advantage of this method is that it can accurately segment each layer of images and learn more detailed information. However, it cannot learn spatial information of another dimension, and the spatial continuity is poor.

Another method is the method based on the 3d model. This method directly inputs the CT image into the 3d segmentation network, such as v-net, 3d u-net, etc., and directly outputs the 3d segmentation result. The advantage of this method is that it can take into account The association between layers, however, 3D network calculation is too large, easily limited by hardware capabilities

Images