MULTIPLE DEEP CODER NETWORKS FOR MEDICAL IMAGES USING IMAGE SEGMENTATION

Electronics and Communication Engineering

Image segmentation is commonly used to detect objects and boundaries. It is vital in many clinical claims, such as the pathological diagnosis of hepatic diseases, surgical planning, and postoperative assessment. The segmentation mission is hindered by fuzzy boundaries, complex backgrounds, and appearances of objects of interest, which vary considerably. The success of the approach is ability highly based on the operator's abilities and the level of hand-eye coordination. Thus, this project was strongly motivated by the necessity to obtain an early and accurate diagnosis of a detected object in medical images. In this project, propose a new polyp segmentation method based on the architecture of a multiple deep encoder decoder networks combination called CDED-net. The architecture cannot only hold multi-level contextual information by extracting discriminative features at different effective fields-of-view and multiple image scales but also learn rich information features from missing pixels in the training phase. Moreover, the network is also able to capture object boundaries by using multi scale effective decoders. It also proposes a strategy for improving the method’s segmentation performance based on a combination of a boundary-emphasization data augmentation method and a new effective dice loss function. The goal of this project is to make our deep learning network available with poorly defined object boundaries, which are caused by the non-specular transition zone between the back ground and fore ground regions.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.