A review of medical image processing using deep learning

Medical image segmentation, a new advancement in biomedical image processing, has significantly improved the sustainability of healthcare. It is now a significant area for research in computer vision. Medical image processing based on deep convolutional neural networks has emerged as a research hotspot with the rapid growth of deep learning. The deep learning-based segmentation of medical images is the main topic of this work. In this paper, first, the fundamental concepts and characteristics of deep learning-based medical picture segmentation are introduced. The future development path is broadened by outlining the research status and describing the three primary medical picture segmentation techniques and their limitations. Based on the description of several diseased tissues and organs, a summary of their distinctiveness and traditional segmentation algorithms is provided. Medical picture segmentation based on deep learning has still run into research problems despite the recent remarkable advancements it has made. For instance, the data set contains few medical pictures, the segmentation accuracy is low, and the resolution is poor. The inconsistent segmentation findings fall short of the real clinical needs. A thorough analysis of the most recent deep learning-based medical picture segmentation techniques is presented to aid researchers in resolving current issues.

کلیدواژه ها:

_ Medical Image ، Deep Learning ، Image Segmentation ، Medical Picture