A Review on Progress in Semantic Image Segmentation and Its Application to Medical Images

Semantic image segmentation is a popular image segmentation technique where each pixel in an image is labeled with an object class. This technique has become a vital part of image analysis nowadays as it facilitates the description, categorization, and visualization of the regions of interest in an image. The recent developments in computer vision algorithms and the increasing availability of large datasets have made semantic image segmentation very popular in the field of computer vision. Motivated by the human visual system which can identify objects in a complex scene very efficiently, researchers are interested in building a model that can semantically segment an image into meaningful object classes. This paper reviews deep learning-based semantic segmentation techniques that use deep neural network architectures for image segmentation of biomedical images. We have provided a discussion on the fundamental concepts related to deep learning methods used in semantic segmentation for the benefit of readers. The standard datasets and existing deep network architectures used in both medical and non-medical fields are discussed with their significance. Finally, this paper concludes by discussing the challenges and future research directions in the field of deep learning-based semantic segmentation for applications in the medical field. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.