Medical image segmentation using deep semantic-based methods: A review of techniques, applications and emerging trends

• Semantic-based segmentation (Semseg) methods are presented in deep learning architecture. • A comparative study is presented for reviewed paper based on performance. • Existing challenges, problems in DL-based semantic segmentation approaches are discussed. • The challenges of Semseg applications are mentioned for other researchers. • Prospect for future work in this area for stable medical image segmentation. Semantic-based segmentation (Semseg) methods play an essential part in medical imaging analysis to improve the diagnostic process. In Semseg technique, every pixel of an image is classified into an instance, where each class is corresponded by an instance. In particular, the semantic segmentation can be used by many medical experts in the domain of radiology, ophthalmologists, dermatologist, and image-guided radiotherapy. The authors present perspectives on the development of an architectural, and operational mechanism of each machine learning-based semantic segmentation approach with merits and demerits. In this regard, researchers have proposed different Semseg methods and examined their performance in a variety of applications such as medical image analysis (e.g., medical image classification and segmentation). A review of recent advances in Semseg techniques are presented in this paper by applying computational image processing and machine learning methods. This article is further presented a comprehensive investigation on how different architectures are helpful for medical image segmentation. Finally, advantages, open challenges, and possible future directions are elaborated in the discussion part, beneficial to the research community to understand the significance of the available medical imaging segmentation technology based on Semseg and thus deliver robust segmentation solutions.