Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?
This review provides a consolidated overview of state-of-the-art 3D medical image segmentation techniques for researchers and practitioners in medical image analysis.
This paper reviews top methods from ten 3D medical image segmentation challenges in 2020, covering diverse tasks and datasets. It identifies common successful practices among these methods and discusses open research problems in the field.
Segmentation is one of the most important and popular tasks in medical image analysis, which plays a critical role in disease diagnosis, surgical planning, and prognosis evaluation. During the past five years, on the one hand, thousands of medical image segmentation methods have been proposed for various organs and lesions in different medical images, which become more and more challenging to fairly compare different methods. On the other hand, international segmentation challenges can provide a transparent platform to fairly evaluate and compare different methods. In this paper, we present a comprehensive review of the top methods in ten 3D medical image segmentation challenges during 2020, covering a variety of tasks and datasets. We also identify the "happy-families" practices in the cutting-edge segmentation methods, which are useful for developing powerful segmentation approaches. Finally, we discuss open research problems that should be addressed in the future. We also maintain a list of cutting-edge segmentation methods at \url{https://github.com/JunMa11/SOTA-MedSeg}.