Book chapter
Chapter 18 - Deep learning medical image segmentation
Medical Image Analysis, pp.475-500
Elsevier Ltd
2024
DOI: 10.1016/B978-0-12-813657-7.00042-X
Abstract
Taking fundamentals of deep learning as pre-requisite, this chapter examines the most relevant approaches to Deep Learning (DL) segmentation starting with Convolutional Neural Networks (CNNs) such as the Fully Convolutional Network (FCN), U-Net, and nnU-Net. Alternative approaches based on Transformer networks are presented. Hybrid Deep Learning and graph-optimization approach Deep LOGISMOS delivers improved performance compared to pure DL methods and allows efficient algorithmic adjudiction. Assisted and sparse annotation approaches are presented that alleviate the burden of manually annotating a large dataset. Explainability of Deep Learning is discussed. The chapter concludes with a case study comparing pure DL and hybrid image segmentation approaches.
Details
- Title: Subtitle
- Chapter 18 - Deep learning medical image segmentation
- Creators
- Sean Mullan - University of IowaLichun Zhang - University of IowaHonghai Zhang - University of IowaMilan Sonka - University of Iowa
- Resource Type
- Book chapter
- Publication Details
- Medical Image Analysis, pp.475-500
- DOI
- 10.1016/B978-0-12-813657-7.00042-X
- Publisher
- Elsevier Ltd
- Language
- English
- Date published
- 2024
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; The Iowa Institute for Biomedical Imaging; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Computer Science; Ophthalmology and Visual Sciences
- Record Identifier
- 9984469060102771
Metrics
62 Record Views