A Review of Non-Fully Supervised Deep Learning for Medical Image Segmentation
Medical image segmentation, a critical task in medical image analysis, aims to precisely delineate regions of interest (ROIs) such as organs, lesions, and cells, and is crucial for applications including computer-aided diagnosis, surgical planning, radiation therapy, and pathological analysis. While...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/6/433 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839653775031140352 |
|---|---|
| author | Xinyue Zhang Jianfeng Wang Jinqiao Wei Xinyu Yuan Ming Wu |
| author_facet | Xinyue Zhang Jianfeng Wang Jinqiao Wei Xinyu Yuan Ming Wu |
| author_sort | Xinyue Zhang |
| collection | DOAJ |
| description | Medical image segmentation, a critical task in medical image analysis, aims to precisely delineate regions of interest (ROIs) such as organs, lesions, and cells, and is crucial for applications including computer-aided diagnosis, surgical planning, radiation therapy, and pathological analysis. While fully supervised deep learning methods have demonstrated remarkable performance in this domain, their reliance on large-scale, pixel-level annotated datasets—a significant label scarcity challenge—severely hinders their widespread deployment in clinical settings. Addressing this limitation, this review focuses on non-fully supervised learning paradigms, systematically investigating the application of semi-supervised, weakly supervised, and unsupervised learning techniques for medical image segmentation. We delve into the theoretical foundations, core advantages, typical application scenarios, and representative algorithmic implementations associated with each paradigm. Furthermore, this paper compiles and critically reviews commonly utilized benchmark datasets within the field. Finally, we discuss future research directions and challenges, offering insights for advancing the field and reducing dependence on extensive annotation. |
| format | Article |
| id | doaj-art-91e9a88e77bb43d187d3bc65c4d2911f |
| institution | Matheson Library |
| issn | 2078-2489 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj-art-91e9a88e77bb43d187d3bc65c4d2911f2025-06-25T13:57:28ZengMDPI AGInformation2078-24892025-05-0116643310.3390/info16060433A Review of Non-Fully Supervised Deep Learning for Medical Image SegmentationXinyue Zhang0Jianfeng Wang1Jinqiao Wei2Xinyu Yuan3Ming Wu4College of Artificial Intelligence, Taiyuan University of Technology, Jinzhong 036000, ChinaSchool of Software, Taiyuan University of Technology, Jinzhong 036000, ChinaSchool of Software, Taiyuan University of Technology, Jinzhong 036000, ChinaSchool of Software, Taiyuan University of Technology, Jinzhong 036000, ChinaDepartment of Computer Science, KU Leuven, 3001 Leuven, BelgiumMedical image segmentation, a critical task in medical image analysis, aims to precisely delineate regions of interest (ROIs) such as organs, lesions, and cells, and is crucial for applications including computer-aided diagnosis, surgical planning, radiation therapy, and pathological analysis. While fully supervised deep learning methods have demonstrated remarkable performance in this domain, their reliance on large-scale, pixel-level annotated datasets—a significant label scarcity challenge—severely hinders their widespread deployment in clinical settings. Addressing this limitation, this review focuses on non-fully supervised learning paradigms, systematically investigating the application of semi-supervised, weakly supervised, and unsupervised learning techniques for medical image segmentation. We delve into the theoretical foundations, core advantages, typical application scenarios, and representative algorithmic implementations associated with each paradigm. Furthermore, this paper compiles and critically reviews commonly utilized benchmark datasets within the field. Finally, we discuss future research directions and challenges, offering insights for advancing the field and reducing dependence on extensive annotation.https://www.mdpi.com/2078-2489/16/6/433medical image segmentationsemi-supervised learningweakly supervised learningunsupervised learningsurvey |
| spellingShingle | Xinyue Zhang Jianfeng Wang Jinqiao Wei Xinyu Yuan Ming Wu A Review of Non-Fully Supervised Deep Learning for Medical Image Segmentation Information medical image segmentation semi-supervised learning weakly supervised learning unsupervised learning survey |
| title | A Review of Non-Fully Supervised Deep Learning for Medical Image Segmentation |
| title_full | A Review of Non-Fully Supervised Deep Learning for Medical Image Segmentation |
| title_fullStr | A Review of Non-Fully Supervised Deep Learning for Medical Image Segmentation |
| title_full_unstemmed | A Review of Non-Fully Supervised Deep Learning for Medical Image Segmentation |
| title_short | A Review of Non-Fully Supervised Deep Learning for Medical Image Segmentation |
| title_sort | review of non fully supervised deep learning for medical image segmentation |
| topic | medical image segmentation semi-supervised learning weakly supervised learning unsupervised learning survey |
| url | https://www.mdpi.com/2078-2489/16/6/433 |
| work_keys_str_mv | AT xinyuezhang areviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT jianfengwang areviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT jinqiaowei areviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT xinyuyuan areviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT mingwu areviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT xinyuezhang reviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT jianfengwang reviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT jinqiaowei reviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT xinyuyuan reviewofnonfullysuperviseddeeplearningformedicalimagesegmentation AT mingwu reviewofnonfullysuperviseddeeplearningformedicalimagesegmentation |