A survey on deep learning for polyp segmentation: techniques, challenges and future trends
Abstract Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually e...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-01-01
|
| Series: | Visual Intelligence |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44267-024-00071-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559018557931520 |
|---|---|
| author | Jiaxin Mei Tao Zhou Kaiwen Huang Yizhe Zhang Yi Zhou Ye Wu Huazhu Fu |
| author_facet | Jiaxin Mei Tao Zhou Kaiwen Huang Yizhe Zhang Yi Zhou Ye Wu Huazhu Fu |
| author_sort | Jiaxin Mei |
| collection | DOAJ |
| description | Abstract Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had problems capturing global context and lacked robustness to complex scenarios. With the advent of deep learning, more and more medical image segmentation algorithms based on deep learning networks have emerged, making significant progress in the field. This paper provides a comprehensive review of polyp segmentation algorithms. We first review some traditional algorithms based on manually extracted features and deep segmentation algorithms, and then describe benchmark datasets related to the topic. Specifically, we carry out a comprehensive evaluation of recent deep learning models and results based on polyp size, taking into account the focus of research topics and differences in network structures. Finally, we discuss the challenges of polyp segmentation and future trends in the field. |
| format | Article |
| id | doaj-art-94e683176c724ee5aac950da342fa5a0 |
| institution | Kabale University |
| issn | 2097-3330 2731-9008 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Visual Intelligence |
| spelling | doaj-art-94e683176c724ee5aac950da342fa5a02025-01-05T12:50:16ZengSpringerVisual Intelligence2097-33302731-90082025-01-013112010.1007/s44267-024-00071-wA survey on deep learning for polyp segmentation: techniques, challenges and future trendsJiaxin Mei0Tao Zhou1Kaiwen Huang2Yizhe Zhang3Yi Zhou4Ye Wu5Huazhu Fu6PCA Lab, Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of EducationPCA Lab, Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of EducationPCA Lab, Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of EducationPCA Lab, Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of EducationSchool of Computer Science and Engineering, Southeast UniversityPCA Lab, Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of EducationInstitute of High Performance Computing, A*STARAbstract Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had problems capturing global context and lacked robustness to complex scenarios. With the advent of deep learning, more and more medical image segmentation algorithms based on deep learning networks have emerged, making significant progress in the field. This paper provides a comprehensive review of polyp segmentation algorithms. We first review some traditional algorithms based on manually extracted features and deep segmentation algorithms, and then describe benchmark datasets related to the topic. Specifically, we carry out a comprehensive evaluation of recent deep learning models and results based on polyp size, taking into account the focus of research topics and differences in network structures. Finally, we discuss the challenges of polyp segmentation and future trends in the field.https://doi.org/10.1007/s44267-024-00071-wPolyp segmentationDeep learningComprehensive evaluationMedical imaging |
| spellingShingle | Jiaxin Mei Tao Zhou Kaiwen Huang Yizhe Zhang Yi Zhou Ye Wu Huazhu Fu A survey on deep learning for polyp segmentation: techniques, challenges and future trends Visual Intelligence Polyp segmentation Deep learning Comprehensive evaluation Medical imaging |
| title | A survey on deep learning for polyp segmentation: techniques, challenges and future trends |
| title_full | A survey on deep learning for polyp segmentation: techniques, challenges and future trends |
| title_fullStr | A survey on deep learning for polyp segmentation: techniques, challenges and future trends |
| title_full_unstemmed | A survey on deep learning for polyp segmentation: techniques, challenges and future trends |
| title_short | A survey on deep learning for polyp segmentation: techniques, challenges and future trends |
| title_sort | survey on deep learning for polyp segmentation techniques challenges and future trends |
| topic | Polyp segmentation Deep learning Comprehensive evaluation Medical imaging |
| url | https://doi.org/10.1007/s44267-024-00071-w |
| work_keys_str_mv | AT jiaxinmei asurveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT taozhou asurveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT kaiwenhuang asurveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT yizhezhang asurveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT yizhou asurveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT yewu asurveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT huazhufu asurveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT jiaxinmei surveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT taozhou surveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT kaiwenhuang surveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT yizhezhang surveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT yizhou surveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT yewu surveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends AT huazhufu surveyondeeplearningforpolypsegmentationtechniqueschallengesandfuturetrends |