{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:32:46Z","timestamp":1773153166139,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T00:00:00Z","timestamp":1723507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,13]]},"DOI":"10.1145\/3706890.3707006","type":"proceedings-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T13:37:20Z","timestamp":1736775440000},"page":"679-684","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing the Medical Image Segmentation capability of Segment Anything Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9878-271X","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7035-6051","authenticated-orcid":false,"given":"Yu","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,1,13]]},"reference":[{"key":"e_1_3_3_1_1_2","volume-title":"Pre-training of deep bidirectional transformers for language understanding.\" arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Devlin, Jacob. \"Bert: Pre-training of deep bidirectional transformers for language understanding.\" arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_3_1_2_2","first-page":"4015","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision.","author":"Kirillov Alexander","year":"2023","unstructured":"Kirillov, Alexander, et al. \"Segment anything.\" Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023. pp. 4015-4026."},{"key":"e_1_3_3_1_3_2","volume-title":"A comprehensive survey on segment anything model for vision and beyond.\" arXiv preprint arXiv:2305.08196","author":"Zhang Chunhui","year":"2023","unstructured":"Zhang, Chunhui, et al. \"A comprehensive survey on segment anything model for vision and beyond.\" arXiv preprint arXiv:2305.08196, 2023."},{"key":"e_1_3_3_1_4_2","volume-title":"Medical sam adapter: Adapting segment anything model for medical image segmentation.\" arXiv preprint arXiv:2304.12620","author":"Wu Junde","year":"2023","unstructured":"Wu, Junde, et al. \"Medical sam adapter: Adapting segment anything model for medical image segmentation.\" arXiv preprint arXiv:2304.12620, 2023."},{"key":"e_1_3_3_1_5_2","volume-title":"Exploring sparse visual prompt for cross-domain semantic segmentation.\" arXiv preprint arXiv:2303.097921","author":"Yang Senqiao","year":"2023","unstructured":"Yang, Senqiao, et al. \"Exploring sparse visual prompt for cross-domain semantic segmentation.\" arXiv preprint arXiv:2303.097921, 2023."},{"key":"e_1_3_3_1_6_2","first-page":"451","volume-title":"MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26","year":"2020","unstructured":"D. Jha et al., \"Kvasir-seg: A segmented polyp dataset.\" in MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26, 2020, pp. 451-462: Springer."},{"key":"e_1_3_3_1_7_2","volume-title":"Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic).\" arXiv preprint arXiv:1902.03368","author":"Codella Noel","year":"2019","unstructured":"Codella, Noel, et al. \"Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic).\" arXiv preprint arXiv:1902.03368, 2019."},{"key":"e_1_3_3_1_8_2","first-page":"218","volume-title":"MMM 2021, Prague, Czech Republic, June 22\u201324, 2021, Proceedings, Part II 27","year":"2021","unstructured":"D. Jha et al., \"Kvasir-instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy.\" in Multimedia Modeling: 27th International Conference, MMM 2021, Prague, Czech Republic, June 22\u201324, 2021, Proceedings, Part II 27, 2021, pp. 218-229: Springer."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Long Jonathan Evan Shelhamer and Trevor Darrell. \"Fully convolutional networks for semantic segmentation.\" Proceedings of the IEEE conference on computer vision and pattern recognition. 2015 pp. 3431-3440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_3_1_10_2","volume-title":"A deep convolutional encoder-decoder architecture for image segmentation.\" IEEE transactions on pattern analysis and machine intelligence 39.12","author":"Badrinarayanan Vijay","year":"2017","unstructured":"Badrinarayanan, Vijay, Alex Kendall, and Roberto Cipolla. \"Segnet: A deep convolutional encoder-decoder architecture for image segmentation.\" IEEE transactions on pattern analysis and machine intelligence 39.12, 2017, 2481-2495."},{"key":"e_1_3_3_1_11_2","unstructured":"Chen Liang-Chieh. \"Semantic image segmentation with deep convolutional nets and fully connected CRFs.\" arXiv preprint arXiv:1412.7062 2014."},{"key":"e_1_3_3_1_12_2","first-page":"12537","volume":"2021","unstructured":"L. Zhu et al, \"Learning statistical texture for semantic segmentation.\" in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12537-12546.","journal-title":"\"Learning statistical texture for semantic segmentation.\" in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_3_1_13_2","first-page":"6798","volume":"2019","unstructured":"F. Zhang et al, \"Acfnet: Attentional class feature network for semantic segmentation.\" in Proceedings of the IEEE\/CVF international conference on computer vision, 2019, pp. 6798-6807.","journal-title":"\"Acfnet: Attentional class feature network for semantic segmentation.\" in Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"e_1_3_3_1_14_2","first-page":"6881","volume-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers.\" in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","year":"2021","unstructured":"S. Zheng et al, \"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers.\" in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2021, pp. 6881-6890."},{"key":"e_1_3_3_1_15_2","first-page":"2790","volume-title":"Parameter-efficient transfer learning for NLP.\" in International conference on machine learning","year":"2019","unstructured":"N. Houlsby et al, \"Parameter-efficient transfer learning for NLP.\" in International conference on machine learning, 2019, pp. 2790-2799."},{"key":"e_1_3_3_1_16_2","volume-title":"Vision transformer adapter for dense predictions.\" arXiv preprint arXiv:2205.08534","author":"Chen Zhe","year":"2022","unstructured":"Chen, Zhe, et al. \"Vision transformer adapter for dense predictions.\" arXiv preprint arXiv:2205.08534, 2022."},{"key":"e_1_3_3_1_17_2","volume-title":"Segment anything in high quality.\" Advances in Neural Information Processing Systems 36","author":"Ke Lei","year":"2024","unstructured":"Ke, Lei, et al. \"Segment anything in high quality.\" Advances in Neural Information Processing Systems 36, 2024."},{"key":"e_1_3_3_1_18_2","volume-title":"Segment everything everywhere all at once.\" Advances in Neural Information Processing Systems 36","author":"Zou Xueyan","year":"2024","unstructured":"Zou, Xueyan, et al. \"Segment everything everywhere all at once.\" Advances in Neural Information Processing Systems 36, 2024."},{"key":"e_1_3_3_1_19_2","volume-title":"Semantic-sam: Segment and recognize anything at any granularity.\" arXiv preprint arXiv:2307.04767","author":"Li Feng","year":"2023","unstructured":"Li, Feng, et al. \"Semantic-sam: Segment and recognize anything at any granularity.\" arXiv preprint arXiv:2307.04767, 2023."},{"key":"e_1_3_3_1_20_2","volume-title":"Speech and Signal Processing (ICASSP). IEEE","author":"Wang Chengliang","year":"2024","unstructured":"Wang, Chengliang, et al. \"SAM-OCTA: A Fine-Tuning Strategy for Applying Foundation Model OCTA Image Segmentation Tasks.\" ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024."},{"key":"e_1_3_3_1_21_2","volume-title":"Segment anything model (sam) enhanced pseudo labels for weakly supervised semantic segmentation.\" arXiv preprint arXiv:2305.05803","author":"Chen Tianle","year":"2023","unstructured":"Chen, Tianle, et al. \"Segment anything model (sam) enhanced pseudo labels for weakly supervised semantic segmentation.\" arXiv preprint arXiv:2305.05803, 2023."},{"key":"e_1_3_3_1_22_2","first-page":"16000","volume":"2022","unstructured":"K. He et al, \"Masked autoencoders are scalable vision learners.\" in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2022, pp. 16000-16009.","journal-title":"\"Masked autoencoders are scalable vision learners.\" in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"e_1_3_3_1_23_2","volume-title":"Fourier features let networks learn high frequency functions in low dimensional domains.\" Advances in neural information processing systems 33","author":"Tancik Matthew","year":"2020","unstructured":"Tancik, Matthew, et al. \"Fourier features let networks learn high frequency functions in low dimensional domains.\" Advances in neural information processing systems 33, 2020, 7537-7547."},{"key":"e_1_3_3_1_24_2","first-page":"8748","volume-title":"Learning transferable visual models from natural language supervision.\" International conference on machine learning","year":"2021","unstructured":"A. Radford et al., \"Learning transferable visual models from natural language supervision.\" International conference on machine learning, 2021, pp. 8748-8763: PMLR."}],"event":{"name":"ISAIMS 2024: 2024 5th International Symposium on Artificial Intelligence for Medicine Science","location":"Amsterdam Netherlands","acronym":"ISAIMS 2024"},"container-title":["Proceedings of the 2024 5th International Symposium on Artificial Intelligence for Medicine Science"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706890.3707006","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706890.3707006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:20Z","timestamp":1750295840000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706890.3707006"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,13]]},"references-count":24,"alternative-id":["10.1145\/3706890.3707006","10.1145\/3706890"],"URL":"https:\/\/doi.org\/10.1145\/3706890.3707006","relation":{},"subject":[],"published":{"date-parts":[[2024,8,13]]},"assertion":[{"value":"2025-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}