{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:16:31Z","timestamp":1783696591658,"version":"3.55.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["[EDDAPA-2024\/100014]"],"award-info":[{"award-number":["[EDDAPA-2024\/100014]"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["C73666\/A31378]"],"award-info":[{"award-number":["C73666\/A31378]"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Accurate segmentation of prostate cancer on magnetic resonance (MR) images is crucial for planning image-guided interventions such as targeted biopsies, cryoablation, and radiotherapy. However, subtle and variable tumour appearances, differences in imaging protocols, and limited expert availability make consistent interpretation difficult. While automated methods aim to address this, they rely on large expertly annotated datasets that are often inconsistent, whereas manual delineation remains labour-intensive. This work aims to bridge the gap between automated and manual segmentation through a framework driven by user-provided point prompts, enabling accurate segmentation with minimal annotation effort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The framework combines reinforcement learning (RL) with a region-growing segmentation process guided by user prompts. Starting from an initial point prompt, region-growing generates a preliminary segmentation, which is iteratively refined through RL. At each step, the RL agent observes the image and current segmentation to predict a new point, from which region growing updates the mask. A reward, balancing segmentation accuracy and voxel-wise uncertainty, encourages exploration of ambiguous regions, allowing the agent to escape local optima and perform sample-specific optimisation. Despite requiring fully supervised training, the framework bridges manual and fully automated segmentation at inference by substantially reducing user effort while outperforming current fully automated methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The framework was evaluated on two public prostate MR datasets (PROMIS and PICAI, with 566 and 1090 cases). It outperformed the previous best automated methods by 9.9% and 8.9%, respectively, with performance comparable to manual radiologist segmentation, reducing annotation time tenfold.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>By combining prompting with RL\u2013driven exploration, the framework achieves radiologist-level prostate cancer segmentation with a fraction of the annotation effort, highlighting the potential of RL to enable adaptive and efficient cancer delineation. Code: URL: github.com\/JQ-Sakura\/prostate-rl-segmentation<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-026-03628-w","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T12:18:40Z","timestamp":1776428320000},"page":"997-1005","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Promptable segmentation with region exploration enables minimal-effort expert-level prostate cancer delineation"],"prefix":"10.1007","volume":"21","author":[{"given":"Junqing","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natasha","family":"Thorley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed Nadeem","family":"Abbasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shonit","family":"Punwani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zion","family":"Tse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yipeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5004-0663","authenticated-orcid":false,"given":"Shaheer U.","family":"Saeed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"issue":"10071","key":"3628_CR1","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1016\/S0140-6736(16)32401-1","volume":"389","author":"HU Ahmed","year":"2017","unstructured":"Ahmed HU, Bosaily AE-S, Brown LC, Gabe R, Kaplan R, Parmar MK, Collaco-Moraes Y, Ward K, Hindley RG, Freeman A, Kirkham A, Oldroyd R, Parker C, Emberton M (2017) PROMIS-Study-Group: Diagnostic accuracy of multi-parametric mri and trus biopsy in prostate cancer (promis): a paired validating confirmatory study. The Lancet 389(10071):815\u2013822","journal-title":"The Lancet"},{"key":"3628_CR2","doi-asserted-by":"crossref","unstructured":"Penzkofer T, Tempany-Afdhal CM (2014) Prostate cancer detection and diagnosis: the role of mr and its comparison with other diagnostic modalities-a radiologist\u2019s perspective. NMR Biomed 27(1)","DOI":"10.1002\/nbm.3002"},{"key":"3628_CR3","doi-asserted-by":"crossref","unstructured":"Dos-Santos-Silva I, Gupta S, Orem J, Shulman LN (2022) Global disparities in access to cancer care. Communications medicine 2(1)","DOI":"10.1038\/s43856-022-00097-5"},{"key":"3628_CR4","doi-asserted-by":"crossref","unstructured":"Sanders JW, Mok H, Hanania AN, Venkatesan AM, Tang C, Bruno TL, Thames HD, Kudchadker RJ, Frank SJ (2022) Computer-aided segmentation on mri for prostate radiotherapy, part i: Quantifying human interobserver variability of the prostate and organs at risk and its impact on radiation dosimetry. Radiother Oncol 169","DOI":"10.1016\/j.radonc.2021.12.011"},{"key":"3628_CR5","doi-asserted-by":"crossref","unstructured":"Sunoqrot MR, Saha A, Hosseinzadeh M, Elschot M, Huisman H (2022) Artificial intelligence for prostate mri: open datasets, available applications, and grand challenges. European radiology experimental 6(1)","DOI":"10.1186\/s41747-022-00288-8"},{"key":"3628_CR6","doi-asserted-by":"crossref","unstructured":"Karam L, Wang Y, Kasivisvanathan V, Rusu M, Hu Y, Saeed SU (2025) Promptable cancer segmentation using minimal expert-curated data. In: Annual Conference on Medical Image Understanding and Analysis (MIUA), pp. 44\u201358","DOI":"10.1007\/978-3-031-98694-9_4"},{"key":"3628_CR7","doi-asserted-by":"crossref","unstructured":"Ma J, He Y, Li F, Han L, You C, Wang B (2024) Segment anything in medical images. Nat Commun 15(1)","DOI":"10.1038\/s41467-024-44824-z"},{"key":"3628_CR8","doi-asserted-by":"crossref","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, Xiao T, Whitehead S, Berg AC, Lo W-Y, Dollar P, Girshick R (2023) Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"3628_CR9","doi-asserted-by":"crossref","unstructured":"Aggarwal R, Sounderajah V, Martin G, Ting DS, Karthikesalingam A, King D, Ashrafian H, Darzi A (2021) Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis. NPJ digital medicine 4(1)","DOI":"10.1038\/s41746-021-00438-z"},{"key":"3628_CR10","doi-asserted-by":"crossref","unstructured":"Yan W, Chiu B, Shen Z, Yang Q, Syer T, Min Z, Punwani S, Emberton M, Atkinson D, Barratt DC, Hu Y (2024) Combiner and hypercombiner networks: Rules to combine multimodality mr images for prostate cancer localisation. Med Image Anal 91","DOI":"10.1016\/j.media.2023.103030"},{"key":"3628_CR11","doi-asserted-by":"crossref","unstructured":"Adams R, Bischof L (1994) Seeded region growing. IEEE Trans Pattern Anal Mach Intell 16(6)","DOI":"10.1109\/34.295913"},{"key":"3628_CR12","doi-asserted-by":"crossref","unstructured":"Czolbe S, Arnavaz K, Krause O, Feragen A (2021) Is segmentation uncertainty useful? In: International Conference on Information Processing in Medical Imaging (IPMI)","DOI":"10.1007\/978-3-030-78191-0_55"},{"key":"3628_CR13","unstructured":"Ahn S, Kim S, Yun S-Y (2023) Mitigating dataset bias by using per-sample gradient. In: International Conference on Learning Representations (ICLR)"},{"key":"3628_CR14","doi-asserted-by":"crossref","unstructured":"Saeed SU, Huang S, Ramalhinho J, Gayo IJ, Montana-Brown N, Bonmati E, Pereira SP, Davidson B, Barratt DC, Clarkson MJ, Hu Y (2024) Competing for pixels: a self-play algorithm for weakly-supervised semantic segmentation. IEEE Trans Pattern Anal Mach Intell 47(2)","DOI":"10.1109\/TPAMI.2024.3474094"},{"key":"3628_CR15","doi-asserted-by":"crossref","unstructured":"Vlontzos A, Alansary A, Kamnitsas K, Rueckert D, Kainz B (2019) Multiple landmark detection using multi-agent reinforcement learning. In: International Conference on Medical Image Computing and Computer-assisted Intervention","DOI":"10.1007\/978-3-030-32251-9_29"},{"key":"3628_CR16","doi-asserted-by":"crossref","unstructured":"Alansary A, Oktay O, Li Y, Le Folgoc L, Hou B, Vaillant G, Kamnitsas K, Vlontzos A, Glocker B, Kainz B, Rueckert D (2019) Evaluating reinforcement learning agents for anatomical landmark detection. Med Image Anal 53","DOI":"10.1016\/j.media.2019.02.007"},{"key":"3628_CR17","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"3628_CR18","doi-asserted-by":"crossref","unstructured":"...Saha A, Bosma JS, Twilt JJ, Van Ginneken B, Bjartell A, Padhani AR, Bonekamp D, Villeirs G, Salomon G, Giannarini G, Kalpathy-Cramer J, Barentsz J, Maier-Hein K, Rusu M, Rouvi\u00e8re O, Bergh R, Panebianco V, Kasivisvanathan V, Obuchowski N, Yakar D, Elschot M, Veltman J, F\u00fctterer J, Rooij M, Huisman H (2024) PI-CAI-consortium: Artificial intelligence and radiologists in prostate cancer detection on mri (pi-cai): an international, paired, non-inferiority, confirmatory study. Lancet Oncol 25(7)","DOI":"10.1016\/S1470-2045(24)00220-1"},{"key":"3628_CR19","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3628_CR20","unstructured":"Ravi N, Gabeur V, Hu Y-T, Hu R, Ryali C, Ma T, Khedr H, R\u00e4dle R, Rolland C, Gustafson L, Mintun E, Pan J, Alwala K, Carion N, Wu C, Girshick R, Doll\u00e1r P, Feichtenhofer C (2024) Sam 2: Segment anything in images and videos. In: International Conference on Learning Representations (ICLR)"},{"key":"3628_CR21","unstructured":"Carion N, Gustafson L, Hu Y-T, Debnath S, Hu R, Suris D, Ryali C, Alwala KV, Khedr H, Huang A, et al (2026) Sam 3: Segment anything with concepts. In: International Conference on Learning Representations (ICLR)"},{"key":"3628_CR22","unstructured":"Ma J, Yang Z, Kim S, Chen B, Baharoon M, Fallahpour A, Asakereh R, Lyu H, Wang B (2025) Medsam2: Segment anything in 3d medical images and videos. arXiv:2504.03600"},{"key":"3628_CR23","unstructured":"Liu A, Xue R, Cao XR, Shen Y, Lu Y, Li X, Chen Q, Chen J (2025) Medsam3: Delving into segment anything with medical concepts. arXiv:2511.19046"},{"key":"3628_CR24","doi-asserted-by":"crossref","unstructured":"Yi W, Wang Y, Thorley N, Ng A, Punwani S, Kasivisvanathan V, Barratt DC, Saeed SU, Hu Y (2025) T2-only prostate cancer prediction by meta-learning from bi-parametric mr imaging. In: 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","DOI":"10.1109\/ISBI60581.2025.10981221"},{"key":"3628_CR25","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Nath V, Tang Y, Yang D, Roth HR, Xu D (2021) Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. In: International MICCAI Brainlesion Workshop, pp 272\u2013284. Springer","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"3628_CR26","doi-asserted-by":"crossref","unstructured":"Butoi VI, Ortiz JJG, Ma T, Sabuncu MR, Guttag J, Dalca AV (2023) Universeg: Universal medical image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision","DOI":"10.1109\/ICCV51070.2023.01960"},{"key":"3628_CR27","doi-asserted-by":"crossref","unstructured":"Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH (2021) nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2)","DOI":"10.1038\/s41592-020-01008-z"},{"key":"3628_CR28","unstructured":"Sim\u00e9oni O, Vo HV, Seitzer M, Baldassarre F, Oquab M, Jose C, Khalidov V, Szafraniec M, Yi S, Ramamonjisoa M, et al (2025) Dinov3. arXiv preprint arXiv:2508.10104"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03628-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03628-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03628-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:55:38Z","timestamp":1783695338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03628-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":28,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["3628"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03628-w","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]},"assertion":[{"value":"19 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Our work uses open-source datasets where all original procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and\/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Informed consent was obtained from all individual participants included in the original studies.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}