{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T16:41:30Z","timestamp":1764866490583,"version":"3.46.0"},"reference-count":38,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62501172"],"award-info":[{"award-number":["62501172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Planning Project of Guangzhou","award":["SL2023A04J00421"],"award-info":[{"award-number":["SL2023A04J00421"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Pre-extracted lumen information of 3D vessel in medical images can effectively assist doctors in intraoperative navigation and postoperative evaluation, which has important clinical value. The main challenge faced by fully automatic 3D vessel segmentation comes from the imbalanced proportion of the vessels in medical image, which may lead to lost target. In this paper, a fully automatic 3D vessel segmentation method based on small-object-sensitive deep reinforcement learning, is presented. The region of target is firstly detected by the bounding box of a deep reinforcement learning (DRL) network, and then is segmented with a convolutional neural network (CNN). To better detect small vessel object, we have made three improvements to the existing DRL-based detection network: 1) A novel state with random receptive field expansion is applied to provide the agent with necessary information even if part of the target is lost. 2) A Recall-priority reward is presented to provide the most complete region for the next segmentation stage. 3) The dependency of vascular spatial positions between adjacent slices is utilized to correct the errors in detection stage, and the topological integrity of the obtained vascular structure is improved. The proposed method has been extensively validated on a challenging vessel dataset with 100 computed tomography angiography (CTA) scans. The segmentation accuracy of this method is Dice=93.75%, which outperforms the baseline and other automatic 3D vessel segmentation algorithms. This method has advantages in positioning accuracy, segmentation accuracy, and operational efficiency, and can be easily applied to clinical applications.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae23d2","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T22:47:36Z","timestamp":1764110856000},"page":"015001","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Small-object-sensitive deep reinforcement learning for fully automatic 3D vessel segmentation in medical images"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1464-9105","authenticated-orcid":false,"given":"Jingliang","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianyang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"bpexae23d2bib1","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1016\/S0140-6736(22)01970-5","type":"journal-article","article-title":"Acute aortic dissection","volume":"401","author":"Carrel","year":"2023","journal-title":"The Lancet"},{"key":"bpexae23d2bib2","doi-asserted-by":"publisher","first-page":"e334e482","DOI":"10.1161\/CIR.0000000000001106","type":"journal-article","article-title":"2022 acc\/aha guideline for the diagnosis and management of aortic disease: A report of the american heart association\/american college of cardiology joint committee on clinical practice guidelines","volume":"146","author":"Isselbacher","year":"2022","journal-title":"Circulation"},{"key":"bpexae23d2bib3","first-page":"e41","type":"journal-article","article-title":"2025 heart disease and stroke statistics: a report of us and global data from the american heart association","volume":"151","author":"Martin","year":"2025","journal-title":"Circulation"},{"key":"bpexae23d2bib4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.actbio.2019.08.017","type":"journal-article","article-title":"Biomechanics of aortic wall failure with a focus on dissection and aneurysm: a review","volume":"99","author":"Sherifova","year":"2019","journal-title":"Acta Biomater"},{"key":"bpexae23d2bib5","doi-asserted-by":"publisher","first-page":"55S\u20133S","DOI":"10.1016\/j.jvs.2020.05.076","type":"journal-article","article-title":"Society for vascular surgery clinical practice guidelines of thoracic endovascular aortic repair for descending thoracic aortic aneurysms","volume":"73","author":"Upchurch","year":"2021","journal-title":"J. Vasc. Surg."},{"key":"bpexae23d2bib6","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1016\/j.jtcvs.2019.02.097","type":"journal-article","article-title":"Echocardiography-guided aortic cannulation by the seldinger technique for type a dissection with cerebral malperfusion","volume":"159","author":"Shimura","year":"2020","journal-title":"J. Thoracic Cardiovascular Surg."},{"volume":"783","year":"2011","author":"Chiesa","key":"bpexae23d2bib7","type":"book"},{"key":"bpexae23d2bib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4250\/jcvi.2020.0106","type":"journal-article","article-title":"Role of computed tomography in postoperative follow-up of arterial switch operation","volume":"29","author":"Kumar","year":"2021","journal-title":"J. Cardiovasc Imaging"},{"key":"bpexae23d2bib9","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1016\/j.media.2009.07.011","type":"journal-article","article-title":"A review of 3d vessel lumen segmentation techniques: models, features and extraction schemes","volume":"13","author":"Lesage","year":"2009","journal-title":"Med. Image Anal."},{"key":"bpexae23d2bib10","doi-asserted-by":"publisher","first-page":"101773","DOI":"10.1016\/j.media.2020.101773","type":"journal-article","article-title":"Detection, segmentation, simulation and visualization of aortic dissections: A review","volume":"65","author":"Pepe","year":"2020","journal-title":"Med. Image Anal."},{"key":"bpexae23d2bib11","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107454","type":"journal-article","article-title":"A review of retinal vessel segmentation for fundus image analysis","volume":"128","author":"Qin","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"bpexae23d2bib12","first-page":"122","type":"book","article-title":"Lumen segmentation of aortic dissection with cascaded convolutional network","author":"Li","year":"2018"},{"key":"bpexae23d2bib13","doi-asserted-by":"publisher","first-page":"1826","DOI":"10.1109\/TMI.2022.3150005","type":"journal-article","article-title":"Segmentation of the true lumen of aorta dissection via morphology-constrained stepwise deep mesh regression","volume":"41","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae23d2bib14","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.neucom.2018.05.019","type":"journal-article","article-title":"Graph cut based automatic aorta segmentation with an adaptive smoothness constraint in 3d abdominal ct images","volume":"310","author":"Deng","year":"2018","journal-title":"Neurocomputing"},{"key":"bpexae23d2bib15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.media.2013.09.004","type":"journal-article","article-title":"Semi-automatic segmentation and detection of aorta dissection wall in mdct angiography","volume":"18","author":"Krissian","year":"2014","journal-title":"Med. Image Anal."},{"key":"bpexae23d2bib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2019.108713","type":"journal-article","article-title":"Fully automatic segmentation of type b aortic dissection from cta images enabled by deep learning","volume":"121","author":"Cao","year":"2019","journal-title":"Eur. J. Radiol."},{"key":"bpexae23d2bib17","doi-asserted-by":"publisher","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","type":"journal-article","article-title":"Transunet: Rethinking the u-net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"bpexae23d2bib18","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1109\/CVPR.2016.91","type":"conference-proceedings","article-title":"You only look once: Unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"bpexae23d2bib19","doi-asserted-by":"publisher","first-page":"42816","DOI":"10.1109\/ACCESS.2024.3378568","type":"journal-article","article-title":"Yolov1 to v8: Unveiling each variant-a comprehensive review of yolo","volume":"12","author":"Hussain","year":"2024","journal-title":"IEEE Access"},{"key":"bpexae23d2bib20","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","type":"journal-article","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"bpexae23d2bib21","first-page":"1","type":"book","article-title":"Faster r-cnn in healthcare and disease detection: A comprehensive review","author":"Tian","year":"2025"},{"key":"bpexae23d2bib22","doi-asserted-by":"publisher","first-page":"2733","DOI":"10.1007\/s10462-021-10061-9","type":"journal-article","article-title":"Deep reinforcement learning in computer vision: a comprehensive survey","volume":"55","author":"Le","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"bpexae23d2bib23","doi-asserted-by":"publisher","first-page":"102193","DOI":"10.1016\/j.media.2021.102193","type":"journal-article","article-title":"Deep reinforcement learning in medical imaging: a literature review","volume":"73","author":"Zhou","year":"2021","journal-title":"Med. Image Anal."},{"key":"bpexae23d2bib24","doi-asserted-by":"publisher","first-page":"2488","DOI":"10.1109\/ICCV.2015.286","type":"conference-proceedings","article-title":"Active object localization with deep reinforcement learning","author":"Caicedo","year":"2015"},{"key":"bpexae23d2bib25","doi-asserted-by":"publisher","first-page":"2561","DOI":"10.1609\/aaai.v34i03.5639","type":"journal-article","article-title":"Bar\u2014a reinforcement learning agent for bounding-box automated refinement","volume":"34","author":"Ayle","year":"2020","journal-title":"Proc. of the AAAI Conf. on Artificial Intelligence"},{"key":"bpexae23d2bib26","first-page":"544","type":"book","article-title":"Deep reinforcement learning for organ localization in ct","author":"Navarro","year":"2020"},{"key":"bpexae23d2bib27","doi-asserted-by":"publisher","first-page":"2375","DOI":"10.3390\/s21072375","type":"journal-article","article-title":"Edge-sensitive left ventricle segmentation using deep reinforcement learning","volume":"21","author":"Xiong","year":"2021","journal-title":"Sensors"},{"key":"bpexae23d2bib28","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1609\/aaai.v30i1.10295","type":"journal-article","article-title":"Deep reinforcement learning with double q-learning","volume":"30","author":"Van Hasselt","year":"2016","journal-title":"Proc. of the AAAI Conf. on Artificial Intelligence"},{"key":"bpexae23d2bib29","first-page":"1","type":"journal-article","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume":"32","author":"Eysenbach","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"bpexae23d2bib30","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","type":"journal-article","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"bpexae23d2bib31","first-page":"234241","type":"book","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"bpexae23d2bib32","doi-asserted-by":"publisher","first-page":"2390","DOI":"10.1109\/ICASSP43922.2022.9746172","type":"conference-proceedings","article-title":"Mixed transformer u-net for medical image segmentation","author":"Wang","year":"2022"},{"key":"bpexae23d2bib33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fphys.2021.732711","type":"journal-article","article-title":"Imagetbad: a 3d computed tomography angiography image dataset for automatic segmentation of type-b aortic dissection","volume":"12","author":"Yao","year":"2021","journal-title":"Front. Physiol."},{"key":"bpexae23d2bib34","first-page":"4727","type":"book","article-title":"A semi-automated image segmentation approach for computational fluid dynamics studies of aortic dissection","author":"Anderson","year":"2014"},{"key":"bpexae23d2bib35","first-page":"275","type":"book","article-title":"Segmentation of the aortic dissection from ct images based on spatial continuity prior model","author":"Xiaojie","year":"2016"},{"key":"bpexae23d2bib36","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1016\/j.procs.2017.05.431","type":"journal-article","article-title":"An adaptive implementation of \u03b5-greedy in reinforcement learning","volume":"109","author":"dos Santos Mignon","year":"2017","journal-title":"Proc. Comput. Sci."},{"key":"bpexae23d2bib37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICSES52305.2021.9633834","type":"conference-proceedings","article-title":"Evolution of yolo-v5 algorithm for object detection: automated detection of library books and performace validation of dataset","author":"Karthi","year":"2021"},{"key":"bpexae23d2bib38","doi-asserted-by":"publisher","first-page":"16560","DOI":"10.1109\/CVPR46437.2021.01629","type":"conference-proceedings","article-title":"clDice - a novel topology-preserving loss function for tubular structure segmentation","author":"Shit","year":"2021"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T16:38:55Z","timestamp":1764866335000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae23d2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12,3]]},"published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae23d2","relation":{},"ISSN":["2057-1976"],"issn-type":[{"type":"electronic","value":"2057-1976"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"Small-object-sensitive deep reinforcement learning for fully automatic 3D vessel segmentation in medical images","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-11-09","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-11-25","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-03","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}