{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:10:47Z","timestamp":1773879047758,"version":"3.50.1"},"reference-count":29,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100008750","name":"Shanghai Municipal Hospital Development Center","doi-asserted-by":"crossref","award":["SHDC2020CR2071B"],"award-info":[{"award-number":["SHDC2020CR2071B"]}],"id":[{"id":"10.13039\/501100008750","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Background.<\/jats:italic>\n                    Varicocele is a common cause of male infertility, with ultrasound (US) serving as the primary diagnostic tool. Current practice relies on manual, subjective measurements of the spermatic vein, which are time-consuming and lack reproducibility. Developing automated tools is hindered by scarce annotated data and intrinsic US challenges like low contrast and high noise.\n                    <jats:italic>Obejectives.<\/jats:italic>\n                    This study aimed to: (1) develop and validate an efficient semi-automated annotation workflow; (2) establish the first performance benchmark for automated spermatic vein segmentation using deep learning; (3) critically evaluate the efficacy of state-of-the-art and customised segmentation models for this specific task.\n                    <jats:italic>Methods.<\/jats:italic>\n                    We proposed a semi-automated pipeline using the Segment Anything Model (SAM) with clinician refinement. Using the resulting dataset, we conducted a comprehensive benchmark, evaluating a baseline U-Net, advanced models (U-Net++, Attention U-Net, and RPA-UNet), and a proposed U-Net with deep supervision (UNet-DS). All models were assessed via leave-one-patient-out cross-validation and statistical tests.\n                    <jats:italic>Results.<\/jats:italic>\n                    The \u2018SAM+clinician\u2019 workflow showed excellent agreement with expert annotation (Dice Similarity Coefficient(DSC) = 92.66%; Kappa = 91.92%). In segmentation, the baseline U-Net achieved a mean DSC of 61.33%. Only Attention U-Net showed a statistically significant improvement (\n                    <jats:italic>p<\/jats:italic>\n                    = 0.0391). UNet-DS attained the mean DSC (64.65%) but this was not statistically significant (\n                    <jats:italic>p<\/jats:italic>\n                    = 0.0781). All models plateaued in a narrow range (DSC: 61%\u201365%), far below performance in mature US segmentation domains.\n                    <jats:italic>Conclusion.<\/jats:italic>\n                    This work validates an efficient semi-automated annotation solution and establishes the first performance benchmark for this task. Results reveal a distinct performance ceiling, indicating the primary barrier is the inherent data limitations, not model architecture. Future breakthroughs require a shift towards bespoke, physics-informed algorithms rather than applying generic deep learning models.\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ae4eed","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T22:48:02Z","timestamp":1773096482000},"page":"025041","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploration and performance analysis of deep learning applications in spermatic vein ultrasound segmentation"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1003-6174","authenticated-orcid":true,"given":"Yunhao","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8231-1392","authenticated-orcid":true,"given":"Penglin","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7740-3519","authenticated-orcid":false,"given":"Rongguo","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiyun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"bpexae4eedbib1","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1093\/humupd\/dmx021","type":"journal-article","article-title":"The diagnosis of male infertility: an analysis of the evidence to support the development of global WHO guidance-challenges and future research opportunities","volume":"23","author":"Barratt","year":"2017","journal-title":"Hum. Reprod. Update"},{"key":"bpexae4eedbib2","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1097\/JU.0000000000001521","type":"journal-article","article-title":"Diagnosis and treatment of infertility in men: AUA\/ASRM guideline part I","volume":"205","author":"Schlegel","year":"2021","journal-title":"J. Urol."},{"key":"bpexae4eedbib3","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s40477-020-00509-z","type":"journal-article","article-title":"Ultrasound evaluation of varicoceles: systematic literature review and rationale of the ESUR-SPIWG Guidelines and Recommendations","volume":"23","author":"Bertolotto","year":"2020","journal-title":"J. Ultrasound"},{"key":"bpexae4eedbib4","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s00330-019-06280-y","type":"journal-article","article-title":"Ultrasound evaluation of varicoceles: guidelines and recommendations of the European Society of Urogenital Radiology Scrotal and Penile Imaging Working Group (ESUR-SPIWG) for detection, classification, and grading","volume":"30","author":"Freeman","year":"2020","journal-title":"Eur. Radiol."},{"key":"bpexae4eedbib5","doi-asserted-by":"publisher","first-page":"182","DOI":"10.4103\/1008-682X.169991","type":"journal-article","article-title":"Diagnosis of clinical and subclinical varicocele: how has it evolved","volume":"18","author":"Belay","year":"2016","journal-title":"Asian J. Androl"},{"key":"bpexae4eedbib6","first-page":"940","type":"journal-article","article-title":"Correlation of contrast-enhanced ultrasound with spermatogenic function in patients with varicocele","volume":"39","author":"Zou","year":"2023","journal-title":"Chin J. Ultrasound Med."},{"key":"bpexae4eedbib7","doi-asserted-by":"publisher","first-page":"610","DOI":"10.13929\/j.1003-3289.201809071","type":"journal-article","article-title":"Progresses of ultrasound in diagnosis andclassification of varicocele","volume":"35","author":"Liang","year":"2019","journal-title":"Chin. J. Med. Imaging Technol."},{"key":"bpexae4eedbib8","doi-asserted-by":"publisher","first-page":"611","DOI":"10.4103\/aja.aja_22_21","type":"journal-article","article-title":"Clinical outcome of pediatric and young adult subclinical varicoceles: a single-institution experience","volume":"23","author":"Cho","year":"2021","journal-title":"Asian J. Androl."},{"key":"bpexae4eedbib9","doi-asserted-by":"publisher","first-page":"164","DOI":"10.5534\/wjmh.220048","type":"journal-article","article-title":"Consensus and diversity in the management of varicocele for male infertility: results of a global practice survey and comparison with guidelines and recommendations","volume":"41","author":"Shah","year":"2023","journal-title":"World J. Mens Health"},{"key":"bpexae4eedbib10","first-page":"4","type":"other","article-title":"Tracking of the internal jugular vein in ultrasound images using optical flow","author":"Karami","year":"2017"},{"key":"bpexae4eedbib11","doi-asserted-by":"publisher","first-page":"359","DOI":"10.20471\/acc.2022.61.02.24","type":"journal-article","article-title":"Scrotal thermography in the evaluation of surgical outcome after varicocele repair: a case report","volume":"61","author":"Karlovic","year":"2022","journal-title":"Acta Clin. Croat."},{"key":"bpexae4eedbib12","doi-asserted-by":"publisher","first-page":"3234","DOI":"10.1109\/TBME.2020.2980540","type":"journal-article","article-title":"Automatic spine ultrasound segmentation for scoliosis visualization and measurement","volume":"67","author":"Ungi","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae4eedbib13","doi-asserted-by":"publisher","DOI":"10.1016\/j.bone.2021.116300","type":"journal-article","article-title":"An automatic measurement system of distal femur morphological parameters using 3D slicer software","volume":"156","author":"Chen","year":"2022","journal-title":"Bone"},{"key":"bpexae4eedbib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102810","type":"journal-article","article-title":"RecON: Online learning for sensorless freehand 3D ultrasound reconstruction","volume":"87","author":"Luo","year":"2023","journal-title":"Med. Image Anal."},{"key":"bpexae4eedbib15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129660","type":"journal-article","article-title":"CoAtUNet: a symmetric encoder-decoder with hybrid transformers for semantic segmentation of breast ultrasound images","volume":"629","author":"Zaidkilani","year":"2025","journal-title":"Neurocomputing"},{"key":"bpexae4eedbib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105194","type":"journal-article","article-title":"FRBNet: feedback refinement boundary network for semantic segmentation in breast ultrasound images","volume":"86","author":"Li","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae4eedbib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106453","type":"journal-article","article-title":"RPA-UNet: a robust approach for arteriovenous fistula ultrasound image segmentation","volume":"95","author":"Luo","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae4eedbib18","doi-asserted-by":"publisher","first-page":"125393","DOI":"10.1109\/ACCESS.2021.3111021","type":"journal-article","article-title":"Automatic segmentation and detection system for varicocele in supine position","volume":"9","author":"AlZoubi","year":"2021","journal-title":"IEEE ACCESS"},{"key":"bpexae4eedbib19","doi-asserted-by":"publisher","first-page":"797","DOI":"10.32604\/cmc.2022.024913","type":"journal-article","article-title":"Automatic segmentation and detection system for varicocele using ultrasound images","volume":"72","author":"Abdalla","year":"2022","journal-title":"CMC"},{"key":"bpexae4eedbib20","doi-asserted-by":"publisher","first-page":"020508","DOI":"10.2352\/J.ImagingSci.Technol.2020.64.2.020508","type":"journal-article","article-title":"Medical image segmentation based on U-Net: a review","volume":"64","author":"Du","year":"2020","journal-title":"J. Imaging Sci. Technol."},{"key":"bpexae4eedbib21","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","type":"journal-article","article-title":"MultiResUNet : rethinking the U-Net architecture for multimodal biomedical image segmentation","volume":"121","author":"Ibtehaz","year":"2020","journal-title":"Neural Netw."},{"key":"bpexae4eedbib22","doi-asserted-by":"publisher","first-page":"82031","DOI":"10.1109\/ACCESS.2021.3086020","type":"journal-article","article-title":"U-Net and its variants for medical image segmentation: a review of theory and applications","volume":"9","author":"Siddique","year":"2021","journal-title":"IEEE Access"},{"key":"bpexae4eedbib23","doi-asserted-by":"publisher","first-page":"5845","DOI":"10.1007\/s10462-022-10152-1","type":"journal-article","article-title":"Modality specific U-Net variants for biomedical image segmentation: a survey","volume":"55","author":"Punn","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"bpexae4eedbib24","doi-asserted-by":"publisher","first-page":"7406","DOI":"10.1007\/s11263-025-02539-8","type":"journal-article","article-title":"On efficient variants of segment anything model: a survey","volume":"133","author":"Sun","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"bpexae4eedbib25","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","type":"journal-article","article-title":"UNet plus plus : redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","author":"Zhou","year":"2020","journal-title":"IEEE T. Med. Imaging"},{"key":"bpexae4eedbib26","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.media.2019.01.012","type":"journal-article","article-title":"Attention gated networks: learning to leverage salient regions in medical images","volume":"53","author":"Schlemper","year":"2019","journal-title":"Med. Image Anal."},{"key":"bpexae4eedbib27","first-page":"562","type":"other","article-title":"Deeply-supervised nets","author":"Lee","year":"2015"},{"key":"bpexae4eedbib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.wfumbo.2024.100068","type":"journal-article","article-title":"Breast cancer ultrasound image segmentation using improved 3DUnet++","volume":"3","author":"Hesaraki","year":"2025","journal-title":"WFUMB Ultrasound Open"},{"key":"bpexae4eedbib29","doi-asserted-by":"publisher","first-page":"668","DOI":"10.16476\/j.pibb.2022.0101","type":"journal-article","article-title":"Automatic classification of liver cancer in B-ultrasound and contrast-enhanced ultrasound based on convolution neural network","volume":"50","author":"Li","year":"2023","journal-title":"Prog. Biochem. Biophys."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T17:36:53Z","timestamp":1773855413000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae4eed"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":29,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,3,18]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae4eed","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"assertion":[{"value":"Exploration and performance analysis of deep learning applications in spermatic vein ultrasound segmentation","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 2026 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":"2025-11-10","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-03-09","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-03-18","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}