{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T03:13:05Z","timestamp":1775272385502,"version":"3.50.1"},"reference-count":49,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R61AT012282"],"award-info":[{"award-number":["R61AT012282"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL174570"],"award-info":[{"award-number":["R01HL174570"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Chronic low back pain (cLBP) profoundly impacts quality of life, yet its underlying mechanisms remain poorly understood. Three\u2010dimensional (3D) ultrasound imaging offers valuable insights into cLBP but poses challenges of manual annotation due to large data volume and poor image quality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>We aim to develop and validate a novel approach called Cross\u2010Scan Fusion Network (CSFN) for segmenting anatomical tissue layers in 3D ultrasound images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>\n                      We analyzed 3D B\u2010mode ultrasound volumes of the lumbar region, with six tissue layers annotated: dermis, superficial fat, superficial fascial membrane, deep fat, deep fascial membrane, and muscle. The dataset included 69 labeled scans from 29 subjects and 30 unlabeled scans from 10 subjects. Labeled scans were split into training (\n                      <jats:italic>n =<\/jats:italic>\n                      19), validation (\n                      <jats:italic>n =<\/jats:italic>\n                      10), and independent test (\n                      <jats:italic>n =<\/jats:italic>\n                      40) sets. For annotation efficiency analysis, 5, 10, 15, and 19 scans in the training set were separately treated as annotated, with the remainder considered unannotated. CSFN leverages a VoxelMorph\u2010style elastic registration network trained with a novel Projected Hausdorff Distance Loss (PHDL) to accurately register anatomical tissue layers across 3D scans. This supports both sample\u2010efficient learning (CSFN\u2010SEL) and semi\u2010supervised learning (CSFN\u2010SSL). In the CSFN\u2010SEL, controlled wrap ratios are applied to pairs of labeled scans to synthesize realistic image\u2010mask pairs, while in the CSFN\u2010SSL, labeled scans are registered onto unlabeled scans to generate high\u2010quality synthesized scans for augmentation. Both real and synthetic data are then combined to train an nnU\u2010Net segmentor, enabling robust segmentation with minimal manual annotations. CSFN was compared to fully\u2010supervised nnU\u2010Net with and without augmentation, and SimCLR (nnU\u2010Net backbone). Model segmentation performance was evaluated using the Dice coefficient, while registration quality was assessed using Dice and Average Symmetric Surface Distance (ASSD). Results were reported as mean\u00a0\u00b1\u00a0standard deviation(SD) and compared using paired two\u2010tailed t\u2010tests on class\u2010wise subject averages. Significance was set at 0.05 and adjusted for multiple comparisons.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      CSFN\u2010SEL consistently outperformed the fully supervised nnU\u2010Net baseline across varying numbers of labeled training samples, improving the mean Dice coefficient from 69.34% to 74.62% (+5.28%,\n                      <jats:italic>p<\/jats:italic>\n                      \u2010value\u00a0&lt;\u00a00.05\/3). CSFN\u2010SSL further improved performance, achieving 79.33%\u00a0(\u00b11.96%) and 81.14%\u00a0(\u00b11.43%) with 5 and 19 training samples, respectively. With only five labeled scans, CSFN\u2010SSL delivered a 9.51% performance gain (effect size\n                      <jats:italic>d<\/jats:italic>\n                      \u00a0=\u00a00.671,\n                      <jats:italic>p<\/jats:italic>\n                      \u2010value\u00a0&lt;\u00a00.05\/3) with minimal annotation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>CSFN improves segmentation accuracy and robustness even with very few labeled scans, providing an effective and practical solution for advancing cLBP imaging and analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical Relevance Satement<\/jats:title>\n                    <jats:p>CSFN enables accurate, automated segmentation of anatomical tissue layers in 3D ultrasound scans with minimal manual annotations, potentially accelerating the clinical evaluation and management of cLBP.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70304","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T13:46:14Z","timestamp":1769780774000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross\u2010scan fusion network: A registration\u2010based framework for annotation\u2010efficient 3D ultrasound segmentation in low back pain assessment"],"prefix":"10.1002","volume":"53","author":[{"given":"Pengyu","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science University of Pittsburgh  Pittsburgh Pennsylvania USA"},{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixue","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"},{"name":"Department of Bioengineering University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyu","family":"Sheng","sequence":"additional","affiliation":[{"name":"Department of Medicine University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maryam","family":"Satapour","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John M.","family":"Cormack","sequence":"additional","affiliation":[{"name":"Department of Medicine University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allison C.","family":"Bean","sequence":"additional","affiliation":[{"name":"Department of Physical Medicine and Rehabilitation University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan","family":"Nussbaum","sequence":"additional","affiliation":[{"name":"Department of Physical Medicine and Rehabilitation University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maya","family":"Maurer","sequence":"additional","affiliation":[{"name":"Anesthesiology &amp; Perioperative School of Medicine University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily","family":"Landis\u2010Walkenhorst","sequence":"additional","affiliation":[{"name":"Anesthesiology &amp; Perioperative School of Medicine University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"},{"name":"Department of Medicine University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajay D.","family":"Wasan","sequence":"additional","affiliation":[{"name":"Anesthesiology &amp; Perioperative School of Medicine University of Pittsburgh  Pittsburgh Pennsylvania USA"},{"name":"Psychiatry School of Medicine University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiantao","family":"Pu","sequence":"additional","affiliation":[{"name":"Department of Radiology University of Pittsburgh  Pittsburgh Pennsylvania USA"},{"name":"Department of Bioengineering University of Pittsburgh  Pittsburgh Pennsylvania USA"},{"name":"Department of Ophthalmology University of Pittsburgh  Pittsburgh Pennsylvania USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.21037\/jhmhp\u201020\u201017"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/21642850.2021.2022487"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rehab.2021.101504"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586\u2010023\u201007602\u2010x"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/1741\u20107015\u20105\u20102"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s005860000190"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12891\u2010024\u201007289\u20101"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2020.02.004"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tjog.2022.06.002"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.7863\/jum.2002.21.10.1063"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201057733\u20104"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2024.1476396"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15091180"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1113\/JP281273"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010021\u201021179\u20103"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1093065"},{"key":"e_1_2_9_18_1","first-page":"623","article-title":"Imaging biomarker development for lower back pain using machine learning: how image analysis can help back pain","volume":"1","author":"Gaonkar B","year":"2022","journal-title":"Biomed Eng Technol"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1097\/j.pain.0000000000002143"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/pm\/pnac142"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3461321"},{"key":"e_1_2_9_22_1","article-title":"SAM & SAM 2 in 3D slicer: segment with SAM extension for annotating medical images","author":"Yildiz Z","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3157828"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12194\u2010021\u201000630\u20106"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994\u2010019\u201005855\u20106"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123052"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"WangD ZhangY ZhangK WangL Focalmix: semi\u2010supervised learning for 3d medical image detection. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)2020:3951\u20103960.","DOI":"10.1109\/CVPR42600.2020.00401"},{"key":"e_1_2_9_28_1","article-title":"Learning with limited annotations: a survey on deep semi\u2010supervised learning for medical image segmentation","author":"Jiao R","year":"2023","journal-title":"Comput Biol Med"},{"key":"e_1_2_9_29_1","unstructured":"ChenT KornblithS NorouziM HintonG A simple framework for contrastive learning of visual representations.In Proceedings of the 37th International Conference on Machine Learning (PMLR);2020:1597\u20101607."},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010022\u201001723\u20104"},{"key":"e_1_2_9_31_1","article-title":"A review of pseudo\u2010labeling for computer vision","author":"Kage P","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"e_1_2_9_32_1","article-title":"Semi\u2010supervised learning with generative adversarial networks","author":"Odena A","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185773"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010021\u201026216\u20109"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"RebuffiS\u2010A EhrhardtS HanK VedaldiA ZissermanA Semi\u2010supervised learning with scarce annotations.In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)2020:762\u2010763.","DOI":"10.1109\/CVPRW50498.2020.00389"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462\u2010023\u201010624\u2010y"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001008\u2010z"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2897538"},{"key":"e_1_2_9_39_1","first-page":"234","volume-title":"U\u2010net: Convolutional networks for biomedical image segmentation","author":"Ronneberger O","year":"2015"},{"issue":"9","key":"e_1_2_9_40_1","article-title":"Multiple comparisons: a tutorial. Part 2: understanding multiple comparisons","volume":"128","author":"Lawson MT","year":"2021","journal-title":"BJOG"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/pits.20234"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.2519\/jospt.2019.8827"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586\u2010009\u20101171\u2010x"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9030069"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3273609"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2014.12.005"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101842"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102513"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2913184"}],"updated-by":[{"DOI":"10.1002\/mp.70413","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000}}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70304","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70304","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T13:34:02Z","timestamp":1773063242000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70304"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1002\/mp.70304"],"URL":"https:\/\/doi.org\/10.1002\/mp.70304","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]},"assertion":[{"value":"2025-06-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70304"}}