{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T15:35:29Z","timestamp":1780414529346,"version":"3.54.1"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:p>Breast cancer is one of the most common and deadly diseases that threaten women\u2019s health worldwide, and early and accurate breast nodule segmentation is of great significance for the early detection, diagnosis and treatment of breast cancer. However, due to the limitation of medical annotated data, the training segmentation models for medical images is still challenging. The Segment Anything Model (SAM) is a foundational model that interactively segments target objects. Although significant achievements have been made in natural images, there are still challenges in the application in medical images. In this paper, the effect of SAM on breast nodule segmentation was studied from three aspects: initial weight, organ (breast) mask and prompt box, so as to explore the feasibility of breast nodule segmentation. Through a series of experiments on the data collected in this paper, it is found that the use of MedSAM initial weights and the use of single individual fixed prompt boxes can obtain better segmentation results, and can take into account practical application problems.<\/jats:p>","DOI":"10.3389\/fonc.2026.1756011","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:30:25Z","timestamp":1773120625000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Practical application of SAM for breast nodules segmentation"],"prefix":"10.3389","volume":"16","author":[{"given":"Wei","family":"Fan","sequence":"first","affiliation":[{"name":"Department of Radiology, Rocket Force Characteristic Medical Center of the Chinese People\u2019s Liberation Army","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ansheng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology, Rocket Force Characteristic Medical Center of the Chinese People\u2019s Liberation Army","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingze","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of MRI Diagnosis, The Second Affiliated Hospital of Harbin Medical University","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Interventional Therapy, National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengyuan","family":"Man","sequence":"additional","affiliation":[{"name":"Department of Radiology, Rocket Force Characteristic Medical Center of the Chinese People\u2019s Liberation Army","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"B1","article-title":"Global Cancer Statistics 2022: the trends projection analysis","volume":"10","author":"Chhikara","year":"2023","journal-title":"Chem Biol Lett"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"De Fauw","year":"2018","journal-title":"Nat Med"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2145-8","article-title":"Video-based AI for beat-to-beat assessment of cardiac function","volume":"580","author":"Ouyang","year":"2020","journal-title":"Nature"},{"key":"B4","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1002\/jmri.24229","article-title":"Fully automatic lesion segmentation in breast MRI using mean-shift and graph-cuts on a region adjacency graph","volume":"39","author":"McClymont","year":"2014","journal-title":"Magn Reson Imaging"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103113","article-title":"Semi-automated and interactive segmentation of contrast-enhancing masses on breast DCE-MRI using spatial fuzzy clustering","volume":"71","author":"Militello","year":"2022","journal-title":"BioMed Signal Process Control"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1118\/1.3238101","article-title":"Treatment response assessment of breast masses on dynamic contrast-enhanced magnetic resonance scans using fuzzy -means clustering and level set segmentation","volume":"36","author":"Shi","year":"2009","journal-title":"Med Phys"},{"key":"B7","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1186\/s13634-017-0476-x","article-title":"Computer-aided detection of breast lesions in DCE-MRI using region growing based on fuzzy C-means clustering and vesselness filter","volume":"2017","author":"Shokouhi","year":"2017","journal-title":"EURASIP J Adv Signal Process"},{"key":"B8","first-page":"67","article-title":"Segmentation of breast MRI using effective Fuzzy C-Means method based on Support Vector Machine","author":"Sathya","year":"2012"},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1117\/12.812971","article-title":"Assessment of texture analysis on DCE-MRI data for the differentiation of breast tumor lesions","author":"Loose","year":"2009"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.20541","article-title":"Breast lesion analysis of shape technique: Semiautomated vs. manual morphological description","volume":"23","author":"Liney","year":"2006","journal-title":"Magn Reson Imaging"},{"key":"B11","doi-asserted-by":"publisher","first-page":"3032","DOI":"10.11591\/ijece.v11i4.pp3032-3039","article-title":"Lane marking detection using simple encode decode deep learning technique: SegNet","volume":"11","author":"Al Mamun","year":"2021","journal-title":"IJECE"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528129","article-title":"Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks","volume":"35","author":"Dou","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B14","unstructured":"Fully convolutional networks for semantic segmentation\n          \n          \n            \n              Long\n              J\n            \n            \n              Shelhamer\n              E\n            \n            \n              Darrell\n              T\n            \n          \n          Boston, MA, USA.\n          Proceedings of the IEEE CVPR 2015\n          \n          2015"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"B16","unstructured":"Attention is all you need\n          \n          \n            \n              Vaswani\n              A\n            \n            \n              Shazeer\n              N\n            \n            \n              Parmar\n              N\n            \n            \n              Uszkoreit\n              J\n            \n            \n              Jones\n              L\n            \n            \n              Gomez\n              AN\n            \n          \n          \n          2017"},{"key":"B17","unstructured":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT\n          \n          \n            \n              Zhou\n              C\n            \n            \n              Li\n              Q\n            \n            \n              Li\n              C\n            \n            \n              Yu\n              J\n            \n            \n              Liu\n              Y\n            \n            \n              Wang\n              G\n            \n          \n          \n          2023"},{"key":"B18","unstructured":"Knowledge-aware Zero-Shot Learning: Survey and Perspectiv\n          \n          \n            \n              Chen\n              J\n            \n            \n              Geng\n              Y\n            \n            \n              Chen\n              Z\n            \n            \n              Horrocks\n              L\n            \n            \n              Pan\n              JZ\n            \n            \n              Chen\n              H\n            \n          \n          \n          2021"},{"key":"B19","unstructured":"GPT-4 Technical Report\n          \n          \n            \n              Achiam\n              J\n            \n            \n              Adler\n              S\n            \n            \n              Agarwal\n              S\n            \n            \n              Ahmad\n              L\n            \n            \n              Akkaya\n              I\n            \n          \n          \n          2023"},{"key":"B20","unstructured":"Segment Anything\n          \n          \n            \n              Kirillov\n              A\n            \n            \n              Mintun\n              E\n            \n            \n              Ravi\n              N\n            \n            \n              Mao\n              H\n            \n            \n              Rolland\n              C\n            \n            \n              Gustafson\n              L\n            \n          \n          \n          2023"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e0309421","DOI":"10.1371\/journal.pone.0309421","article-title":"Breast tumor segmentation using neural cellular automata and shape guided segmentation in mammography images","volume":"19","author":"Ali","year":"2024","journal-title":"PloS One"},{"key":"B22","first-page":"1","article-title":"Leveraging CNN-transformer hybrid architecture for accurate breast tumor segmentation in mammograms","author":"Ali","year":"2025"},{"key":"B23","unstructured":"Computer-Vision Benchmark Segment-Anything Model (SAM) in Medical Images: Accuracy in 12 Datasets\n          \n          \n            \n              He\n              S\n            \n            \n              Bao\n              R\n            \n            \n              Li\n              J\n            \n            \n              Stout\n              J\n            \n            \n              Bjornerud\n              A\n            \n            \n              Grant\n              PE\n            \n          \n          \n          2023"},{"key":"B24","doi-asserted-by":"publisher","first-page":"131713","DOI":"10.1016\/j.neucom.2025.131713","article-title":"Enhanced 3D tumor synthesis and segmentation framework using multiscale diffusion and hybrid SAM-Swin models across diverse anatomical datasets","volume":"659","author":"Yao","year":"2026","journal-title":"Neurocomputing"},{"key":"B25","doi-asserted-by":"publisher","first-page":"102473","DOI":"10.1016\/j.compmedimag.2024.102473","article-title":"A review of the Segment Anything Model (SAM) for medical image analysis: Accomplishments and perspectives","volume":"119","author":"Ali","year":"2025","journal-title":"Computerized Med Imaging Graphics"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547","article-title":"Medical SAM adapter: Adapting segment anything model for medical image segmentation","volume":"102","author":"Wu","year":"2025","journal-title":"Med Image Anal"},{"key":"B27","unstructured":"Medical SAM 2: Segment medical images as video via Segment Anything Model 2\n          \n          \n            \n              Jia\n              Z\n            \n            \n              Hamdi\n              A\n            \n            \n              Yun\n              Q\n            \n            \n              Yue\n              J\n            \n            \n              Jun\n              W\n            \n          \n          \n          2024"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108238","article-title":"Segment anything model for medical image segmentation: Current applications and future directions","volume":"171","author":"Zhang","year":"2024","journal-title":"Comput Biol Med"},{"key":"B29","unstructured":"Segment Anything in Medical Images\n          \n          \n            \n              Ma\n              J\n            \n            \n              He\n              Y\n            \n            \n              Li\n              F\n            \n            \n              Han\n              L\n            \n            \n              You\n              C\n            \n            \n              Wang\n              B\n            \n          \n          \n          2023"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17751","article-title":"Dual branch segment anything model-transformer fusion network for accurate breast ultrasound image segmentation","volume":"52","author":"Li","year":"2025","journal-title":"Med Phys"},{"key":"B31","unstructured":"Ultrasound SAM Adapter: Adapting SAM for Breast Lesion Segmentation in Ultrasound Images\n          \n          \n            \n              Zheng\n              T\n            \n            \n              Le\n              G\n            \n            \n              Xi\n              W\n            \n            \n              Bo\n              J\n            \n          \n          \n          2024"},{"key":"B32","unstructured":"BreastSAM: A Study of Segment Anything Model for Breast Tumor Detection in Ultrasound Images\n          \n          \n            \n              Ming\n              H\n            \n            \n              Yu\n              L\n            \n            \n              Xiao\n              Y\n            \n          \n          \n          2023"},{"key":"B33","unstructured":"SAM-UNet: Enhancing Zero-Shot Segmentation of SAM for Universal Medical Images\n          \n          \n            \n              Si\n              Y\n            \n            \n              Hai\n              B\n            \n            \n              Jian\n              S\n            \n          \n          \n          2024"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918","article-title":"Segment anything model for medical image analysis: an experimental study","volume":"89","author":"Mazurowski","year":"2023","journal-title":"Med Image Anal"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1756011\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:30:29Z","timestamp":1773120629000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1756011\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":34,"alternative-id":["10.3389\/fonc.2026.1756011"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1756011","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"article-number":"1756011"}}