{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:07:23Z","timestamp":1782846443425,"version":"3.54.5"},"reference-count":37,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Given the highly heterogeneous biology of breast cancer, a more effective noninvasive diagnostic tool that unravels microscopic histopathology patterns is urgently needed.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to identify cancerous regions in ultrasound images of breast cancer via convolutional neural network based on registered grayscale ultrasound images and readily accessible biopsy whole slide images (WSIs).<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This single-center study prospectively included participants undergoing ultrasound-guided core needle biopsy procedures for Breast Imaging Reporting and Data System category 4 or 5 breast lesions for whom breast cancer was pathologically confirmed from July 2022 to February 2023 consecutively. The basic information, ultrasound image data, biopsy tissue specimens, and corresponding WSIs were collected. After core needle biopsy procedures, the stained breast tissue specimens were sliced and coregistered with an ultrasound image of a needle tract. Convolutional neural network models for identifying breast cancer cells in ultrasound images were developed using FCN-101 and DeepLabV3 networks. The image-level predictive performance was evaluated and compared quantitatively by pixel accuracy, Dice similarity coefficient, and recall. Pixel-level classification was illustrated through confusion matrices. The cancerous region in the testing dataset was further visualized in ultrasound images. Potential clinical applications were qualitatively assessed by comparing the automatic segmentation results and the actual pathological tissue distributions.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 105 participants with 386 ultrasound images of breast cancer were included, with 270 (70%), 78 (20.2%), and 38 (9.8%) images in the training, validation, and test datasets, respectively. Both models performed well in predicting the cancerous regions in the biopsy area, whereas the FCN-101 model was superior to the DeepLabV3 model in terms of pixel accuracy (86.91% vs 69.55%;\n P<\/jats:italic>\n =.002) and Dice similarity coefficient (77.47% vs 69.90%;\n P<\/jats:italic>\n <.001). The two models yielded recall values of 54.64% and 58.46%, with no significant difference between them (\n P<\/jats:italic>\n =.80). Furthermore, the FCN-101 model had an advantage in predicting cancerous regions, while the DeepLabV3 model achieved more accurate predictive pixels in normal tissue (both\n P<\/jats:italic>\n <.05). Visualization of cancerous regions on grayscale ultrasound images demonstrated high consistency with those identified on WSIs.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The technique for spatial registration of breast WSIs and ultrasound images of a needle tract was established. Breast cancer regions were accurately identified and localized on a pixel level in high-frequency ultrasound images via an advanced convolutional neural network with histopathologic WSI as the reference standard.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/81181","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:11:47Z","timestamp":1769202707000},"page":"e81181-e81181","source":"Crossref","is-referenced-by-count":0,"title":["Identification and Localization of Breast Tumor Components via a Convolutional Neural Network Based on High-Frequency Ultrasound Combined With Histopathologic Registration: Prospective Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4225-5143","authenticated-orcid":false,"given":"Jia-Qian","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1164-4413","authenticated-orcid":false,"given":"Wen-Wen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7789-2131","authenticated-orcid":false,"given":"Zhi-Fei","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3186-3170","authenticated-orcid":false,"given":"Fei","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9754-2273","authenticated-orcid":false,"given":"Tong-Yi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3320-714X","authenticated-orcid":false,"given":"Tian-Tian","family":"Zhen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2738-8906","authenticated-orcid":false,"given":"Hui-Juan","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9761-9525","authenticated-orcid":false,"given":"Xiao-Yan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9706-4622","authenticated-orcid":false,"given":"Ze","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2151-2980","authenticated-orcid":false,"given":"Ming","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"issue":"7","key":"R1","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1038\/nrclinonc.2015.73","article-title":"Clinical management of breast cancer heterogeneity","volume":"12","author":"Zardavas","journal-title":"Nat Rev Clin Oncol"},{"issue":"2","key":"R2","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1038\/s41416-021-01328-7","article-title":"Breast cancer as an example of tumour heterogeneity and tumour cell plasticity during malignant progression","volume":"125","author":"L\u00fc\u00f6nd","journal-title":"Br J Cancer"},{"issue":"4","key":"R3","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djv367","article-title":"Ultrasound as the primary screening test for breast cancer: analysis from ACRIN 6666","volume":"108","author":"Berg","journal-title":"J Natl Cancer Inst"},{"issue":"4","key":"R4","doi-asserted-by":"publisher","DOI":"10.3390\/cancers12040848","article-title":"Morphologic and genomic heterogeneity in the evolution and progression of breast cancer","volume":"12","author":"Kutasovic","journal-title":"Cancers (Basel)"},{"issue":"3","key":"R5","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1007\/s10549-018-4801-3","article-title":"Response rates and pathologic complete response by breast cancer molecular subtype following neoadjuvant chemotherapy","volume":"170","author":"Haque","journal-title":"Breast Cancer Res Treat"},{"issue":"4","key":"R6","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1097\/SLA.0000000000002953","article-title":"The clinical significance of breast-only and node-only pathologic complete response (pCR) after neoadjuvant chemotherapy (NACT): a review of 20,000 breast cancer patients in the National Cancer Data Base (NCDB)","volume":"268","author":"Fayanju","journal-title":"Ann Surg"},{"issue":"14","key":"R7","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13143521","article-title":"Assessment and prediction of response to neoadjuvant chemotherapy in breast cancer: a comparison of imaging modalities and future perspectives","volume":"13","author":"Romeo","journal-title":"Cancers (Basel)"},{"issue":"2","key":"R8","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1148\/radiol.2017170180","article-title":"Imaging neoadjuvant therapy response in breast cancer","volume":"285","author":"Fowler","journal-title":"Radiology"},{"issue":"12","key":"R9","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1016\/S1470-2045(22)00613-1","article-title":"Eliminating breast surgery for invasive breast cancer in exceptional responders to neoadjuvant systemic therapy: a multicentre, single-arm, phase 2 trial","volume":"23","author":"Kuerer","journal-title":"Lancet Oncol"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.222830","article-title":"MRI-based quantification of intratumoral heterogeneity for predicting treatment response to neoadjuvant chemotherapy in breast cancer","volume":"308","author":"Shi","journal-title":"Radiology"},{"issue":"7","key":"R11","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1016\/j.ejso.2016.03.019","article-title":"Serial MRI scans help in assessing early response to neoadjuvant chemotherapy and tailoring breast cancer treatment","volume":"42","author":"Fatayer","journal-title":"Eur J Surg Oncol"},{"issue":"2","key":"R12","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1038\/s43018-020-0026-6","article-title":"Imaging mass cytometry and multiplatform genomics define the phenogenomic landscape of breast cancer","volume":"1","author":"Ali","journal-title":"Nat Cancer"},{"issue":"7","key":"R13","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.7700","article-title":"Artificial intelligence algorithms to assess hormonal status from tissue microarrays in patients with breast cancer","volume":"2","author":"Shamai","journal-title":"JAMA Netw Open"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.858453","article-title":"Breast cancer molecular subtype prediction on pathological images with discriminative patch selection and multi-instance learning","volume":"12","author":"Liu","journal-title":"Front Oncol"},{"issue":"5","key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.esmoop.2024.102974","article-title":"Pan-Asian adapted ESMO Clinical Practice Guidelines for the diagnosis, treatment and follow-up of patients with early breast cancer","volume":"9","author":"Park","journal-title":"ESMO Open"},{"issue":"12","key":"R16","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2020.4103","article-title":"Accuracy of post-neoadjuvant chemotherapy image-guided breast biopsy to predict residual cancer","volume":"155","author":"Tasoulis","journal-title":"JAMA Surg"},{"issue":"Suppl 1","key":"R17","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1038\/s41379-020-00706-5","article-title":"Papillary neoplasms of the breast including upgrade rates and management of intraductal papilloma without atypia diagnosed at core needle biopsy","volume":"34","author":"Brogi","journal-title":"Mod Pathol"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2023.104706","article-title":"Deep learning radiopathomics based on preoperative US images and biopsy whole slide images can distinguish between luminal and non-luminal tumors in early-stage breast cancers","volume":"94","author":"Huang","journal-title":"EBioMedicine"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102288","article-title":"Selective identification and localization of indolent and aggressive prostate cancers via CorrSigNIA: an MRI-pathology correlation and deep learning framework","volume":"75","author":"Bhattacharya","journal-title":"Med Image Anal"},{"key":"R20","unstructured":"Morris E Comstock C Lee C et al. ACR BI-RADS magnetic resonance imaging ACR BI-RADS atlas, breast imaging reporting and data system. Vol 5. 2013. URL: https:\/\/www.acr.org\/Clinical-Resources\/Clinical-Tools-and-Reference\/Reporting-and-Data-Systems\/BI-RADS [Accessed 08-01-2026]"},{"key":"R21","unstructured":"QuPath. URL: https:\/\/qupath.github.io\/ [Accessed 21-01-2026]"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2018.11.028","article-title":"Autonomous concrete crack detection using deep fully convolutional neural network","volume":"99","author":"Dung","journal-title":"Automation in Construction"},{"key":"R23","doi-asserted-by":"crossref","unstructured":"Chen LC Papandreou G Schroff F et al. Rethinking atrous convolution for semantic image segmentation. arXiv. Preprint posted online on Jun 17, 2017. [doi: 10.1007\/978-3-030-01234-2_49]","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"R24","unstructured":"Chai ZF . Breast cancer component segmentation. GitHub repository. 2024. URL: https:\/\/github.com\/ChaiZhifeiF\/Breast-Cancer-Component-Segmentation [Accessed 23-07-2024]"},{"issue":"2","key":"R25","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.ejrad.2007.04.008","article-title":"Observer variability of Breast Imaging Reporting and Data System (BI-RADS) for breast ultrasound","volume":"65","author":"Lee","journal-title":"Eur J Radiol"},{"issue":"3","key":"R26","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1148\/radiol.2523080670","article-title":"Breast imaging reporting and data system lexicon for US: interobserver agreement for assessment of breast masses","volume":"252","author":"Abdullah","journal-title":"Radiology"},{"issue":"3","key":"R27","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1148\/radiol.12102294","article-title":"Prostate: registration of digital histopathologic images to in vivo MR images acquired by using endorectal receive coil","volume":"263","author":"Ward","journal-title":"Radiology"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1148\/radiol.2017160906","article-title":"Prostate cancer: a correlative study of multiparametric MR imaging and digital histopathology","volume":"285","author":"Kwak","journal-title":"Radiology"},{"issue":"2","key":"R29","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1007\/s00330-019-06436-w","article-title":"Automated multiparametric localization of prostate cancer based on B-mode, shear-wave elastography, and contrast-enhanced ultrasound radiomics","volume":"30","author":"Wildeboer","journal-title":"Eur Radiol"},{"issue":"2","key":"R30","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1148\/radiol.2020192330","article-title":"Prostate microstructure in prostate cancer using 3-T MRI with diffusion-relaxation correlation spectrum imaging: validation with whole-mount digital histopathology","volume":"296","author":"Zhang","journal-title":"Radiology"},{"issue":"11","key":"R31","doi-asserted-by":"publisher","first-page":"6699","DOI":"10.1109\/JBHI.2024.3444908","article-title":"Framework for deep learning based multi-modality image registration of snapshot and pathology images","volume":"28","author":"Schoop","journal-title":"IEEE J Biomed Health Inform"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2015.11.001","article-title":"3D surface-based registration of ultrasound and histology in prostate cancer imaging","volume":"47","author":"Schalk","journal-title":"Comput Med Imaging Graph"},{"issue":"6","key":"R33","doi-asserted-by":"publisher","first-page":"2118","DOI":"10.1118\/1.3130017","article-title":"Development and validation of a new guidance device for lateral approach stereotactic breast biopsy","volume":"36","author":"Ma","journal-title":"Med Phys"},{"issue":"1092","key":"R34","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20180250","article-title":"Differentiating vacuum-assisted breast biopsy from core needle biopsy: is it necessary?","volume":"91","author":"Nakano","journal-title":"Br J Radiol"},{"issue":"2","key":"R35","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/s10396-022-01279-3","article-title":"Comparison of the clinical and pathological characteristics of ultrasound-guided biopsy for breast masses and non-mass lesions between 16-gauge spring-loaded core needle biopsy and 12-gauge spring-loaded vacuum-assisted biopsy","volume":"50","author":"Yashima","journal-title":"J Med Ultrasonics"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1148\/radiol.220548","article-title":"Antithrombotic therapy and hematoma risk during image-guided core-needle breast biopsy","volume":"306","author":"Loving","journal-title":"Radiology"},{"key":"R37","unstructured":"ChaiZhifeiF\/breast-cancer-component-segmentation. GitHub. URL: https:\/\/github.com\/ChaiZhifeiF\/Breast-Cancer-Component-Segmentation [Accessed 21-01-2026]"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e81181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:14:53Z","timestamp":1782843293000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e81181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":37,"URL":"https:\/\/doi.org\/10.2196\/81181","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,23]]},"article-number":"v14i7e81181"}}