{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:36:34Z","timestamp":1785418594276,"version":"3.56.0"},"reference-count":33,"publisher":"AOSIS","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SAJR"],"abstract":"<jats:p>Background:\u00a0Breast cancer remains a major public health burden in South Africa, with diagnostic delays contributing to poor outcomes. Ultrasound is effective for early detection but is limited by access and operator variability. Integrating artificial intelligence (AI) into point-of-care ultrasound (POCUS) offers a potential solution.\nObjectives:\u00a0To evaluate the diagnostic performance of a locally developed AI-enabled POCUS system (Breast AI) in predicting malignancy among women with palpable breast abnormalities.\nMethod:\u00a0A prospective cohort study was conducted between June 2024 and November 2024 at Groote Schuur Hospital. Women aged \u2265 25 years with suspicious breast lesions underwent Breast AI ultrasound prior to biopsy. Real-time malignancy risk scores were compared with histopathological results. Diagnostic accuracy was assessed using sensitivity, specificity, positive predictive value (PPV), F1 score and area under the curve (AUC).\nResults:\u00a0Among 159 participants, Breast AI achieved a sensitivity of 67.2%, specificity of 79.4% and PPV of 70.3% at a 51% threshold. The AUC was 0.76, reflecting moderate discriminatory performance. F1 score analysis identified 51% as the optimal cut-off (F1 = 65.7%). Benign pathologies such as fibroadenomas and fat necrosis correlated with low AI scores. A three-tiered risk model was developed: &lt; 30% (low), 30% \u2013 51% (intermediate) and &gt; 51% (high risk).\nConclusion:\u00a0Breast AI demonstrates promising diagnostic accuracy for triaging suspicious breast lesions, particularly in resource-constrained settings.\nContribution:\u00a0This study provides real-world evidence supporting the integration of AI into POCUS to improve breast cancer detection and clinical decision-making in low-resource environments.<\/jats:p>","DOI":"10.4102\/sajr.v29i1.3195","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T07:36:37Z","timestamp":1759908997000},"update-policy":"https:\/\/doi.org\/10.4102\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["AI-enabled POCUS for breast cancer risk stratification in a resource-limited tertiary clinic"],"prefix":"10.4102","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7602-0206","authenticated-orcid":false,"given":"Kathryn","family":"Malherbe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8910-6925","authenticated-orcid":false,"given":"Francois","family":"Malherbe","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03p74gp79","id-type":"ROR","asserted-by":"publisher"}],"name":"University of Cape Town"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0545-5413","authenticated-orcid":false,"given":"Liana","family":"Roodt","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/03p74gp79","id-type":"ROR","asserted-by":"publisher"}],"name":"University of Cape Town"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2580","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"ref0","doi-asserted-by":"crossref","unstructured":"Swinny CA, Kagee A, Roomaney R. Delayed help-seeking for symptomatic breast cancer: Reasons for delay among participants receiving assessment at a public healthcare facility in South Africa. S Afr J Psychol. 2022;52(1):87\u201398. https:\/\/doi.org\/10.1177\/0081246321992477","DOI":"10.1177\/0081246321992477"},{"key":"ref1","doi-asserted-by":"crossref","unstructured":"Moodley J, Cairncross L, Naiker T, Constant D. From symptom discovery to assessment-women\u2019s pathways to breast cancer care: A cross-sectional study. BMC Cancer. 2018;18:1\u201311. https:\/\/doi.org\/10.1186\/s12885-018-4219-7","DOI":"10.1186\/s12885-018-4219-7"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"Dlamini Z, Molefi T, Khanyile R, et al. From incidence to intervention: A comprehensive look at breast cancer in South Africa. Oncol Ther. 2024;12(1):1\u201311. https:\/\/doi.org\/10.1007\/s40487-023-00248-1","DOI":"10.1007\/s40487-023-00248-1"},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"Sarmah N, Sibiya MN, Khoza TE. The sociocultural influences on breast cancer screening among rural African women in South Africa. Int J Environ Res Public Health. 2023;20(21): 7005. https:\/\/doi.org\/10.3390\/ijerph20217005","DOI":"10.3390\/ijerph20217005"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"Rayne S, Schnippel K, Firnhaber C, Wright K, Kruger D, Benn CA. Fear of treatments surpasses demographic and socioeconomic factors in affecting patients with breast cancer in urban South Africa. J Glob Oncol. 2017;3(2):125\u2013134. https:\/\/doi.org\/10.1200\/JGO.2015.002691","DOI":"10.1200\/JGO.2015.002691"},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"Gonzaga MA. How accurate is ultrasound in evaluating palpable breast masses? Pan Afr Med J. 2010;7:1. Epub 2010 Sep 2. PMID: 21918690; PMCID: PMC3172638.","DOI":"10.4314\/pamj.v7i1.69094"},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"Youk JH, Kim EK, Kim MJ, Kwak JY, Son EJ. Performance of hand-held whole-breast ultrasound based on BI-RADS in women with mammographically negative dense breast. Eur Radiol. 2010;21(4):667\u2013675. https:\/\/doi.org\/10.1007\/s00330-010-1955-8","DOI":"10.1007\/s00330-010-1955-8"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"Malherbe K. Revolutionizing breast cancer screening: Integrating artificial intelligence with clinical examination for targeted care in South Africa. J Radiol Nurs. 2025;44(2);195\u2013202. https:\/\/doi.org\/10.1016\/j.jradnu.2024.12.004","DOI":"10.1016\/j.jradnu.2024.12.004"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"Omidiji O, Campbell PC, Irurhe N, Atalabi OM, Toyobo O. Breast cancer screening in a resource poor country: Ultrasound versus mammography. Ghana Med J. 2017;51(1):6. https:\/\/doi.org\/10.4314\/gmj.v51i1.2","DOI":"10.4314\/gmj.v51i1.2"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Mans P-A, Adeniyi OV. South African medical interns\u2019 perspectives on the use of point of care ultrasound. S Afr Fam Pract. 2023;65(1):a5772. https:\/\/doi.org\/10.4102\/safp.v65i1.5772","DOI":"10.4102\/safp.v65i1.5772"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"Sarmah N, Sibiya MN, Khoza TE. Barriers and enablers to breast cancer screening in rural South Africa. Curationis. 2024;47(1):a2583. https:\/\/doi.org\/10.4102\/curationis.v47i1.2583","DOI":"10.4102\/curationis.v47i1.2583"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"Zheng D, He X, Jing J. Overview of artificial intelligence in breast cancer medical imaging. J Clin Med. 2023;12(2):419. https:\/\/doi.org\/10.3390\/jcm12020419","DOI":"10.3390\/jcm12020419"},{"key":"ref12","unstructured":"Malherbe K. A diagnostic algorithm for accurate detection of breast carcinoma on ultrasound [homepage on the Internet]. Doctoral dissertation, University of Pretoria; 2023 [cited 2021 Aug 18]. Available from: https:\/\/repository.up.ac.za\/items\/2721960b-6eaa-4044-8a9e-e92b5df863d2"},{"key":"ref13","unstructured":"D\u2019Orsi CJ, Sickles EA, Mendelson EB, Morris EA. Breast imaging reporting and data system (BI-RADS) committee. ACR BI-RADS\u00ae atlas, breast imaging reporting and data system. Reston, VA: American College of Radiology; 2013."},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"Esteva A, Chou K, Yeung S, et al. Deep learning-enabled medical computer vision. NPJ Digit Med. 2019;2:10. https:\/\/doi.org\/10.1038\/s41746-020-00376-2","DOI":"10.1038\/s41746-020-00376-2"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"Zhu Y, Tan Y, Pang P. Deep learning of ultrasound images predicts histopathology of breast cancer. J Ultrasound Med. 2019;38(9):2509\u20132516. https:\/\/doi.org\/10.1002\/jum.14942","DOI":"10.1002\/jum.14942"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"McKinney SM, Sieniek M, Godbole V, et al. International evaluation of an AI system for breast cancer screening. Nature. 2020;577(7788):89\u201394. https:\/\/doi.org\/10.1038\/s41586-019-1799-6","DOI":"10.1038\/s41586-019-1799-6"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez-Ruiz A, L\u00e5ng K, Gubern-Merida A, et al. Stand-alone artificial intelligence for breast cancer detection in mammography: Comparison with 101 radiologists. J Natl Cancer Inst. 2019;111(9):916\u2013922. https:\/\/doi.org\/10.1093\/jnci\/djy222","DOI":"10.1093\/jnci\/djy222"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"Zhou LQ, Wu XL, Huang SY. Lymph node metastasis prediction from primary breast cancer US images using deep learning. Radiology. 2020;294(1):19\u201328. https:\/\/doi.org\/10.1148\/radiol.2019190372","DOI":"10.1148\/radiol.2019190372"},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"Kwon H, Oh SH, Kim M-G, et al. Enhancing breast cancer detection through advanced AI-driven ultrasound technology: A comprehensive evaluation of vis-bus. Diagnostics. 2024;14(17): 1867. https:\/\/doi.org\/10.3390\/diagnostics14171867","DOI":"10.3390\/diagnostics14171867"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"Koo C, Yang A, Welch CS, et al. Validating racial and ethnic non-bias of artificial intelligence decision support for diagnostic breast ultrasound evaluation. J Med Imag. 2023;10(06):061108. https:\/\/doi.org\/10.1117\/1.JMI.10.6.061108","DOI":"10.1117\/1.JMI.10.6.061108"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"Dickens C, Joffe M, Jacobson JS, et al. Stage at breast cancer diagnosis and distance from diagnostic hospital in a Periurban setting: A South African public hospital case series of over 1,000 women. Int J Cancer. 2014;135(9):2173\u20132182. https:\/\/doi.org\/10.1002\/ijc.28861","DOI":"10.1002\/ijc.28861"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"Tshabalala G, Blanchard C, Mmoledi K, et al. A qualitative study to explore healthcare providers\u2019 perspectives on barriers and enablers to early detection of breast and cervical cancers among women attending primary healthcare clinics in Johannesburg, South Africa. PLoS Global Public Health. 2023;3(5):e0001826. https:\/\/doi.org\/10.1371\/journal.pgph.0001826","DOI":"10.1371\/journal.pgph.0001826"},{"key":"ref23","unstructured":"Ha R, Mutasa S, Karcich J, et al. Predicting breast cancer molecular subtype with MRI-derived radiomics. Radiology. 2021;298(1):60\u201370."},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Berg WA, Zhang Z, Lehrer D, et al. Detection of breast cancer with addition of annual screening ultrasound or a single screening MRI to mammography in women with elevated breast cancer risk. JAMA. 2012;307(13):1394\u20131404. https:\/\/doi.org\/10.1001\/jama.2012.388","DOI":"10.1001\/jama.2012.388"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"Wanders JOP, Veldhuis WB, Loo CE, et al. Volumetric breast density affects performance of digital screening mammography. Breast Cancer Res Treat. 2017;162(1):95\u2013103. https:\/\/doi.org\/10.1007\/s10549-016-4090-7","DOI":"10.1007\/s10549-016-4090-7"},{"key":"ref26","doi-asserted-by":"crossref","unstructured":"Giuliano V, Giuliano C. Improved breast cancer detection using 3D automated breast ultrasound in women with dense breast tissue. Clin Imaging. 2013;37(3):480\u2013486. https:\/\/doi.org\/10.1016\/j.clinimag.2012.09.018","DOI":"10.1016\/j.clinimag.2012.09.018"},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"Kim HE, Kim HH, Han BK, et al. Changes in cancer detection and false-positive recall in mammography using artificial intelligence: A retrospective, multireader study. Lancet Digit Health. 2020;2(3):e138\u2013e148. https:\/\/doi.org\/10.1016\/S2589-7500(20)30003-0","DOI":"10.1016\/S2589-7500(20)30003-0"},{"key":"ref28","unstructured":"Carty NJ, Carter C, Rubin C, Ravichandran D, Royle GT, Taylor I. Management of fibroadenoma of the breast. Ann R Coll Surg Engl. 1995 Mar;77(2):127\u201330. PMID: 7793802; PMCID: PMC2502143."},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"Youk JH, Gweon HM, Son EJ. Shear-wave elastography in breast ultrasonography: the state of the art. Ultrasonography. 2017 Oct;36(4):300\u2013309. https:\/\/doi.org\/10.14366\/usg.17024. Epub 2017 Apr 5. PMID: 28513127; PMCID: PMC5621798.","DOI":"10.14366\/usg.17024"},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"M\u00e9ndez CA, Pizzorni Ferrarese F, Summers P, Petralia G, Menegaz G. DCE-MRI and DWI Integration for Breast Lesions Assessment and Heterogeneity Quantification. Int J Biomed Imaging. 2012;2012:676808. https:\/\/doi.org\/10.1155\/2012\/676808. Epub 2012 Nov 19. PMID: 23213317; PMCID: PMC3507154.","DOI":"10.1155\/2012\/676808"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"Skaane P, Young K, Skjennald A. Population-based mammography screening: Comparison of screen-film and full-field digital mammography with soft-copy reading\u2014The Oslo I Study. Radiology. 2003;229(3):877\u2013884. https:\/\/doi.org\/10.1148\/radiol.2293021171","DOI":"10.1148\/radiol.2293021171"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"Aliyu LD, Kurjak A, Wataganara T, et al. Ultrasound in Africa: What can really be done? J Perinat Med. 2016;44(2):119\u2013123. https:\/\/doi.org\/10.1515\/jpm-2015-0224","DOI":"10.1515\/jpm-2015-0224"}],"container-title":["South African Journal of Radiology"],"original-title":[],"link":[{"URL":"https:\/\/sajr.org.za\/index.php\/sajr\/article\/view\/3195\/3910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T07:36:44Z","timestamp":1759909004000},"score":1,"resource":{"primary":{"URL":"https:\/\/sajr.org.za\/index.php\/sajr\/article\/view\/3195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":33,"URL":"https:\/\/doi.org\/10.4102\/sajr.v29i1.3195","relation":{},"ISSN":["1027-202X","2078-6778"],"issn-type":[{"value":"1027-202X","type":"print"},{"value":"2078-6778","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"article-number":"a3195"}}