{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T18:17:10Z","timestamp":1779905830935,"version":"3.53.1"},"reference-count":14,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"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:sec><jats:title>Background<\/jats:title><jats:p>This study evaluates the performance of a deep learning\u2013based artificial intelligence (AI) system developed under the Stradexa (a branded form of doxorubicin used regionally in South Africa) initiative, designed for real-time risk stratification and treatment monitoring in HER2-positive breast cancer. Conducted in a routine clinical setting, the system\u2019s predictive capacity was assessed by comparing AI-generated risk scores derived from B-mode ultrasound with histopathology, immunohistochemistry, and treatment response in patients undergoing trastuzumab or doxorubicin therapy. The AI tool demonstrated favorable diagnostic accuracy and a meaningful correlation between risk score reduction and tumor response during therapy, particularly in the trastuzumab group. These findings support the integration of AI-assisted ultrasound for personalized oncology management.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objectives<\/jats:title><jats:p>This study aims to evaluate the effectiveness of Herceptin (trastuzumab) compared to Stradexa (a branded form of doxorubicin used regionally in South Africa) (doxorubicin) in reducing Breast AI\u2013predicted malignancy risk percentages and to assess the feasibility of using a deep learning\u2013based AI system for monitoring treatment response in breast cancer.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 86 patients were selected from a larger cohort of 150, based on inclusion criteria of histologically confirmed breast cancer, availability of baseline and follow-up ultrasound scans, and ongoing chemotherapy with either transtumazub or doxorubicin. Patients with incomplete imaging, prior treatment, or other malignancies were excluded. The sample size of 86 provided borderline statistical power (~0.74) to detect moderate effect sizes between treatment groups, considering an alpha of 0.05. B-mode ultrasound images were analyzed using a convolutional neural network\u2013driven Breast AI platform to generate malignancy risk percentages before and during treatment. Statistical analysis was performed to evaluate within-group and between-group changes in AI scores using appropriate inferential methods. All results, interpretations, and manuscript content were produced entirely by human researchers without the use of generative AI tools.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>These findings highlight the potential of AI-based imaging tools to support real-time treatment monitoring in breast cancer. The observed trend favoring Herceptin suggests that AI-generated risk scores may serve as non-invasive indicators of treatment efficacy. Broader validation across larger, more diverse cohorts is warranted to confirm these preliminary results and further develop AI-guided oncology workflows.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2025.1639474","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T11:13:16Z","timestamp":1755169996000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Validation of a deep learning\u2013based AI system for HER2-targeted breast cancer assessment using ultrasound imaging in a clinical setting"],"prefix":"10.3389","volume":"15","author":[{"given":"Kathryn","family":"Malherbe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.v127.16","article-title":"The ever-increasing importance of cancer as a leading cause of premature death worldwide","volume":"127","author":"Bray","year":"2021","journal-title":"Cancer"},{"key":"B2","article-title":"Personalized oncology: AI-driven imaging\u00a0biomarkers for treatment response in breast cancer","volume":"17","author":"Smith","year":"2020","journal-title":"Nat Rev Clin Oncol"},{"key":"B3","article-title":"Machine learning-based risk stratification for breast cancer: A multicenter study","volume":"23","author":"Liu","year":"2022","journal-title":"Lancet Oncol"},{"key":"B4","article-title":"Real-time AI-guided oncology treatment: Implications for chemotherapy regimens","volume":"38","author":"Patel","year":"2020","journal-title":"J Clin Oncol"},{"key":"B5","article-title":"The impact of age on breast cancer subtypes and treatment response: An analysis of 10,000 cases","volume":"119","author":"Kim","year":"2018","journal-title":"Br J Cancer"},{"key":"B6","first-page":"197","article-title":"The role of AI in breast cancer diagnostics: A systematic review of deep learning applications","volume":"63","author":"Jones","year":"2019","journal-title":"J Med Imaging Radiat Oncol"},{"key":"B7","article-title":"AI-enhanced ultrasound imaging for breast cancer detection: Current challenges and future perspectives","volume":"182","author":"Williams","year":"2020","journal-title":"Breast Cancer Res Treat"},{"key":"B8","article-title":"The application of deep learning to breast cancer imaging: Current trends and future directions","volume":"11","author":"Fernandes","year":"2022","journal-title":"Cancer Med"},{"key":"B9","volume-title":"A diagnostic algorithm for accurate detection of breast carcinoma on ultrasound","author":"Malherbe","year":"2023"},{"key":"B10","first-page":"277","article-title":"Breast image analysis for risk assessment, detection, diagnosis, and treatment response","volume":"21","author":"Giger","year":"2019","journal-title":"Annu Rev Biomed Eng"},{"key":"B11","article-title":"A deep learning mammography-based model for improved breast cancer risk prediction","volume":"3","author":"Yala","year":"2021","journal-title":"Radiology: Artif Intell"},{"key":"B12","article-title":"AI-powered risk assessment for breast cancer recurrence: A 5-year follow-up study","volume":"34","author":"Chang","year":"2023","journal-title":"Ann Oncol"},{"key":"B13","first-page":"50","article-title":"AI-assisted mammography interpretation: Reducing variability in breast cancer diagnosis","volume":"300","author":"Zhao","year":"2021","journal-title":"Radiology"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3390\/s23065354","article-title":"Systematic meta-analysis of computer-aided detection of breast cancer using hyperspectral imaging","volume":"23","author":"Ullah","year":"2023","journal-title":"Sensors"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1639474\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T11:13:18Z","timestamp":1755169998000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1639474\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,14]]},"references-count":14,"alternative-id":["10.3389\/fonc.2025.1639474"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1639474","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,14]]},"article-number":"1639474"}}