Validation of a Quantitative Ultrasound Texture Analysis Model for Early Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer: A Prospective Serial Imaging Study

• Published in: Cancers Vol. 17; no. 15; p. 2594
• Main Authors: Moore-Palhares, Daniel, Sannachi, Lakshmanan, Chan, Adrian Wai, Dasgupta, Archya, DiCenzo, Daniel, Gandhi, Sonal, Pezo, Rossanna, Eisen, Andrea, Warner, Ellen, Wright, Frances, Look Hong, Nicole, Sadeghi-Naini, Ali, Skarpathiotakis, Mia, Curpen, Belinda, Betel, Carrie, Kolios, Michael C., Trudeau, Maureen, Czarnota, Gregory J.
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 07.08.2025; MDPI
• Subjects: Adjuvant treatment; Artificial intelligence; Breast cancer; Cancer; Cancer therapies; Care and treatment; Chemotherapy; ErbB-2 protein; Estrogen receptors; Fourier transforms; Image processing; Invasiveness; Learning algorithms; Machine learning; Oncology, Experimental; Patients; Radiomics; Response rates; Statistical analysis; Tomography; Trastuzumab; Tumors; Ultrasonic imaging; Ultrasound; Canada; Ontario; quantitative ultrasound; neoadjuvant chemotherapy; precision oncology; radiomics; breast cancer; machine learning
• ISSN: 2072-6694; 2072-6694
• DOI: 10.3390/cancers17152594

Background/Objectives: Patients with breast cancer who do not achieve a complete response to neoadjuvant chemotherapy (NAC) may benefit from intensified adjuvant systemic therapy. However, such treatment escalation is typically delayed until after tumour resection, which occurs several months into the treatment course. Quantitative ultrasound (QUS) can detect early microstructural changes in tumours and may enable timely identification of non-responders during NAC, allowing for earlier treatment intensification. In our previous prospective observational study, 100 breast cancer patients underwent QUS imaging before and four times during NAC. Machine learning algorithms based on QUS texture features acquired in the first week of treatment were developed and achieved 78% accuracy in predicting treatment response. In the current study, we aimed to validate these algorithms in an independent prospective cohort to assess reproducibility and confirm their clinical utility. Methods: We included breast cancer patients eligible for NAC per standard of care, with tumours larger than 1.5 cm. QUS imaging was acquired at baseline and during the first week of treatment. Tumour response was defined as a ≥30% reduction in target lesion size on the resection specimen compared to baseline imaging. Results: A total of 51 patients treated between 2018 and 2021 were included (median age 49 years; median tumour size 3.6 cm). Most were estrogen receptor–positive (65%) or HER2-positive (33%), and the majority received dose-dense AC-T (n = 34, 67%) or FEC-D (n = 15, 29%) chemotherapy, with or without trastuzumab. The support vector machine algorithm achieved an area under the curve of 0.71, with 86% accuracy, 91% specificity, 50% sensitivity, 93% negative predictive value, and 43% positive predictive value for predicting treatment response. Misclassifications were primarily associated with poorly defined tumours and difficulties in accurately identifying the region of interest. Conclusions: Our findings validate QUS-based machine learning models for early prediction of chemotherapy response and support their potential as non-invasive tools for treatment personalization and clinical trial development focused on early treatment intensification.