Abstract PO5-01-10: Evaluating a computer-aided platform for predicting recurrence and survival in an Oncotype Dx tested breast cancer cohort

Abstract Background: Oncotype DX Breast Recurrence ScoreÒ (ODXRS) is a widely used predictive measure of breast cancer recurrence risk and chemotherapy benefit for patients with estrogen receptor positive (ER+), human epidermal growth factor receptor-2 negative (HER2-) breast cancers. ODXRS testing incurs additional costs and delays. These drawbacks could be obviated by innovative computer-aided technologies within digital pathology workflows. Such technologies could be developed to perform a wide variety of diagnostic and prognostic tests on digital whole slide images (WSIs) of hematoxylin and eosin (H&E)-stained tissue alone. This would save time, cost, and sample tissue whilst still providing critical prognostic information for patient management. Q-Plasia OncoReader Breast (QPORB) is a computer-aided solution which extracts information from H&E WSIs to provide diagnostic and prognostic information for breast cancer specimens. Aims: The aim of this study was to identify whether the computer aided QPROB platform could successfully predict breast cancer recurrence from H&E WSIs alone in line with recurrence predicted by ODXRS. Methods: H&E slides corresponding to tissue blocks sent for ODXRS testing from primary breast cancer resection/excision specimens from St James’s University Hospital, Leeds, UK (n=137 cases, 1 slide per case) were collected, anonymized, and scanned at x20 magnification on an Aperio AT2 scanner. Relevant pathological and clinical data were collected from electronic pathology reports and patient records. These data included ODXRS and recurrence events. QPORB analyzed each case/slide and generated a digital biomarker profile from the H&E images alone, combining statistical physics and tumor biology to quantify malignant cell cycle deformation. QPORB’s biomarker profile and ODXRS for each case was compared to disease-free survival (DFS) and overall survival (OS). Kaplan-Meier survival analyses were performed. Confounding factors (age, tumor grade, invasive tumor size and Charlson Comorbidity Index) were accounted for. Results: Results of three QPORB-generated indices - two putatively associated with overall cell cycle signature and one with G1 deformation, and their combined overall biomarker profile did not predict DFS in this cohort. However, with regards to OS, all three indices and the combined biomarker profile predicted OS over a median follow-up period of 5 years (P=0.044). 5% of WSIs (7/137) did not meet the criteria to be analyzed by QPORB and 4% (6/137) could not be analyzed by QPORB (attrition). While ODXRS similarly predicted OS but not DFS, the follow-up duration was suboptimal. Conclusion: While QPORB indices evaluated in this work, putatively associated with overall cell cycle signature and G1 deformation, did not predict breast cancer recurrence on a par with ODXRS, it has shown promising results as potential adjunct device to provide an estimate of OS for breast cancer patients eligible for ODXRS testing. Future work will expand on this observational cohort, blindly validate these findings, and extend the work to encompass all breast cancer molecular subtypes. Citation Format: Satabhisa Mukhopadhyay, Elizabeth Walsh, Rebecca Millican-Slater, Andrew Hanby, Joanne Stephenson, Tathagata Dasgupta, Nicolas Orsi. Evaluating a computer-aided platform for predicting recurrence and survival in an Oncotype Dx tested breast cancer cohort [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO5-01-10.