Highly accurate response prediction in high-risk early breast cancer patients using a biophysical simulation platform

Abstract

Purpose Pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) in early breast cancer (EBC) is largely dependent on breast cancer subtype, but no clinical-grade model exists to predict response and guide selection of treatment. A biophysical simulation of response to NAC has the potential to address this unmet need. Methods We conducted a retrospective evaluation of a biophysical simulation model as a predictor of pCR. Patients who received standard NAC at the University of Chicago for EBC between January 1st, 2010 and March 31st, 2020 were included. Response was predicted using baseline breast MRI, clinicopathologic features, and treatment regimen by investigators who were blinded to patient outcomes. Results A total of 144 tumors from 141 patients were included; 59 were triple-negative, 49 HER2-positive, and 36 hormone-receptor positive/HER2 negative. Lymph node disease was present in half of patients, and most were treated with an anthracycline-based regimen (58.3%). Sensitivity and specificity of the biophysical simulation for pCR were 88.0% (95% confidence interval [CI] 75.7 – 95.5) and 89.4% (95% CI 81.3 – 94.8), respectively, with robust results regardless of subtype. In patients with predicted pCR, 5-year event-free survival was 98%, versus 79% with predicted residual disease (log-rank p = 0.01, HR 4.57, 95% CI 1.36 – 15.34). At a median follow-up of 5.4 years, no patients with predicted pCR experienced disease recurrence. Conclusion A biophysical simulation model accurately predicts pCR and long-term outcomes from baseline MRI and clinical data, and is a promising tool to guide escalation/de-escalation of NAC.

Next generation immuno-oncology tumor profiling using a rapid, non-invasive, computational biophysics biomarker in early-stage breast cancer

“…The pCR rate in the I-SPY2 trial with pembrolizumab and SOC chemotherapy was 60% in TNBC and 30% in HR+/HER2cancers (Nanda et al, 2020), while the GIADA trial demonstrated a pCR rate of 16.3% in IO-treated HR+/HER2-patients (Franzoi et al, 2021;Dieci et al, 2022). The success of this validation strategy supports the potential for expansion of virtual clinical trials in both research and drug development applications (Howard et al, 2022). Additionally, this result signals the potential of the TumorIO Score to accurately predict ICI responsiveness and provide a strong correlation to randomized control trials.…”

“…We then correlated single cell PD-L1 expression with transcriptional biomarkers related to metabolic activity ( Supplementary Figures 1 , 2 ) and angiogenesis ( Supplementary Figure 3 ). PD-L1 expression throughout the tumor cannot be visualized using SOC imaging; therefore, as a surrogate for spatially-resolved PD-L1 expression, we simulated and quantified the spatial distribution of both metabolic activity and angiogenesis within individual patient tumors and the TME using the Simul- omics 4D Engine (Howard et al, 2022 ). This analysis resulted in a spatial map of biological features correlated with PD-L1 expression probability, which together underly the TumorIO spatial biomarker.…”

“…Virtual tumors were created from DCE-MRIs using the Simul-omics 4D Engine biophysical modeling platform (Howard et al, 2022 ). This platform uses artificial intelligence in the form of a convolutional neural network (CNN) to segment patient DCE-MRIs into regions corresponding to tumor, vasculature, and surrounding tissue automatically (followed by manual review; Figure 2 ).…”

“…Immunohistochemistry (IHC), although widely used to assess PD-L1 pathology, is nevertheless highly variable and dependent on experimental methodology (Patel and Kurzrock, 2015 ). An opportune moment therefore exists for employing innovative approaches incorporating mathematical modeling (Caballo et al, 2022 ; Howard et al, 2022 ), with the intent to develop novel biomarkers to determine tumor IO responsiveness, with a forthcoming need in ESBC (Franzoi et al, 2021 ).…”

“…We address these conventional biomarker pitfalls by employing and integrating validated biophysics-based computational biology methods (Howard et al, 2022 ) in order to predict IO therapy response. We have previously demonstrated that our technology's data predictions match with radiologist-verified assessment.…”