Abstract P5-02-09: Quantitative analysis of fiber-level collagen features in H&E whole-slide images predicts neoadjuvant therapy response in patients with HER2+ breast cancer

Background: Neoadjuvant treatment (NAT) combining chemotherapy and HER2-targeted agents is frequently administered to HER2-positive (HER2+) breast cancer (BC) patients, with some experiencing a pathological complete response (pCR) and others having residual disease measured by the residual cancer burden (RCB) score. Here, we use a physics-guided machine learning (ML)-based approach to extract fiber-level collagen features from hematoxylin and eosin (H&E)-stained whole slide images (WSIs) and identify collagen-related associations with treatment response in HER2+ patients receiving NAT.

Methods: Clinical data and specimens from stage II-III HER2+ BC patients enrolled on the De-escalation to Adjuvant Antibodies Post-pCR to Neoadjuvant THP (DAPHNe; NCT03716180) clinical trial and treated with neoadjuvant paclitaxel/trastuzumab/pertuzumab were analyzed. An ML-based model trained to identify regions of BC tissue as invasive carcinoma, ductal carcinoma in situ (DCIS), diffuse inflammatory infiltrate, stroma, necrosis, or normal tissue was deployed on WSIs of H&E-stained diagnostic core needle biopsies (N=89) to generate tissue overlays. Additional tissue areas were computed from the tissue model predictions using heatmap transformation, including tumor nests (continuous regions predicted as invasive cancer epithelium or DCIS), tumor nest borders (stromal region boundaries 10 μm from tumor nests), and bulk tumor borders (stromal region boundaries 300 μm from aggregated tumor nests). A separate ML-based model trained to identify fiber-level collagen features in WSIs of H&E-stained specimens was also deployed to generate collagen overlays. A fiber feature extraction pipeline was utilized to characterize properties of all identified collagen fibers in the WSI (on the order of hundreds of thousands per slide), including length, width, tortuosity, and angle. These fiber features were then assessed based on their position within the tumor (e.g. relative to the tumor nest border). Combinatorial features (e.g. angle of fibers with respect to tumor boundary) were then explored univariately for associations (N=609) with treatment response. Patients with pCR (RCB=0; N=53) were considered responders, while all other cases (RCBI-III; N=36) were designated non-responders. Due to the small size of the cohort analyzed here, raw p-values are reported.

Results: Using estrogen receptor status as a clinical covariate, a logistic regression-based univariate analysis of 609 collagen-associated features revealed six features to strongly associate with pCR (p< 0.05, AUC≥0.75; Table 1). Notable feature themes were identified: 1) fiber tortuosity in tumor nest borders and tumor borders, 2) angle of fibers in tumor border with respect to tumor boundary, and 3) distribution patterns of fiber width in tumor nest borders. The presence of fibers perpendicular to tumor boundary tangents was negatively associated with pCR, as was higher fiber tortuosity and thickness in tumor nest borders.

Conclusions: Improved prediction of response to NAT in patients with BC is needed to determine appropriate treatment strategies for each patient. Here, using ML-based models to identify tissue features and collagen fibers, we identify collagen-associated features, measured directly from WSIs of H&E-stained diagnostic BC biopsies, that negatively correlate with pCR. Additional development of this strategy, including the addition of cell identification models and known clinical information, is underway to further refine this novel predictive model.

Generating Cell Type-Specific Protein Signatures from Non-symptomatic and Diseased Tissues

Here we demonstrate a technique to generate proteomic signatures of specific cell types within heterogeneous populations. While our method is broadly applicable across biological systems, we have limited the current work to study neural cell types isolated from human, post-mortem Alzheimer's disease (AD) and aged-matched non-symptomatic (NS) brains. Motivating the need for this tool, we conducted an initial meta-analysis of current, human AD proteomics studies. While the results broadly corroborated major neurodegenerative disease hypotheses, cell type-specific predictions were limited. By adapting our Formaldehyde-fixed Intracellular Target-Sorted Antigen Retrieval (FITSAR) method for proteomics and applying this technique to characterize AD and NS brains, we generated enriched neuron and astrocyte proteomic profiles for a sample set of donors (available at www.fitsarpro.appspot.com ). Results showed the feasibility for using FITSAR to evaluate cell-type specific hypotheses. Our overall methodological approach provides an accessible platform to determine protein presence in specific cell types and emphasizes the need for protein-compatible techniques to resolve systems complicated by cellular heterogeneity.