Abstract 1160: Multi-scale deep learning feature distributions distinguish invasive ductal and lobular breast cancer slides
Patience Mukashyaka, Ali Foroughi pour, Jeffrey H. Chuang · Cancer Research · 2022
Abstract Advances in digital pathology have streamlined use of deep learning methodologies to connect morphology and phenotype in hematoxylin and eosin(H&E) stained images. Whole slide images (WSIs) are gigantic, necessitating a tile-based analysis: a WSI is broken into smaller images called tiles, each tile is analyzed separately, and tile level information are then combined to get a slide level prediction. Context aware models integrating tiles of different sizes have been used to combine morphological features present at different scales, and attention-based pipelines have successfully been used to combine tile level information. Pipelines that combine attention-based and context aware learning are less studied. While both methodologies have shown utility when used individually, models that combine both tend to suffer from a large number of parameters to estimate, which frustrates reliable training. Here we show percentiles of deep learning features extracted at different scales serve as a crude multiscale attention mechanism. The proposed model separates TCGA-BRCA invasive ductal and lobular carcinoma FFPE WSIs (AUC=0.85±0.02), which improves upon the performance of the fully tile-based model of [1] (AUC=0.80 ±0.04). The proposed approach enjoys higher average AUC and lower standard deviation across multiple random train/test splits of data. Our results suggest percentile-based feature construction is an interesting alternative when reliable training of fully deep learning models is challenging. References: [1] Noorbakhsh, J., Farahmand, S., Foroughi pour, A. et al. Deep learning-based cross-classifications reveal conserved spatial behaviors within tumor histological images. Nat Commun 11, 6367 (2020). https://doi.org/10.1038/s41467-020-20030-5 Citation Format: Patience Mukashyaka, Ali Foroughi Pour, Jeffrey H. Chuang. Multi-scale deep learning feature distributions distinguish invasive ductal and lobular breast cancer slides [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1160.