A deep learning approach to assess the predominant tumor growth pattern in whole-slide images of lung adenocarcinoma

Z. Swiderska-Chadaj, K. Nurzynska, G. Bartlomiej, K. Grunberg, L. van der Woude, M. Looijen-Salamon, A. Walts, T. Markiewicz, F. Ciompi and A. Gertych

Medical Imaging 2020;11320:113200D.

DOI Cited by ~4

When diagnosing and reporting lung adenocarcinoma (LAC), pathologists currently include an assessment of histologic tumor growth patterns because the predominant growth pattern has been reported to impact prognosis. However, the subjective nature of manual slide evaluation contributes to suboptimal inter-pathologist variability in tumor growth pattern assessment. We applied a deep learning approach to identify and automatically delineate areas of four tumor growth patterns (solid, acinar, micropapillary, and cribriform) and non-tumor areas in whole-slide images (WSI) from resected LAC specimens. We trained a DenseNet model using patches from 109 slides collected at two institutions. The model was tested using 56 WSIs including 20 that were collected at a third institution. Using the same slide set, the concordance between the DenseNet model and an experienced pathologist (blinded to the DenseNet results) in determining the predominant tumor growth pattern was substantial(kappa score = 0.603). Using a subset of 36 test slides that were manually annotated for tumor growth patterns, we also measured the F1-score for each growth pattern: 0.95 (solid), 0.78 (acinar), 0.76 (micropapillary), 0.28 (cribriform) and 0.97 (non-tumor). Our results suggest that DenseNet assessment of WSIs with solid, acinar, and micropapillary predominant tumor growth is more robust than for the WSIs with predominant cribriform growth which are less frequently encountered.