Deep Domain Adversarial Learning for Species- Agnostic Classification of Histologic Subtypes of Osteosarcoma

Osteosarcomas (OSs) are aggressive bone tumors with many divergent histologic patterns. During pa-thology review, OSs are subtyped based on the predominant histologic pattern; however, tumors often demonstrate multiple patterns. This high tumor heterogeneity coupled with scarcity of samples compared with other tumor types render histology-based prognosis of OSs challenging. To combat lower case numbers in humans, dogs with spontaneous OSs have been suggested as a model species. Herein, a convolutional neural network was adversarially trained to classify distinct histologic patterns of OS in humans using mostly canine OS data during training. Adversarial training improved domain adaption of a histologic subtype classifier from canines to humans, achieving an average multiclass F1 score of 0.77 (95% CI, 0.74-0.79) and 0.80 (95% CI, 0.78-0.81) when compared with the ground truth in canines and humans, respectively. Finally, this trained model, when used to characterize the histologic land-scape of 306 canine OSs, uncovered distinct clusters with markedly different clinical responses to standard-of-care therapy. (Am J Pathol 2023, 193: 60-72; https://doi.org/10.1016/ j.ajpath.2022.09.009)