Reducing Histopathology Slide Magnification Improves the Accuracy and Speed of Ovarian Cancer Subtyping

Artificial intelligence has found increasing use for ovarian cancer histological subtyping, but the optimal slide magnification for computational interpretation is unclear. Higher magnifications offer abundant cytological information, whereas lower magnifications give a broader histoarchitectural overview. Using attention-based multiple instance learning, we performed the most extensive analysis of ovarian cancer tissue magnifications to date, with data at six magnifications subjected to the same preprocessing, hyperparameter tuning, and validation procedures. The lowest magnifications (1.25x and 2.5x) performed best in cross-validation, and intermediate magnifications (5x and 10x) performed best in hold-out testing (62% and 61% accuracy, respectively). Lower magnification models ran significantly faster, with the 5x model taking 5% as long in training and 31% as long in inference compared to 40x. This indicates that the standard usage of high magnifications for computational subtyping may be unnecessary, with lower magnifications offering faster, more accurate alternatives.