results: 研究发现，最低的缩放大小（1.25x和2.5x）在十分之一验证中表现最好，而中间的缩放大小（5x和10x）在保留测试中表现最好（准确率为62%和61%）。此外，使用较低的缩放大小可以更快速地训练和评估卵巢癌病型。Abstract
Artificial intelligence has found increasing use for ovarian cancer morphological subtyping from histopathology slides, but the optimal 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, cross-validation and hold-out testing 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 were also significantly faster, with the 5x model taking 5% as long to train and 31% as long to evaluate slides compared to 40x. This indicates that the standard usage of high magnifications for computational ovarian cancer subtyping may be unnecessary, with lower magnifications giving faster, more accurate alternatives.
摘要