Breen Jack, Allen Katie, Zucker Kieran, Godson Lucy, Orsi Nicolas M, Ravikumar Nishant
Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), School of Computing, University of Leeds, Leeds, UK.
Leeds Institute of Medical Research at St James's, School of Medicine, University of Leeds, Leeds, UK.
NPJ Precis Oncol. 2025 Jan 30;9(1):33. doi: 10.1038/s41698-025-00799-8.
Histopathology foundation models show great promise across many tasks, but analyses have been limited by arbitrary hyperparameters. We report the most rigorous single-task validation study to date, specifically in the context of ovarian carcinoma morphological subtyping. Attention-based multiple instance learning classifiers were compared using three ImageNet-pretrained encoders and fourteen foundation models, each trained with 1864 whole slide images and validated through hold-out testing and two external validations (the Transcanadian Study and OCEAN Challenge). The best-performing classifier used the H-optimus-0 foundation model, with balanced accuracies of 89%, 97%, and 74%, though UNI achieved similar results at a quarter of the computational cost. Hyperparameter tuning the classifiers improved performance by a median 1.9% balanced accuracy, with many improvements being statistically significant. Foundation models improve classification performance and may allow for clinical utility, with models providing a second opinion in challenging cases and potentially improving the accuracy and efficiency of diagnoses.
组织病理学基础模型在许多任务中显示出巨大的前景，但分析受到任意超参数的限制。我们报告了迄今为止最严格的单任务验证研究，特别是在卵巢癌形态学亚型分类的背景下。使用三个在ImageNet上预训练的编码器和14个基础模型对基于注意力的多实例学习分类器进行了比较，每个模型都使用1864张全切片图像进行训练，并通过留出测试和两次外部验证（加拿大横断面研究和海洋挑战）进行验证。性能最佳的分类器使用H-optimus-0基础模型，平衡准确率分别为89%、97%和74%，不过UNI以四分之一的计算成本取得了类似的结果。对分类器进行超参数调整使平衡准确率中位数提高了1.9%，许多改进具有统计学意义。基础模型提高了分类性能，并可能具有临床实用性，这些模型可在具有挑战性的病例中提供第二种意见，并有可能提高诊断的准确性和效率。
