E2EFP-MIL: End-to-end and high-generalizability weakly supervised deep convolutional network for lung cancer classification from whole slide image
E2EFP-MIL: End-to-end and high-generalizability weakly supervised deep convolutional network for lung cancer classification from whole slide image
复制标题
DOI：
10.1016/j.media.2023.102837
复制
发表时间：
2023-05-20
影响因子：
10.9
通讯作者：
Hou, Yan
中科院分区：
文献类型：
--
作者：
Cao, Lei;Wang, Jie;Hou, Yan
有效、准确地区分肺癌的组织病理学亚型是个体化治疗的关键。到目前为止，人工智能技术已经开发出来，但其性能在更异构的数据上仍然存在争议，阻碍了其临床部署。在这里，我们提出了一种端到端的、通用性好的、数据高效的、基于弱监督的深度学习方法。该方法，端到端的特征金字塔深度多示例学习模型（E2 EFP-MIL），包含一个迭代采样模块，一个可训练的特征金字塔模块和一个鲁棒的特征聚合模块。E2 EFP-MIL使用端到端学习来自动提取广义形态特征并识别有区别的组织形态学模式。该方法使用来自TCGA的1007个肺癌全载玻片图像（WSI）进行训练，测试集中AUC为0.95-0.97。我们在5个真实世界的外部异质性队列中验证了E2 EFP-MIL，包括来自美国和中国的近1600个WSI，AUC为0.94-0.97，并发现100-200个训练图像足以实现>0.9的AUC。E2 EFP-MIL的性能优于多种基于MIL的最先进方法，具有高精度和低硬件要求。优异和稳健的结果证明了E2 EFP-MIL在临床实践中的普遍性和有效性。我们的代码可在https://github.com/raycaohmu/E2EFP-MIL上获得。
Efficient and accurate distinction of histopathological subtype of lung cancer is quite critical for the indi-vidualized treatment. So far, artificial intelligence techniques have been developed, whose performance yet remained debatable on more heterogenous data, hindering their clinical deployment. Here, we propose an end-to-end, well-generalized and data-efficient weakly supervised deep learning-based method. The method, end-to-end feature pyramid deep multi-instance learning model (E2EFP-MIL), contains an iterative sampling module, a trainable feature pyramid module and a robust feature aggregation module. E2EFP-MIL uses end-to-end learning to extract generalized morphological features automatically and identify discriminative histomorphological patterns. This method is trained with 1007 whole slide images (WSIs) of lung cancer from TCGA, with AUCs of 0.95-0.97 in test sets. We validated E2EFP-MIL in 5 real-world external heterogenous cohorts including nearly 1600 WSIs from both United States and China with AUCs of 0.94-0.97, and found that 100-200 training images are enough to achieve an AUC of >0.9. E2EFP-MIL overperforms multiple state-of-the-art MIL-based methods with high accuracy and low hardware requirements. Excellent and robust results prove generalizability and effectiveness of E2EFP-MIL in clinical practice. Our code is available at https://github.com/raycaohmu/E2EFP-MIL.