E2EFP-MIL: End-to-end and high-generalizability weakly supervised deep convolutional network for lung cancer classification from whole slide image

• Published in: Medical image analysis 2023-08, Vol.88, p.102837-102837, Article 102837
• Main Authors: Cao, Lei, Wang, Jie, Zhang, Yuanyuan, Rong, Zhiwei, Wang, Meng, Wang, Liuying, Ji, Jianxin, Qian, Youhui, Zhang, Liuchao, Wu, Hao, Song, Jiali, Liu, Zheng, Wang, Wenjie, Li, Shuang, Wang, Peiyu, Xu, Zhenyi, Zhang, Jingyuan, Zhao, Liang, Wang, Hang, Sun, Mengting, Huang, Xing, Yin, Rong, Lu, Yuhong, Liu, Ziqian, Deng, Kui, Wang, Gongwei, Qiu, Mantang, Li, Kang, Wang, Jun, Hou, Yan
• Format: Article
• Language: English
• Subjects: Area Under Curve; Artificial Intelligence; China; Classification; Computational pathology; Convolutional neural network; Deep learning; Humans; Lung cancer; Lung Neoplasms - diagnostic imaging; Neural Networks, Computer; Subtype diagnosis; Weakly supervised learning
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2023.102837

Efficient and accurate distinction of histopathological subtype of lung cancer is quite critical for the individualized 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. [Display omitted] •A novel end-to-end and highly-generalized weakly supervised deep learning method to aid in lung cancer subtype diagnosis.•Patch sampling module and feature aggregation module to learn features more effectively and comprehensively.•Data efficient, 100 to 200 slides instead of thousands of ones is enough obtain test AUCs of >0.9.•International, multicentre evaluation showing a promising generalizability on more heterogenous real-world data.•Results better than the other deep learning methods in the identification of lung cancer subtypes.