Department of Pathology, Daping Hospital, Army Medical University, Chongqing, 400042, People's Republic of China.
College of Computer and Cyber Security, Chengdu University of Technology, Chengdu, 610059, People's Republic of China.
J Cancer Res Clin Oncol. 2023 Sep;149(11):8581-8592. doi: 10.1007/s00432-023-04795-y. Epub 2023 Apr 25.
The classification of primary lung adenocarcinoma is complex and varied. Different subtypes of lung adenocarcinoma have different treatment methods and different prognosis. In this study, we collected 11 datasets comprising subtypes of lung cancer and proposed FL-STNet model to provide the assistance for improving clinical problems of pathologic classification in primary adenocarcinoma of lung.
Samples were collected from 360 patients diagnosed with lung adenocarcinoma and other subtypes of lung diseases. In addition, an auxiliary diagnosis algorithm based on Swin-Transformer, which used Focal Loss for function in training, was developed. Meanwhile, the diagnostic accuracy of the Swin-Transformer was compared to pathologists.
The Swin-Transformer captures not only information in the overall tissue structure but also the local tissue details in the images of lung cancer pathology. Furthermore, training FL-STNet with the Focal Loss function can further balance the difference in the amount of data between different subtypes, improving recognition accuracy. The average classification accuracy, F1, and AUC of the proposed FL-STNet reached 85.71%, 86.57%, and 0.9903. The average accuracy of the FL-STNet was higher by 17% and 34%, respectively, than in the senior pathologist and junior pathologist group.
The first deep learning based on an 11-category classifier was developed for classifying lung adenocarcinoma subtypes based on WSI histopathology. Aiming at the deficiencies of the current CNN and Vit, FL-STNet model is proposed in this study by introducing Focal Loss and combining the advantages of Swin-Transformer model.
原发性肺腺癌的分类复杂多样。不同亚型的肺腺癌有不同的治疗方法和不同的预后。本研究收集了 11 个数据集，包括肺癌亚型，并提出了 FL-STNet 模型，为提高原发性肺腺癌病理分类的临床问题提供帮助。
从 360 名被诊断为肺腺癌和其他类型肺病的患者中收集样本。此外，还开发了一种基于 Swin-Transformer 的辅助诊断算法，该算法在训练中使用焦点损失作为功能。同时，将 Swin-Transformer 的诊断准确性与病理学家进行了比较。
Swin-Transformer 不仅可以捕捉到整个组织结构中的信息，还可以捕捉到肺癌病理学图像中的局部组织细节。此外，使用焦点损失函数训练 FL-STNet 可以进一步平衡不同亚型之间数据量的差异，提高识别准确率。所提出的 FL-STNet 的平均分类准确率、F1 和 AUC 分别达到 85.71%、86.57%和 0.9903。FL-STNet 的平均准确率比高级病理学家和初级病理学家组分别高出 17%和 34%。
本研究首次开发了一种基于 11 类分类器的深度学习方法，用于基于 WSI 组织病理学对肺腺癌亚型进行分类。针对目前 CNN 和 Vit 的不足，本研究提出了 FL-STNet 模型，通过引入焦点损失并结合 Swin-Transformer 模型的优势，提出了 FL-STNet 模型。
