An annotation-free whole-slide training approach to pathological classification of lung cancer types using deep learning.
An annotation-free whole-slide training approach to pathological classification of lung cancer types using deep learning.
复制标题
使用深度学习对肺癌类型进行病理分类的无注释全幻灯片训练方法。
DOI：
10.1038/s41467-021-21467-y
复制
发表时间：
2021-02-19
影响因子：
16.6
通讯作者：
Chen CY
中科院分区：
文献类型：
--
作者：
Chen CL;Chen CC;Yu WH;Chen SH;Chang YC;Hsu TI;Hsiao M;Yeh CY;Chen CY
数字病理学的深度学习受到全切片图像（WSIs）极高空间分辨率的阻碍。大多数研究都采用基于块的方法，这往往需要详细的注释图像块。这通常涉及在WSI上费力的徒手轮廓绘制。为了减轻这种轮廓的负担，并从大量WSI的扩展训练中获得好处，我们开发了一种方法，仅使用幻灯片级诊断在整个WSI上训练神经网络。我们的方法利用统一的内存机制来克服计算加速器的内存约束。在9662个肺癌WSI数据集上进行的实验表明，该方法在测试集上分别实现了腺癌和鳞癌分类的受试者工作特征曲线下的面积为0.9594和0.9414。此外，该方法表现出更高的分类性能比多实例学习，以及强大的定位结果的小病变，通过类激活映射。数字病理学的深度学习受到整个切片图像（WSIs）的极高空间分辨率的阻碍，这需要研究人员采用基于块的方法和费力的徒手轮廓绘制。在这里，作者开发了一种全幻灯片训练方法，使用深度学习的幻灯片级诊断对肺癌类型进行分类。
Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole-slide images (WSIs). Most studies have employed patch-based methods, which often require detailed annotation of image patches. This typically involves laborious free-hand contouring on WSIs. To alleviate the burden of such contouring and obtain benefits from scaling up training with numerous WSIs, we develop a method for training neural networks on entire WSIs using only slide-level diagnoses. Our method leverages the unified memory mechanism to overcome the memory constraint of compute accelerators. Experiments conducted on a data set of 9662 lung cancer WSIs reveal that the proposed method achieves areas under the receiver operating characteristic curve of 0.9594 and 0.9414 for adenocarcinoma and squamous cell carcinoma classification on the testing set, respectively. Furthermore, the method demonstrates higher classification performance than multiple-instance learning as well as strong localization results for small lesions through class activation mapping. Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole slide images (WSIs), which requires researchers to adopt patch-based methods and laborious free-hand contouring. Here, the authors develop a whole-slide training method to classify types of lung cancers using slide-level diagnoses with deep learning.
登录
查看更多内容
DOI：
10.1109/tpami.2020.3019563
发表时间：
2022-03-01
影响因子：
23.6
作者：
Pinckaers, Hans;van Ginneken, Bram;Litjens, Geert
通讯作者：
Litjens, Geert
影响因子：
5.2
作者：
Chuang, Wen-Yu;Chang, Shang-Hung;Yeh, Chao-Yuan
通讯作者：
Yeh, Chao-Yuan
DOI：
10.1073/pnas.1717139115
发表时间：
2018-03-27
影响因子：
11.1
作者：
Mobadersany P;Yousefi S;Amgad M;Gutman DA;Barnholtz-Sloan JS;Velázquez Vega JE;Brat DJ;Cooper LAD
通讯作者：
Cooper LAD
通过卷积神经网络进行低剂量 CT
影响因子：
3.4
作者：
Chen, Hu;Zhang, Yi;Wang, Ge
通讯作者：
Wang, Ge
影响因子：
120.7
作者：
Bejnordi, Babak Ehteshami;Veta, Mitko;van der Laak, Jeroen A. W. M.
通讯作者：
van der Laak, Jeroen A. W. M.