https://scholars.lib.ntu.edu.tw/handle/123456789/607536
標題: | Prediction of Breast Cancer Recurrence Using a Deep Convolutional Neural Network Without Region-of-Interest Labeling | 作者: | Phan N.N Hsu C.-Y Huang C.-C Tseng L.-M ERIC YAO-YU CHUANG |
關鍵字: | 70-gene signature;deep learning;label-free;pathology;transfer learning;whole slide image;epidermal growth factor receptor;estrogen receptor;progesterone receptor;accuracy;adult;area under the curve;Article;breast cancer;cancer recurrence;cancer staging;convolutional neural network;feasibility study;female;genetic screening;genetic susceptibility;human;human tissue;image segmentation;major clinical study;middle aged;patch dynamics;recall;sensitivity and specificity;transfer of learning | 公開日期: | 2021 | 卷: | 11 | 來源出版物: | Frontiers in Oncology | 摘要: | Purpose: The present study aimed to assign a risk score for breast cancer recurrence based on pathological whole slide images (WSIs) using a deep learning model. Methods: A total of 233 WSIs from 138 breast cancer patients were assigned either a low-risk or a high-risk score based on a 70-gene signature. These images were processed into patches of 512x512 pixels by the PyHIST tool and underwent color normalization using the Macenko method. Afterward, out of focus and pixelated patches were removed using the Laplacian algorithm. Finally, the remaining patches (n=294,562) were split into 3 parts for model training (50%), validation (7%) and testing (43%). We used 6 pretrained models for transfer learning and evaluated their performance using accuracy, precision, recall, F1 score, confusion matrix, and AUC. Additionally, to demonstrate the robustness of the final model and its generalization capacity, the testing set was used for model evaluation. Finally, the GRAD-CAM algorithm was used for model visualization. Results: Six models, namely VGG16, ResNet50, ResNet101, Inception_ResNet, EfficientB5, and Xception, achieved high performance in the validation set with an overall accuracy of 0.84, 0.85, 0.83, 0.84, 0.87, and 0.91, respectively. We selected Xception for assessment of the testing set, and this model achieved an overall accuracy of 0.87 with a patch-wise approach and 0.90 and 1.00 with a patient-wise approach for high-risk and low-risk groups, respectively. Conclusions: Our study demonstrated the feasibility and high performance of artificial intelligence models trained without region-of-interest labeling for predicting cancer recurrence based on a 70-gene signature risk score. Copyright ? 2021 Phan, Hsu, Huang, Tseng and Chuang. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118662498&doi=10.3389%2ffonc.2021.734015&partnerID=40&md5=b533bbbf706a7c671639b39597a04f24 https://scholars.lib.ntu.edu.tw/handle/123456789/607536 |
ISSN: | 2234943X | DOI: | 10.3389/fonc.2021.734015 |
顯示於: | 生醫電子與資訊學研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。