Jun Wang1, Qianying Liu2, Haotian Xie3, Zhaogang Yang4, Hefeng Zhou1. 1. Department of Informatics, King's College London, London WC2R 2LS, UK. 2. College of Management, Shenzhen University, Shenzhen 518060, China. 3. Department of Mathematics, The Ohio State University, Columbus, OH 43210, USA. 4. Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
Abstract
(1) Purpose: To improve the capability of EfficientNet, including developing a cropping method called Random Center Cropping (RCC) to retain the original image resolution and significant features on the images' center area, reducing the downsampling scale of EfficientNet to facilitate the small resolution images of RPCam datasets, and integrating attention and Feature Fusion (FF) mechanisms with EfficientNet to obtain features containing rich semantic information. (2) Methods: We adopt the Convolutional Neural Network (CNN) to detect and classify lymph node metastasis in breast cancer. (3) Results: Experiments illustrate that our methods significantly boost performance of basic CNN architectures, where the best-performed method achieves an accuracy of 97.96% ± 0.03% and an Area Under the Curve (AUC) of 99.68% ± 0.01% on RPCam datasets, respectively. (4) Conclusions: (1) To our limited knowledge, we are the only study to explore the power of EfficientNet on Metastatic Breast Cancer (MBC) classification, and elaborate experiments are conducted to compare the performance of EfficientNet with other state-of-the-art CNN models. It might provide inspiration for researchers who are interested in image-based diagnosis using Deep Learning (DL). (2) We design a novel data augmentation method named RCC to promote the data enrichment of small resolution datasets. (3) All of our four technological improvements boost the performance of the original EfficientNet.
(1) Purpose: To improve the capability of EfficientNet, including developing a cropping method called Random Center Cropping (RCC) to retain the original image resolution and significant features on the images' center area, reducing the downsampling scale of EfficientNet to facilitate the small resolution images of RPCam datasets, and integrating attention and Feature Fusion (FF) mechanisms with EfficientNet to obtain features containing rich semantic information. (2) Methods: We adopt the Convolutional Neural Network (CNN) to detect and classify lymph node metastasis in breast cancer. (3) Results: Experiments illustrate that our methods significantly boost performance of basic CNN architectures, where the best-performed method achieves an accuracy of 97.96% ± 0.03% and an Area Under the Curve (AUC) of 99.68% ± 0.01% on RPCam datasets, respectively. (4) Conclusions: (1) To our limited knowledge, we are the only study to explore the power of EfficientNet on Metastatic Breast Cancer (MBC) classification, and elaborate experiments are conducted to compare the performance of EfficientNet with other state-of-the-art CNN models. It might provide inspiration for researchers who are interested in image-based diagnosis using Deep Learning (DL). (2) We design a novel data augmentation method named RCC to promote the data enrichment of small resolution datasets. (3) All of our four technological improvements boost the performance of the original EfficientNet.
Entities:
Keywords:
CNN; diagnosis; feature fusion; image classification; metastatic breast cancer
Authors: Armando E Giuliano; Karla V Ballman; Linda McCall; Peter D Beitsch; Meghan B Brennan; Pond R Kelemen; David W Ollila; Nora M Hansen; Pat W Whitworth; Peter W Blumencranz; A Marilyn Leitch; Sukamal Saha; Kelly K Hunt; Monica Morrow Journal: JAMA Date: 2017-09-12 Impact factor: 56.272
Authors: Mark Kriegsmann; Katharina Kriegsmann; Georg Steinbuss; Christiane Zgorzelski; Anne Kraft; Matthias M Gaida Journal: Int J Mol Sci Date: 2021-05-20 Impact factor: 5.923