A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images

• Published in: Computer methods and programs in biomedicine Vol. 140; pp. 283 - 293
• Main Authors: Pang, Shuchao, Yu, Zhezhou, Orgun, Mehmet A.
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.03.2017
• Subjects: Biomedical image classification; Convolutional neural network; Data augmentation; Deep learning; Diagnostic Imaging; Internal Medicine; Machine Learning; Models, Theoretical; Neural Networks (Computer); Other; Transfer learning; Deep learning; Data augmentation; Biomedical image classification; Transfer learning; Convolutional neural network

•An end-to-end classifier for biomedical images is proposed based on deep CNN with a highly stable and precise accuracy rate.•Transfer learning technology reduces feature learning time and boosts the classification ability for biomedical applications.•We show how to train a domain transferred deep c...