This paper proposes a novel deep neural network architecture to effectively localize potential biomarkers in medical images, when only the image-level labels are available during model training. The proposed architecture combines an encoder-decoder, a CNN classifier, and a generative adversarial network (GAN) in a novel way, such that the CNN classifier and the discriminator in the GAN can respectively pull
and push
potential biomarkers out from original images, and therefore can help the encoder-decoder more effectively remove biomarkers. Biomarkers in abnormal images can then be easily localized and segmented by subtracting the output of the encoder-decoder from its original input. The proposed approach was evaluated on diabetic retinopathy images with real biomarkers and on skin images with simulated biomarkers, showing state-of-the-art performance in localizing biomarkers even if biomarkers are irregularly scattered and are of various sizes.
lightwisemax / diabetic-retinopathy-pytorch Goto Github PK
View Code? Open in Web Editor NEWbiomarker detection on diatetic retinopathy
License: Apache License 2.0