{Soumava Paul Ramanathan Sethuraman Ekagra Ranjan Siddharth Kapoor Debdoot Sheet Aupendu Kar}

Abstract

Deep learning models trained in natural images are commonly used for different classification tasks in the medical domain. Generally, very high dimensional medical images are down-sampled by us- ing interpolation techniques before feeding them to deep learning models that are ImageNet compliant and accept only low-resolution images of size 224 × 224 px. This popular technique may lead to the loss of key information thus hampering the classification. Signifi- cant pathological features in medical images typically being small sized and highly affected. To combat this problem, we introduce a convolutional neural network (CNN) based classification approach which learns to reduce the resolution of the image using an autoen- coder and at the same time classify it using another network, while both the tasks are trained jointly. This algorithm guides the model to learn essential representations from high-resolution images for classification along with reconstruction. We have used the publicly available dataset of chest x-rays to evaluate this approach and have outperformed state-of-the-art on test data. Besides, we have experi- mented with the effects of different augmentation approaches in this dataset and report baselines using some well known ImageNet class of CNNs.