Pneumonia Diagnosis through pixels -- A Deep Learning Model for detection and classification

Manual identification and classification of pneumonia and COVID-19 infection is a cumbersome process that, if delayed can cause irreversible damage to the patient. We have compiled CT scan images from various sources, namely, from the China Consortium of Chest CT Image Investigation (CC-CCII), the Negin Radiology located at Sari in Iran, an open access COVID-19 repository from Havard dataverse, and Sri Ramachandra University, Chennai, India. The images were preprocessed using various methods such as normalization, sharpening, median filter application, binarizing, and cropping to ensure uniformity while training the models. We present an ensemble classification approach using deep learning and machine learning methods to classify patients with the said diseases. Our ensemble model uses pre-trained networks such as ResNet-18 and ResNet-50 for classification and MobileNetV2 for feature extraction. The features from MobileNetV2 are used by the gradient-boosting classifier for the classification of patients. Using ResNet-18, ResNet-50, and the MobileNetV2 aided gradient boosting classifier, we propose an ensemble model with an accuracy of 98 percent on unseen data.

MIST GAN: Modality Imputation Using Style Transfer for MRI

MRI entails a great amount of cost, time and effort for the generation of all the modalities that are recommended for efficient diagnosis and treatment planning. Recent advancements in deep learning research show that generative models have achieved substantial improvement in the aspects of style transfer and image synthesis. In this work, we formulate generating the missing MR modality from existing MR modalities as an imputation problem using style transfer. With a multiple-to-one mapping, we model a network that accommodates domain specific styles in generating the target image. We analyse the style diversity both within and across MR modalities. Our model is tested on the BraTS'18 dataset and the results obtained are observed to be on par with the state-of-the-art in terms of visual metrics, SSIM and PSNR. After being evaluated by two expert radiologists, we show that our model is efficient, extendable, and suitable for clinical applications.