Detection and localization of COVID-19 on chest X-rays

BSc Project

The preparation for the Lung X-Ray Mask Segmentation project included the use of augmentation methods like flipping to improve the dataset, along with measures to ensure data uniformity and quality. The model architecture was explored with two types of ResNets: the traditional CNN layers and Depthwise Separable.

Official repository of ICML 2023 paper: Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat

Implementation of the paper "CXR-IRGen: An Integrated Vision and Language Model for the Generation of Clinically Accurate Chest X-Ray Image-Report Pairs" (WACV 2024)

Learning to Generalize towards Unseen Domains via a Content-Aware Style Invariant Framework for Disease Detection from Chest X-rays

Pruning and fine-tuning for debiasing an already-trained neural network with applications to deep chest X-ray classifiers

The best single model performance on the CheXpert chest X-ray classification competition

COVID-19 Detection Chest X-rays and CT scans: COVID-19 Detection based on Chest X-rays and CT Scans using four Transfer Learning algorithms: VGG16, ResNet50, InceptionV3, Xception. The models were trained for 500 epochs on around 1000 Chest X-rays and around 750 CT Scan images on Google Colab GPU. A Flask App was later developed wherein user can…

Enhancing Visual Learning for Limited Data in Disease Diagnosis: Leveraging the power of vision transformers to learn useful features and using them with a custom classifier

An implementation of pix2pix GAN to improve Xray image quality

Flexible federated learning enables institutions to jointly train deep learning models even when data is non-uniformly labeled. The resulting models are superior to models which are trained with conventional methods.

Detecting Shortcuts in Medical Images - A Case Study in Chest X-rays - ISBI 2023

Repository for the paper "Exploring Image Augmentations for Siamese Representation Learning with Chest X-Rays"

This is the implementation of the CDGPT2 model mentioned in our paper 'Automated Radiology Report Generation using Conditioned Transformers'

Official Code for GazeGNN: A Gaze-guided Graph Neural Network for Chest X-ray Classification [WACV 2024]

Automatically split the chest x-ray into two views

Code for the paper "When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations"