MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025

COVID-19 Detection Using Chest X-Ray

[DALI 2022] "Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study" by Gregory Holste, Song Wang, Ziyu Jiang, Thomas C. Shen, Ronald M. Summers, Yifan Peng, and Zhangyang Wang

🫁 Chest X-ray abnormalities localization via ensemble of deep convolutional neural networks

State-of-the-Art Pneumonia detection from chest X-rays system using EfficientNetV2 + FPN + Faster R-CNN. Features Focal Loss, Weighted Box Fusion, Mosaic Augmentation & StratifiedGroupKFold. Built for RSNA Pneumonia Detection Challenge. Achieves competitive mAP with mixed-precision training.

Deep learning model for pneumonia detection in chest X-rays using TensorFlow and Streamlit

[MICCAI 2023] "How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?" by Gregory Holste et al.

Securing Collaborative Medical AI by Using Differential Privacy

Ethnic bias analysis in medical imaging AI: Demonstrating that explainable-by-design models achieve 80% bias reduction across 5 ethnic groups (50k images)

COVID-19 Detection Using CXR and Attention Guided CNN

Chest X-ray screening research with explicit distribution shift evaluation, per-disease binary models and validated Grad-CAM localization.

Official implementation of Set Prediction in the Latent Space (LSP)

Building an AI model for chest X-ray under patient privacy guarantees

[EMNLP 2025 Main] CREPE: Rapid Chest X-ray Report Evaluation by Predicting Multi-category Error Counts

Deep learning model for X-ray image analysis and medical condition detection using CNN-based image classification and health assessment.

MobileNetV2 pneumonia classifier validated on an independent 485-sample cross-operator cohort. 96.4% sensitivity, 96.4% ROC-AUC, bootstrap p=0.978. FastAPI inference API, Streamlit dashboard, DICOM support, Docker-ready

Keras implementation of different types of Generative Adversarial Networks (GANs)

2026. Deep learning-based chest X-ray reading assistance research prototype with DenseNet121 classification and Grad-CAM explainability.

Reproducible deep learning pipeline for multi-label thoracic disease detection using the NIH ChestX-ray14 dataset. Evaluates ResNet and DenseNet CNN architectures with patient-level splits, clinical performance metrics (ROC-AUC, sensitivity, specificity), and Grad-CAM visualizations for interpretable localization of radiographic pathology features.

Detecting presence of COVID-19 from Chest X-ray scans using CNN and Class Activation Maps