Commit History
-
Create preprocessor_config.json
Verified signaturefor compatibilitybdb205b -
Update README.md
Verified signatureUpdate metadata to enable download trackingbf56aca -
Update config.json
Verified signatureupdating confige51f1bc -
Create model_index.json
Verified signaturemodel_index.json creation53256cd -
Adding `safetensors` variant of this model (#1)
Verified signature- Adding `safetensors` variant of this model (c48421dd216a365f37de3f21565f9c2848408fe2) Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>0b906a9 -
Update config.json
Verified signatureupdating config22529ad -
Rename EfficientNet_B0_best_93.44.pth to pytorch_model.bin
Verified signaturerenaming EfficientNet_B0_best_93.44.pth6e24260 -
Create config.json
Verified signatureAdd minimal config.json9c3d959
-
Update README.md
Verified signaturea59da1e -
Update README.md
Verified signature9e436f1 -
Create README.md
Verified signature⚠️ Bias, Risks, and Limitations 🚧 Potential Biases Trained primarily on US-based patient data May not generalize well to different demographics & imaging techniques Model confidence does not equal correctness 🚑 Limitations Not a diagnostic tool: AI cannot replace radiologists Best suited for frontal X-rays (not lateral) Cannot detect rare conditions not in the dataset ✅ Recommendations Always consult a radiologist for diagnosis. Fine-tune the model on regional hospital data if needed. Use ensemble learning for higher accuracy. 📖 Training Details Dataset 1: NIH Chest X-ray Dataset (~100,000 images) Dataset 2: NLMCXR Dataset (Radiology Reports + X-ray images) Loss Function: Cross-Entropy Loss Optimizer: Adam with Learning Rate Scheduling Batch Size: 32 Epochs: 20 Hardware Used: NVIDIA V100 GPU (AWS Cloud) 📊 Evaluation Metrics AUROC (Area Under Receiver Operating Curve) Precision / Recall F1 Score …564280d -
Upload EfficientNet_B0_best_93.44.pth
Verified signature# 🩺 AI-Powered Chest X-ray Analysis Model-Rayz ## 🌟 **Overview** This model is designed to **analyze chest X-rays and detect potential lung conditions** using **EfficientNet_B0**. It was trained on the **NIH Chest X-ray Dataset** and **NLMCXR Dataset** to provide **multi-class classification across 14 conditions**. This model was developed to **bridge the gap in accessibility** for those awaiting X-ray reports, helping provide **fast, AI-powered insights** while awaiting a professional diagnosis. --- ## 🏗 **Model Details** - **Model Architecture**: `EfficientNet_B0` - **Training Data**: `NIH Chest X-ray Dataset`, `NLMCXR Dataset` - **Classes**: - **14 lung conditions detected**, including: - Atelectasis, Cardiomegaly, Consolidation, Edema, Effusion, Emphysema, Fibrosis, Hernia, Infiltration, Mass, Nodule, Pleural Thickening, Pneumonia, Pneumothorax, and "No Finding" for normal scans. - **Optimization**: - Model optimized with **pruning**, **quantization**, and **TensorRT…2b2e13e -
initial commit
Verified signature4c40ad0