fix: gradio 4.44.1 + correct model info in README (cache bust)

README.md

@@ -7,7 +7,7 @@ sdk: gradio
 sdk_version: 4.44.1
 app_file: app.py
 pinned: false
-license: mit
+license: apache-2.0
 ---
 
 # Angio AI — Coronary Angiography Analysis System
@@ -26,7 +26,7 @@ Upload a coronary X-ray angiography (XCA) video and the pipeline automatically:
 | 1 | Keyframe extraction | Best diagnostic frame (contrast × sharpness score) |
 | 2 | Mask2Former | Stenosis detection — bounding boxes + instance masks |
 | 3a | ResUNet | Binary vessel mask (Dice 0.8015 on ARCADE) |
-| 3b | nnUNet | 26-class coronary anatomy segmentation |
+| 3b | YOLOv8m-seg | 26-class coronary anatomy segmentation |
 | 4 | FFR Pipeline v4 | Quantitative Flow Ratio (QFR) estimation |
 | 5 | SYNTAX Score | Lesion complexity scoring |
 
@@ -36,11 +36,11 @@ Upload a coronary X-ray angiography (XCA) video and the pipeline automatically:
 
 All checkpoints are stored in [`MuhammadAdil63/angio-ai-checkpoints`](https://huggingface.co/MuhammadAdil63/angio-ai-checkpoints) and downloaded automatically on first run.
 
-| File | Architecture | Task | Dice / mAP |
-|------|-------------|------|-----------|
+| File | Architecture | Task | Performance |
+|------|-------------|------|------------|
 | `mask2former_best.pth` | Mask2Former Swin-Base | Stenosis detection | — |
-| `binary_best.pth` | ResUNet (16→256 ch) | Binary vessel seg | 0.8015 |
-| `best.pt` | nnUNet nc=26 | 26-class anatomy seg | — |
+| `binary_best.pth` | ResUNet (16→256 ch) | Binary vessel segmentation | Dice 0.8015 |
+| `best.pt` | YOLOv8m-seg (nc=26) | 26-class coronary anatomy | — |
 
 Dataset: [ARCADE Challenge](https://arcade.grand-challenge.org/) (syntax + stenosis splits)