Add Streamlit deployment link to model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- medical
|
| 5 |
+
- vision
|
| 6 |
+
- image-classification
|
| 7 |
+
- pytorch
|
| 8 |
+
- skin-cancer
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# DermaVision: Skin Lesion Analysis 🩺
|
| 12 |
+
|
| 13 |
+
🔥 **Live Interactive Demo:** [Click here to try the DermaVision App](https://share.streamlit.io/) *(Hosted on Streamlit Community Cloud)*
|
| 14 |
+
|
| 15 |
+
DermaVision is an EfficientNetV2-S model fine-tuned on the HAM10000 dataset to classify dermoscopic images into 7 skin lesion categories.
|
| 16 |
+
|
| 17 |
+
### Model Details
|
| 18 |
+
- **Architecture:** EfficientNetV2-S
|
| 19 |
+
- **Task:** Multi-class Image Classification
|
| 20 |
+
- **Dataset:** HAM10000
|
| 21 |
+
- **Target AUC-ROC:** > 0.90
|
| 22 |
+
|
| 23 |
+
### Code & Repository
|
| 24 |
+
The full source code, including the FastAPI backend and Streamlit dashboard, is available on GitHub: [farazmalik180/DermaVision](https://github.com/farazmalik180/DermaVision)
|
| 25 |
+
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
### Warning / Medical Disclaimer
|
| 29 |
+
DermaVision is a research project and academic demonstration. It is NOT a certified medical device and should NOT be used as a substitute for professional dermatological diagnosis. Always consult a board-certified dermatologist for any skin concern.
|