Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,26 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- medical
|
| 5 |
+
- cnn
|
| 6 |
+
- dermatology
|
| 7 |
+
- melanoma
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# simpleNet: Skin Lesion Classification (Benign vs Malignant)
|
| 11 |
+
|
| 12 |
+
**simpleNet** is a lightweight Convolutional Neural Network (CNN) model for binary skin lesion classification, distinguishing between **benign** and **malignant (melanoma)** cases.
|
| 13 |
+
|
| 14 |
+
## Model Description
|
| 15 |
+
- Architecture: Custom CNN with 3 convolutional blocks and regularization (Batch Normalization, Dropout, L2).
|
| 16 |
+
- Input size: **224 × 224 × 3 RGB images**.
|
| 17 |
+
- Output: 2 classes → `["benign", "malignant"]`.
|
| 18 |
+
- Trained on a combination of curated skin lesion datasets, including **ISIC** samples.
|
| 19 |
+
|
| 20 |
+
The model is optimized for **generalization** and has been validated with external images, showing robust performance for melanoma detection.
|
| 21 |
+
|
| 22 |
+
## Intended Use
|
| 23 |
+
- **Educational and research purposes**.
|
| 24 |
+
- Demonstrating the potential of CNNs for medical imaging.
|
| 25 |
+
- Not intended for clinical use without further validation and regulatory approval.
|
| 26 |
+
|