https://github.com/bsenst/capstone1-skin-lesion-classifier

Experimental neural network to classify skin lesions from the HAM10k collection.
https://github.com/bsenst/capstone1-skin-lesion-classifier

neural-network python3 skin-lesion-classification xception-model

Last synced: about 1 month ago
JSON representation

Experimental neural network to classify skin lesions from the HAM10k collection.

• Host: GitHub
• URL: https://github.com/bsenst/capstone1-skin-lesion-classifier
• Owner: bsenst
• License: apache-2.0
• Created: 2022-11-23T12:07:05.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-12-17T18:52:42.000Z (over 3 years ago)
• Last Synced: 2025-03-28T18:19:49.128Z (about 1 year ago)
• Topics: neural-network, python3, skin-lesion-classification, xception-model
• Language: Jupyter Notebook
• Homepage:
• Size: 387 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# capstone1-skin-lesion-classifier

Experimental neural network to classify skin lesions from the HAM10k collection.

***Disclaimer: This work is part of an educational project. It is not intended for clinical application. As such it can not make real world predictions for skin lesions. To get recommendations regarding skin lesions one should ask for expert advice such as provided by a dermatologist.***

The dataset on kaggle: https://www.kaggle.com/datasets/kmader/skin-cancer-mnist-ham10000

The notebook to train the initial model: https://www.kaggle.com/code/bnzn261029/capstone1-ham10k-skincancer

The model on huggingface: https://huggingface.co/bsenst/skin-cancer-HAM10k/settings

The gradio app on huggingface spaces: https://huggingface.co/spaces/bsenst/keras-image-classifier

![image](https://user-images.githubusercontent.com/8211411/205152550-c0785d54-db1a-4dc5-a898-e438f06ac647.png)

The model classifies images using the following classes: 

* Actinic keratoses and intraepithelial carcinoma / Bowen's disease (akiec), 

* basal cell carcinoma (bcc), 

* benign keratosis-like lesions (solar lentigines / seborrheic keratoses and lichen-planus like keratoses, bkl),

* dermatofibroma (df), 

* melanoma (mel), 

* melanocytic nevi (nv) and 

* vascular lesions (angiomas, angiokeratomas, pyogenic granulomas and hemorrhage, vasc)