What is SkinDetect?

SkinDetect is a free and open-source app that uses artificial intelligence (Tensorflow) to recognize eight different types of skin lesions. The app can detect various types of skin lesions, ranging from dangerous skin cancers like basal cell carcinoma (BCC), the most common form of skin cancer, to harmless lesions like normal moles (melanocytic nevi).

What can it detect?

The following 8 lesion types can be detected by SkinDetect:

  • Actinic keratoses (akiec)
  • Basal cell carcinoma (bcc)
  • Benign keratosis-like lesions (bkl)
  • Dermatofibroma (df)
  • Melanoma (mel)
  • Melanocytic nevi (nv)
  • Vascular lesions (vasc)
  • Squamous cell carcinoma (scc)

Motivation

The SkinDetect app was developed to contribute to the 17 Sustainable Development Goals established by the United Nations. Specifically, this app strives to support the aim to limit diseases all around the world, which was formulated under development goal number 3: "good health and well-being" .

Tech Stack

  • Flutter
  • Dart

License

Apache-2.0 License

Resources & Downloads

GitHub - MZimmermann-coder/SkinDetect_v2: SkinDetect is an app created to diagnose skin lesions, including the most widespread types of skin cancer, via its custom-trained AI. This is the repository for the second version of the app, developed with Flutter and Tensorflow.
SkinDetect is an app created to diagnose skin lesions, including the most widespread types of skin cancer, via its custom-trained AI. This is the repository for the second version of the app, devel…
GitHubMZimmermann-coder