Description

SkinDx is Machine Learning freeware mobile app for pigmented skin lesion diagnosis.

This app uses Tensorflow and Tensorflow Lite for developing machine learning mobile app. The ssd_mobilenet_v2 model is used for transfer training with dataset from ISIC (benign vs malignant) and HM10000 dataset. The accuracy test of these models are evaluated on mobile. The scores are as follow:

ISIC dataset

  • benign 63.89%
  • malignant 97.32%

total 79.03%

HAM10000 dataset

  • akiec 0.00%
  • bcc 13.73%
  • mel 54.95%
  • bkl 27.52%
  • nv 82.24%
  • vasc 42.86%
  • df 9.09%

total 65.73%

You can use this app only for screening skin lesion. It CAN'T be used for diagnosis without any supervision from medical expert.

Screenshots

Video

-

Platform requirement

  • Android 6.0 or later

History

  • Version 1.0 released (July 2019)
Get it on Google Play