Published March 30, 2023 | Version v2
Other Open

12: Skin Lesion Images for Melanoma Classification (ISIC)

Description

This model was trained on the training data set for the ISIC 2019 challenge. Training data already includes data from previous years (2018 and 2017). It consists of 25,331 dermoscopic images among nine different diagnostic categories:
  • Melanoma
  • Melanocytic nevus
  • Basal cell carcinoma
  • Actinic keratosis
  • Benign keratosis (solar lentigo / seborrheic keratosis / lichen planus-like keratosis)
  • Dermatofibroma
  • Vascular lesion
  • Squamous cell carcinoma
  • None of the above
The model was trained using this script; a summary of its performance can be found here.

Files

521746_model_converted.zip

Files (121.5 MB)

Name Size
md5:e7b63b73a51db6c13083e5f2c18fe89a
28.3 MB Preview Download
md5:e926ecf888a1e6895fdcb27fd7d090d4
92.3 MB Download
md5:b2864623cc718db9672910f02c7c1d76
499.9 kB Preview Download
md5:b85af5445945378e16b7e921d4d6ea92
496.4 kB Preview Download

Additional details

Related works

Is part of
10.5281/zenodo.7740029 (DOI)