Skip to content

Latest commit

 

History

History
78 lines (69 loc) · 4.37 KB

README.md

File metadata and controls

78 lines (69 loc) · 4.37 KB

Web-based Melanoma Detection

ArXiv link

Standalone Melanoma web application

Melanoma web application

Supported datasets

DBs Network Img size Private Score 1 Public Score 2
ISIC'16+ISIC'17+ISIC'18+ISIC'19+MEDNODE+Kaggle DenseNet121 150x150 0.7211 0.7472
ISIC'18 ResNet50 150x150 0.5999 0.6301
ISIC'20 ResNet50 150x150 0.7751 0.8126
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20+PH2 ResNet152 150x150 0.8064 0.8073
ISIC'19 ResNet152 150x150 0.6769 0.7234
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20+PH2+
7pointcriteria+PAD_UFES_20+MEDNODE+Kaggle
ResNet152 150x150 0.7774 0.7894
Multiple 3 Ensemble 4 150x150 0.7618 0.7621
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20+PH2 ResNet152 384x384 0.7028 0.7134
ISIC'16+ISIC'17+ISIC2018+ISIC'19 DenseNet169 384x384 0.6943 0.7471
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC2020+PH2+
_7_point_criteria+PAD_UFES_20+MEDNODE+KaggleMB
DenseNet169 384x384 0.7963 0.8535
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20+PH2+
MEDNODE+KaggleMB
DenseNet169 384x384 0.8028 0.8247
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20+PH2+
PAD_UFES_20+MEDNODE
DenseNet169 384x384 0.7980 0.8338
ISIC'16+ISIC'17+ISIC'18+_7_point_criteria+
PAD_UFES_20
ResNet50 384x384 0.4199 0.4484
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20+PH2 ResNet152 384x384 0.7028 0.7234
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20+PH2+
_7_point_criteria+PAD_UFES_20+MEDNODE
ResNet152V2 384x384 0.8144 0.8284
ISIC'16+MEDNODE Xception 384x384 0.7409 0.7474
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20+PH2+
_7_point_criteria+PAD_UFES_20+MEDNODE+KaggleMB
ResNet152V2 384x384 0.8009 0.8219
ISIC'16+ISIC'18+ISIC'19+ISIC'20 DenseNet169 384x384 0.8195 0.8619
ISIC'16+ISIC'17+ISIC'18+ISIC'19+ISIC'20 DenseNet169 384x384 0.7673 0.8267

Note

1 Score on 70% of private testsets. The potential winner(s) are determined solely by the leaderboard ranking on the private leaderboard.
2 Score on the public testsets for reference
3 Averaged the models in the table, trained with multiple datasets
4 Averaged the probabilities from the models in the table

Environment (chimera clean env)

  • Keras - 2.5.0rc0
  • Tensorflow - 2.5.0
  • Augmentor - 0.2.10
  • matplotlib==3.2.1
  • pandas==1.2.0
  • numpy==1.19.4
  • pip install pydot
  • conda install -c anaconda graphviz

Contact

[email protected]