Web-based Melanoma Detection

ArXiv link

Standalone Melanoma web application

Melanoma web application

Supported datasets

• HAM10000
• ISIC2016
• ISIC2017
• ISIC2018
• ISIC2019
• ISIC2020
• PH2
• 7-point criteria dataset
• PAD_UFES_20
• MED-NODE
• Kaggle

SIIM-ISIC leaderboard results

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]