Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data
TL
TL;DR
This paper addresses skin lesion classification with an ensemble of deep learning models including EfficientNets, SENet, and ResNeXt WSL, selected by a search strategy and predicts an additional, unknown class with a data-driven approach and makes use of patient meta data with an additional input branch.
References19 items
1
Left Ventricle Quantification Using Direct Regression with Segmentation Regularization and Ensembles of Pretrained 2D and 3D CNNs
2
BCN20000: Dermoscopic Lesions in the Wild
3
Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study.
4
AutoAugment: Learning Augmentation Strategies From Data
5