WonDerM: Skin Lesion Classification with Fine-tuned Neural Networks
Published in
arXiv.org(2018)External Links:
TL
TL;DR
The WonDerM pipeline is designed, that resamples the preprocessed skin lesion images, builds neural network architecture fine-tuned with segmentation task data, and uses an ensemble method to classify the seven skin diseases.
Abstract
As skin cancer is one of the most frequent cancers globally, accurate, non-invasive dermoscopy-based diagnosis becomes essential and promising. A task of the Part 3 of the ISIC Skin Image Analysis Challenge at MICCAI 2018 is to predict seven disease classes with skin lesion images, including melanoma (MEL), melanocytic nevus (NV), basal cell carcinoma (BCC), actinic keratosis / Bowen's disease (intraepithelial carcinoma) (AKIEC), benign keratosis (solar lentigo / seborrheic keratosis / lichen planus-like keratosis) (BKL), dermatofibroma (DF) and vascular lesion (VASC) as defined by the International Dermatology Society. In this work, we design the WonDerM pipeline, that resamples the preprocessed skin lesion images, builds neural network architecture fine-tuned with segmentation task data (the Part 1), and uses an ensemble method to classify the seven skin diseases. Our model achieved the score 0.899 in validation data.
References16 items
1
The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
2
The global burden of melanoma: results from the Global Burden of Disease Study 2015
3
Melanocytic nevi and melanoma: unraveling a complex relationship
4
Dermatologist-level classification of skin cancer with deep neural networks
5