WonDerM: Skin Lesion Classification with Fine-tuned Neural Networks

08/10/2018

∙

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.

READ FULL TEXT

WonDerM: Skin Lesion Classification with Fine-tuned Neural Networks

A Dense CNN approach for skin lesion classification

Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning

Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting

SkinSAM: Empowering Skin Cancer Segmentation with Segment Anything Model

A Web-based Mpox Skin Lesion Detection System Using State-of-the-art Deep Learning Models Considering Racial Diversity

SkinGPT: A Dermatology Diagnostic System with Vision Large Language Model

Expert Opinion Elicitation for Assisting Deep Learning based Lyme Disease Classifier with Patient Data

WonDerM: Skin Lesion Classification with Fine-tuned Neural Networks

Related Research

A Dense CNN approach for skin lesion classification

Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning

Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting

SkinSAM: Empowering Skin Cancer Segmentation with Segment Anything Model

A Web-based Mpox Skin Lesion Detection System Using State-of-the-art Deep Learning Models Considering Racial Diversity

SkinGPT: A Dermatology Diagnostic System with Vision Large Language Model

Expert Opinion Elicitation for Assisting Deep Learning based Lyme Disease Classifier with Patient Data