CVJul 17, 2018

A Dense CNN approach for skin lesion classification

arXiv:1807.06416v2
Originality Synthesis-oriented
AI Analysis

This work addresses automated diagnosis of skin cancer for medical applications, but is incremental as it adapts existing methods to a specific dataset.

The researchers tackled skin lesion classification by fine-tuning a 61-layer DenseNet pre-trained on ImageNet with a Center Loss function on the ISIC 2018 dataset, achieving competitive performance on seven lesion types.

This article presents a Deep CNN, based on the DenseNet architecture jointly with a highly discriminating learning methodology, in order to classify seven kinds of skin lesions: Melanoma, Melanocytic nevus, Basal cell carcinoma, Actinic keratosis / Bowen's disease, Benign keratosis, Dermatofibroma, Vascular lesion. In particular a 61 layers DenseNet, pre-trained on IMAGENET dataset, has been fine-tuned on ISIC 2018 Task 3 Challenge Dataset exploiting a Center Loss function.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes