# Knowledge Transfer for Melanoma Screening with Deep Learning

## TL;DR

This paper systematically evaluates transfer learning techniques for melanoma screening using deep neural networks, highlighting the benefits of deeper pre-trained models and fine-tuning for improved diagnostic accuracy.

## Contribution

It provides a comprehensive analysis of transfer learning's effectiveness in melanoma detection, including the impact of model depth and fine-tuning strategies.

## Key findings

- Deeper models pre-trained on ImageNet perform better.
- Fine-tuning improves melanoma classification accuracy.
- Achieved AUCs of 80.7% and 84.5% on two datasets.

## Abstract

Knowledge transfer impacts the performance of deep learning -- the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for medical tasks, which we can alleviate by recycling knowledge from models trained on different tasks, in a scheme called transfer learning. Although much of the best art on automated melanoma screening employs some form of transfer learning, a systematic evaluation was missing. Here we investigate the presence of transfer, from which task the transfer is sourced, and the application of fine tuning (i.e., retraining of the deep learning model after transfer). We also test the impact of picking deeper (and more expensive) models. Our results favor deeper models, pre-trained over ImageNet, with fine-tuning, reaching an AUC of 80.7% and 84.5% for the two skin-lesion datasets evaluated.