Corpus overview


MeSH Disease

HGNC Genes

There are no HGNC terms in the subcorpus

SARS-CoV-2 proteins

There are no SARS-CoV-2 protein terms in the subcorpus


SARS-CoV-2 Proteins
    displaying 1 - 1 records in total 1
    records per page

    Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs

    Authors: Emma Rocheteau; Doyoon Kim

    id:2011.04475v3 Date: 2020-11-06 Source: arXiv

    Melanoma MESHD is not the most common form of skin cancer MESHD, but it is the most deadly. Currently, the disease is diagnosed by expert dermatologists, which is costly and requires timely access to medical treatment. Recent advances in deep learning have the potential to improve diagnostic performance, expedite urgent referrals and reduce burden on clinicians. Through smart phones, the technology could reach people who would not normally have access to such healthcare services, e.g. in remote parts of the world, due to financial constraints or in 2020, COVID-19 MESHD cancellations. To this end, we have investigated various transfer learning approaches by leveraging model parameters pre-trained on ImageNet with finetuning on melanoma MESHD detection. We compare EfficientNet, MnasNet, MobileNet, DenseNet, SqueezeNet, ShuffleNet, GoogleNet, ResNet, ResNeXt, VGG and a simple CNN with and without transfer learning. We find the mobile network, EfficientNet (with transfer learning) achieves the best mean performance with an area under the receiver operating characteristic curve (AUROC) of 0.931$\pm$0.005 and an area under the precision recall curve (AUPRC) of 0.840$\pm$0.010. This is significantly better than general practitioners (0.83$\pm$0.03 AUROC) and dermatologists (0.91$\pm$0.02 AUROC).

The ZB MED preprint Viewer preVIEW includes all COVID-19 related preprints from medRxiv and bioRxiv, from ChemRxiv, from ResearchSquare, from arXiv and from and is updated on a daily basis (7am CET/CEST).
The web page can also be accessed via API.



MeSH Disease
HGNC Genes
SARS-CoV-2 Proteins

Export subcorpus as...

This service is developed in the project nfdi4health task force covid-19 which is a part of nfdi4health.

nfdi4health is one of the funded consortia of the National Research Data Infrastructure programme of the DFG.