Papers › Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs

Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs

6 Nov 2020arXiv:2011.04475archive 2025-07-28

Emma Rocheteau, Doyoon Kim

Melanoma is not the most common form of skin cancer, 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 cancellations. To this end, we have investigated various transfer learning approaches by leveraging model parameters pre-trained on ImageNet with finetuning on melanoma 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±0.005 and an area under the precision recall curve (AUPRC) of 0.840±0.010. This is significantly better than general practitioners (0.83±0.03 AUROC) and dermatologists (0.91±0.02 AUROC).

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

aimadeus/Transfer_learning_melanoma officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiagnosticTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockChannel ShuffleConcatenated Skip ConnectionConvolutionDense BlockDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetFire ModuleGlobal Average PoolingGrouped ConvolutionGroupwise Point ConvolutionInverted Residual BlockKaiming InitializationMax PoolingMnasNetPointwise ConvolutionRMSPropReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionShuffleNetShuffleNet BlockSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockSqueezeNetXavier Initialization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections