论文标题
从照片中自动诊断皮肤病变的深度转移学习
Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs
论文作者
论文摘要
黑色素瘤不是皮肤癌最常见的形式，但最致命。目前，该疾病是由专家皮肤科医生诊断出的，这是昂贵的，需要及时获得医疗。深度学习的最新进展有可能提高诊断性能，加快紧急转诊并减轻临床医生的负担。通过智能手机，该技术可以吸引那些通常无法获得此类医疗服务的人，例如在世界偏远地区，由于财务限制或2020年COVID-19取消。为此，我们通过利用模型参数在ImageNet上预先训练的模型参数，并在黑色素瘤检测中进行了鉴定，从而研究了各种转移学习方法。我们比较了EfficityNet，MNASNET，Mobilenet，Densenet，Squeezenet，Shufflenet，Googlenet，Resnet，Resnet，Resnext，vgg和一个简单的CNN，并具有带有和没有转移学习的简单CNN。我们发现移动网络（带有转移学习）可以达到最佳的平均性能，而接收器操作特征曲线（AUROC）下的区域为0.931 $ \ pm $ 0.005，并且在精确召回曲线（AUPRC）下的区域为0.840 $ \ pm $ \ pm $ 0.010。这比全科医生（0.83 $ \ pm $ 0.03 AUROC）和皮肤科医生（0.91 $ \ pm $ 0.02 AUROC）要好得多。
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$\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).
