当前位置:网站首页>从照片中自动诊断皮肤病变的深度转移学习(CS CV)

从照片中自动诊断皮肤病变的深度转移学习(CS CV)

2020-12-07 19:23:54 凌茜

黑色素瘤是世界上最常见的皮肤癌。目前,该病由皮肤科专家诊断,费用昂贵,需要及时就医。深度学习的最新进展有可能提高诊断性能,加快紧急转诊和减轻临床医生的负担。通过智能手机,这项技术可以惠及那些通常无法获得此类医疗保健服务的人,例如,在世界偏远地区,由于资金限制,或在2020年,COVID-19取消。为此,我们研究了各种转移学习方法,利用ImageNet上预先训练的模型参数,并对黑色素瘤检测进行了微调。我们比较了带转移学习和不带转移学习的EfficientNet、MnasNet、MobileNet、DenseNet、squezenet、ShuffleNet、GoogleNet、ResNet、ResNeXt、VGG和一个简单的卷积神经网络(CNN)。我们发现,在移动网络中,EfficientNet(带转移学习)的平均性能最好,接收器工作特性曲线下的面积(AUROC)为0.931±0.005,精确召回曲线下的面积为0.840±0.010。这明显优于全科医生(0.83±0.03 AUROC)和皮肤科医生(0.91±0.02 AUROC)。

原文题目:Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs

原文:Melanoma is the most common form of skin cancer worldwide. 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).

原文作者:Emma Rocheteau, Doyoon Kim

原文地址:https://arxiv.org/abs/2011.04475

原创声明,本文系作者授权云+社区发表,未经许可,不得转载。

如有侵权,请联系 yunjia_community@tencent.com 删除。

版权声明
本文为[凌茜]所创,转载请带上原文链接,感谢
https://cloud.tencent.com/developer/article/1748735