Dermatologist-level classification of skin cancer with deep neural networks.
Dermatologist-level classification of skin cancer with deep neural networks.
复制标题
DOI：
10.1038/nature21056
复制
发表时间：
2017-02-02
期刊：
影响因子：
64.8
通讯作者：
Thrun S
中科院分区：
文献类型：
--
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
皮肤癌是人类最常见的恶性肿瘤，主要通过视觉诊断，首先进行初步的临床筛查，然后可能进行皮肤镜分析、活组织检查和组织病理学检查。由于皮肤损伤外观的细粒度变化，使用图像对皮肤损伤进行自动分类是一项具有挑战性的任务。深度卷积神经网络(CNN)显示出跨越许多细粒度对象类别的一般和高度可变的任务的潜力。在这里，我们使用单一的CNN，直接从图像训练端到端，仅使用像素和疾病标签作为输入，来演示皮肤损伤的分类。我们使用包含2,032种不同疾病的129,450张临床图像的数据集--比以前的数据集大两个数量级--来训练CNN。我们用两个关键的二进制分类用例：角质形成细胞癌与良性脂溢性角化病；恶性黑色素瘤与良性痣，在活检证实的临床图像上与21名委员会认证的皮肤科医生测试其性能。第一个病例代表最常见癌症的鉴定，第二个病例代表最致命的皮肤癌的鉴定。CNN在这两项任务中的表现与所有接受测试的专家不相上下，展示了一种能够以皮肤科医生相当的能力对皮肤癌进行分类的人工智能。配备了深度神经网络的移动设备可能会将皮肤科医生的触角伸向临床以外的领域。据预测，到2021年，全球将有63亿智能手机用户。因此，有可能提供低成本的普遍获得重要诊断护理的机会。
Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images—two orders of magnitude larger than previous datasets—consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref.) and can therefore potentially provide low-cost universal access to vital diagnostic care.
登录
查看更多内容
影响因子：
2.2
作者：
Binder, M;Kittler, H;Wolff, K
通讯作者：
Wolff, K
影响因子：
19.5
作者：
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者：
Fei-Fei, Li
影响因子：
64.8
作者：
Mnih, Volodymyr;Kavukcuoglu, Koray;Hassabis, Demis
通讯作者：
Hassabis, Demis
影响因子：
10.3
作者：
CLARK, WH;ELDER, DE;HALPERN, AC
通讯作者：
HALPERN, AC
影响因子：
--
作者：
Stern, Robert S.
通讯作者：
Stern, Robert S.