BACKGROUND Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. OBJECTIVE To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. METHODS In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. RESULTS The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. LIMITATIONS Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. CONCLUSION Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance.

中文翻译：

---

计算机算法显示出潜力，可以提高皮肤科医生诊断皮肤黑色素瘤的准确性：2017年国际皮肤影像协作组织的结果。

背景技术计算机视觉在基于图像的皮肤黑素瘤诊断中有希望，但是临床用途尚不确定。目的确定国际黑色素瘤检测挑战中的计算机算法是否可以提高皮肤科医生诊断黑色素瘤的准确性。方法在本横断面研究中，我们使用了来自黑色素瘤检测挑战的测试数据集中的150张皮肤镜检查图像（50张黑色素瘤，50张痣，50张脂溢性角化病）以及23个团队的算法结果。在在线读者研究中，八名皮肤科医生和九名皮肤科医生对皮肤镜病变图像进行了分类，并提供了他们的置信度。结果排名最高的计算机算法在接收器工作特性曲线下的面积为0.87，高于皮肤科医生（0.74）和居民（0.66）的面积（P <。所有比较都为001）。在皮肤科医生对分类的总体敏感性为76.0％时，该算法具有更高的特异性（85.0％对72.6％，P = .001）。低置信度等级（占评估的26.6％）将计算机算法分类输入到皮肤科医生评估中，可使皮肤科医生的敏感性从76.0％提高到80.8％，而特异性从72.6％增加到72.8％。局限性缺乏完整皮肤损伤谱以及临床元数据的人工研究环境。结论越来越多的证据表明，深层神经网络可以高度准确地对黑色素瘤及其良性隐匿者的皮肤图像进行分类，并有可能改善人类的表现。低置信度等级（占评估的26.6％）将计算机算法分类输入到皮肤科医生评估中，可使皮肤科医生的敏感性从76.0％提高到80.8％，而特异性从72.6％增加到72.8％。局限性缺乏完整皮肤损伤谱以及临床元数据的人工研究环境。结论越来越多的证据表明，深层神经网络可以高度准确地对黑色素瘤及其良性隐匿者的皮肤图像进行分类，并有可能改善人类的表现。低置信度等级（占评估的26.6％）将计算机算法分类输入到皮肤科医生评估中，可使皮肤科医生的敏感性从76.0％提高到80.8％，而特异性从72.6％增加到72.8％。局限性缺乏完整皮肤损伤谱以及临床元数据的人工研究环境。结论越来越多的证据表明，深层神经网络可以高度准确地对黑色素瘤及其良性隐匿者的皮肤图像进行分类，并有可能改善人类的表现。