Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection.
Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection.
复制标题
DOI：
10.2147/jmdh.s306284
复制
发表时间：
2021
影响因子：
3.3
通讯作者：
Wang YC
中科院分区：
文献类型：
--
作者：
Ningrum DNA;Yuan SP;Kung WM;Wu CC;Tzeng IS;Huang CY;Li JY;Wang YC
皮肤癌的发病率是全球恶性肿瘤的负担之一，每年都在增加，其中黑色素瘤是最致命的。基于成像的皮肤癌自动检测仍然具有挑战性，因为皮肤病变的变异性和有限的标准数据集可用。最近的研究表明，深度卷积神经网络(CNN)在预测简单和高度复杂图像的结果方面具有潜力。然而，它的实现需要高级的计算设施，这在低资源和偏远的医疗保健领域是不可行的。将图像和患者的元数据结合起来是有潜力的，但这项研究仍然缺乏。我们希望使用人工智能(AI)模型，基于皮肤镜图像和患者元数据开发恶性黑色素瘤检测，该模型将在低资源设备上工作。我们使用了国际皮肤成像协作(ISIC)档案的开放访问皮肤病学库，数据集由23,801张经活检证实的皮肤镜图像组成。我们测试了恶性黑色素瘤与非恶性黑色素瘤的分类性能。从1200个样本图像中，我们将数据分为训练(72%)、验证(18%)和测试(10%)。我们比较了CNN只有图像数据(CNN模型)和CNN图像数据结合人工神经网络(ANN)患者元数据(CNN+ANN模型)。CNN+ANN模型的均衡准确率(92.34%)高于CNN模型(73.69%)。使用ANN的患者元数据的组合防止了仅使用皮肤镜图像的CNN模型中发生的过度拟合。该模型的小尺寸(24MB)使其能够在不需要云计算的中型计算机上运行，适合部署在资源有限的设备上。CNN+ANN模型可以在数据有限的情况下提高恶性黑色素瘤检测的分类准确率，在偏远和低资源的医疗保健中作为一种筛查设备具有很好的发展前景。
Incidence of skin cancer is one of the global burdens of malignancies that increase each year, with melanoma being the deadliest one. Imaging-based automated skin cancer detection still remains challenging owing to variability in the skin lesions and limited standard dataset availability. Recent research indicates the potential of deep convolutional neural networks (CNN) in predicting outcomes from simple as well as highly complicated images. However, its implementation requires high-class computational facility, that is not feasible in low resource and remote areas of health care. There is potential in combining image and patient’s metadata, but the study is still lacking. We want to develop malignant melanoma detection based on dermoscopic images and patient’s metadata using an artificial intelligence (AI) model that will work on low-resource devices. We used an open-access dermatology repository of International Skin Imaging Collaboration (ISIC) Archive dataset consist of 23,801 biopsy-proven dermoscopic images. We tested performance for binary classification malignant melanomas vs nonmalignant melanomas. From 1200 sample images, we split the data for training (72%), validation (18%), and testing (10%). We compared CNN with image data only (CNN model) vs CNN for image data combined with an artificial neural network (ANN) for patient’s metadata (CNN+ANN model). The balanced accuracy for CNN+ANN model was higher (92.34%) than the CNN model (73.69%). Combination of the patient’s metadata using ANN prevents the overfitting that occurs in the CNN model using dermoscopic images only. This small size (24 MB) of this model made it possible to run on a medium class computer without the need of cloud computing, suitable for deployment on devices with limited resources. The CNN+ANN model can increase the accuracy of classification in malignant melanoma detection even with limited data and is promising for development as a screening device in remote and low resources health care.