On the Automatic Detection and Classification of Skin Cancer Using Deep Transfer Learning.
On the Automatic Detection and Classification of Skin Cancer Using Deep Transfer Learning.
复制标题
关于使用深度迁移学习的皮肤癌自动检测和分类。
DOI：
10.3390/s22134963
复制
发表时间：
2022-06-30
期刊：
影响因子：
3.9
通讯作者：
Faouri, Esraa
中科院分区：
文献类型：
--
作者：
Fraiwan, Mohammad;Faouri, Esraa
皮肤癌(黑色素瘤和非黑色素瘤)是最常见的癌症类型之一，每年导致全球数十万人死亡。它通过皮肤细胞的异常生长表现出来。早期诊断极大地增加了康复的机会。此外，它可能使手术、放射或化学治疗变得不必要，或减少其总体使用量。因此，可以降低医疗成本。皮肤癌的诊断过程从皮肤镜开始，皮肤镜检查皮损的一般形状、大小和颜色特征，然后对可疑皮损进行进一步采样和实验室测试以确定是否患有皮肤癌。近年来，由于深度学习人工智能的兴起，基于图像的诊断得到了很大的发展。本文研究了原始深度迁移学习在皮肤损伤图像分类中的适用性。使用HAM1000皮肤镜图像数据集，使用13个深度迁移学习模型开发了一个系统，该系统接受这些图像作为输入，而不需要明确的特征提取或预处理。广泛的评估揭示了这种方法的优点和缺点。虽然一些癌症类型被正确分类的准确率很高，但数据集的不平衡、某些类别的图像数量较少、类别数量较多使最好的总体准确率降至82.9%。
Skin cancer (melanoma and non-melanoma) is one of the most common cancer types and leads to hundreds of thousands of yearly deaths worldwide. It manifests itself through abnormal growth of skin cells. Early diagnosis drastically increases the chances of recovery. Moreover, it may render surgical, radiographic, or chemical therapies unnecessary or lessen their overall usage. Thus, healthcare costs can be reduced. The process of diagnosing skin cancer starts with dermoscopy, which inspects the general shape, size, and color characteristics of skin lesions, and suspected lesions undergo further sampling and lab tests for confirmation. Image-based diagnosis has undergone great advances recently due to the rise of deep learning artificial intelligence. The work in this paper examines the applicability of raw deep transfer learning in classifying images of skin lesions into seven possible categories. Using the HAM1000 dataset of dermoscopy images, a system that accepts these images as input without explicit feature extraction or preprocessing was developed using 13 deep transfer learning models. Extensive evaluation revealed the advantages and shortcomings of such a method. Although some cancer types were correctly classified with high accuracy, the imbalance of the dataset, the small number of images in some categories, and the large number of classes reduced the best overall accuracy to 82.9%.
登录
查看更多内容
影响因子：
3.2
作者：
Manzo M;Pellino S
通讯作者：
Pellino S
影响因子：
6.1
作者：
Oliveira, Roberta B.;Filho, Mercedes E.;Tavares, Joao Manuel R. S.
通讯作者：
Tavares, Joao Manuel R. S.
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
5.1
作者：
Chatterjee, Saptarshi;Dey, Debangshu;Gorai, Surajit
通讯作者：
Gorai, Surajit
DOI：
10.1016/j.compmedimag.2007.01.003
发表时间：
2007-09-01
影响因子：
5.7
作者：
Celebi, M. Emre;Kingravi, Hassan A.;Moss, Randy H.
通讯作者：
Moss, Randy H.