Deep Learning Method for Melanoma Discrimination Using Blood Flow Distribution Images
Deep Learning Method for Melanoma Discrimination Using Blood Flow Distribution Images
复制标题
使用血流分布图像识别黑色素瘤的深度学习方法
DOI：
10.1002/tee.23363
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Hachiga T
中科院分区：
文献类型：
--
作者：
Akiguchi S;Kyoden T;Tajiri T;Andoh T;Hachiga T
我们开发了一种多点激光多普勒测速仪（MLDV），可以非侵入性地测量血流速度。该装置可以获取血流速度的绝对值并对血流分布进行成像。血流速度的绝对值表明对受影响区域的随访。因此，我们对黑色素瘤和乳腺癌进行了随访。然而，该设备无法确定测量部位是否癌变。因此，在本研究中，我们构建了一个以血流分布图像作为输入的深度学习系统，并测试它是否可以区分黑色素瘤。结果表明，这种技术在疾病的早期阶段特别有效，当时皮肤表面没有发现异常。 © 2021 日本电气工程师协会。由 Wiley 期刊有限责任公司出版。
We have developed a multipoint laser Doppler velocimeter (MLDV) that can measure blood flow velocity non‐invasively. The device can acquire blood flow velocity in absolute value and image the blood flow distribution. Absolute values of blood flow velocity indicated a follow‐up on the affected area. Therefore, we have performed a follow‐up for melanoma and breast cancer. However, this device does not have the ability to determine whether a measurement site is cancerous or not. Thus, in this study, we built a deep learning system with blood flow distribution images as input and tested whether it can discriminate melanoma or not. The results showed that this technique was particularly effective in the early stages of the disease when no abnormalities were found on the skin surface. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.