首页> 外文会议>National Conference on Biomedical Engineering;International Iranian Conference on Biomedical Engineering >A Mobile Application for Early Detection of Melanoma by Image Processing Algorithms
【24h】

A Mobile Application for Early Detection of Melanoma by Image Processing Algorithms

机译:通过图像处理算法在黑色素瘤早期检测中的移动应用

获取原文

摘要

Melanoma is the most dangerous skin cancer which causes many deaths annually. However, early detection can help treat it. For accurate detection of melanoma, dermatologists use biopsy which is usually associated with pain, time and cost. With the advancement of technology and the development of smartphones, many mobile applications have been designed for early detection of melanoma. Although they are fast in the detection of melanoma and save time and money, they are not as accurate as the biopsy. In this paper, the authors proposed an application for early detection of melanoma using image processing methods and pattern recognition algorithms by Android Studio software, Java programming language, and the OpenCV library. All detection steps were carried out using the Android smartphone. For better performance in the classification step, in addition to the smartphone, a computer was also used. This application is user-friendly and the calculated Accuracy, Sensitivity, and Specificity are 95%, 98%, and 92.19% on average, respectively. It should be noted that these results are more reliable when the lesions are geometrically distinct.
机译:黑色素瘤是最危险的皮肤癌,每年都会导致许多死亡。但是,尽早发现有助于治疗。为了准确地检测黑色素瘤,皮肤科医生使用活检通常与疼痛,时间和费用有关。随着技术的进步和智能手机的发展,已经设计出许多用于早期发现黑素瘤的移动应用程序。尽管它们可以快速检测黑色素瘤并节省时间和金钱,但它们不如活检准确。在本文中,作者提出了一种通过Android Studio软件,Java编程语言和OpenCV库使用图像处理方法和模式识别算法对黑素瘤进行早期检测的应用程序。所有检测步骤均使用Android智能手机执行。为了在分类步骤中获得更好的性能,除了智能手机,还使用了计算机。该应用程序易于使用,计算出的准确度,灵敏度和特异性分别平均为95%,98%和92.19%。应该注意的是,当病变在几何上是不同的时,这些结果更加可靠。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号