arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.00534cs.CV
收藏

基于深度神经网络的皮肤癌识别与分类

Skin cancer reorganization and classification with deep neural network

Yale University School of Medicine(耶鲁大学医学院)

Hao Chang

摘要:

黑色素瘤作为皮肤癌的一种,是非常危险的。基于皮肤镜的早期检测和再碳化策略对于黑色素瘤治疗至关重要。然而,训练有素的皮肤科医生主导诊断的准确性。为了解决这个问题,许多努力集中在开发自动图像分析系统。在这里,我们报告了一种基于深度学习技术的新策略,并实现了非常高的皮肤病变分割和黑色素瘤诊断准确率:1)我们构建了一个分割神经网络(skin_segnn),它实现了非常高的病变边界检测准确率; 2)我们基于Google inception v3网络(skin_recnn)及其经过良好训练的权重构建了另一个非常深的神经网络。新设计的基于迁移学习的深度神经网络skin_inceptions_v3_nn有助于实现高预测精度。

英文摘要:

As one kind of skin cancer, melanoma is very dangerous. Dermoscopy based early detection and recarbonization strategy is critical for melanoma therapy. However, well-trained dermatologists dominant the diagnostic accuracy. In order to solve this problem, many effort focus on developing automatic image analysis systems. Here we report a novel strategy based on deep learning technique, and achieve very high skin lesion segmentation and melanoma diagnosis accuracy: 1) we build a segmentation neural network (skin_segnn), which achieved very high lesion boundary detection accuracy; 2) We build another very deep neural network based on Google inception v3 network (skin_recnn) and its well-trained weight. The novel designed transfer learning based deep neural network skin_inceptions_v3_nn helps to achieve a high prediction accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑