[论文解读] Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks

Lei Bi, Jin‐Man Kim+2 more|arXiv (Cornell University)|Mar 12, 2017

Cutaneous Melanoma Detection and Management参考文献 8被引用 173

一句话总结

本文提出使用深度残差网络（ResNets）从大规模皮肤镜图像中学习鲁棒特征，用于自动皮肤病变分析，特别是对黑色素瘤检测，在 ISIC 2017 挑战中。

ABSTRACT

Malignant melanoma has one of the most rapidly increasing incidences in the world and has a considerable mortality rate. Early diagnosis is particularly important since melanoma can be cured with prompt excision. Dermoscopy images play an important role in the non-invasive early detection of melanoma [1]. However, melanoma detection using human vision alone can be subjective, inaccurate and poorly reproducible even among experienced dermatologists. This is attributed to the challenges in interpreting images with diverse characteristics including lesions of varying sizes and shapes, lesions that may have fuzzy boundaries, different skin colors and the presence of hair [2]. Therefore, the automatic analysis of dermoscopy images is a valuable aid for clinical decision making and for image-based diagnosis to identify diseases such as melanoma [1-4]. Deep residual networks (ResNets) has achieved state-of-the-art results in image classification and detection related problems [5-8]. In this ISIC 2017 skin lesion analysis challenge [9], we propose to exploit the deep ResNets for robust visual features learning and representations.

研究动机与目标

• 由于人类解释的主观性和变异性，推动自动 dermoscopy 分析以帮助早期黑色素瘤诊断。
• 利用大规模 dermoscopy 数据集来学习鲁棒的视觉特征。
• 应用深度残差网络来提高基于图像的皮肤病变分类与检测。

提出的方法

• 利用深度残差网络（ResNets）从 dermoscopy 图像中学习鲁棒特征。
• 在大规模 dermoscopy 数据集上进行训练，以捕捉多样的病变特征。
• 旨在在 ISIC 2017 挑战框架内提高黑色素瘤的分类/检测性能。

实验结果

研究问题

• RQ1 深度残差网络是否能够从大规模 dermoscopy 图像中学习鲁棒表示以进行皮肤病变分析？
• RQ2 与以往方法相比，ResNets 是否在 dermoscopy 的黑色素瘤相关分类/检测性能上有所提升？
• RQ3 在 ISIC 2017 Challenge 设置下，该方法的表现如何？

主要发现

• 该方法展示了使用 ResNets 从大规模 dermoscopy 图像中学习用于皮肤病变分析的鲁棒特征。
• 该工作通过 dermoscopy 图像的自动分析来实现黑色素瘤的检测。
• 该方法定位于在 ISIC 2017 Challenge 进行评估。
• 论文报告了利用深度学习进行非侵入性早期黑色素瘤检测的进展。