Fusing fine-tuned deep features for skin lesion classification
Fusing fine-tuned deep features for skin lesion classification
复制标题
DOI：
10.1016/j.compmedimag.2018.10.007
复制
发表时间：
2019-01-01
影响因子：
5.7
通讯作者：
Wang, Chunliang
中科院分区：
文献类型：
--
作者：
Mahbod, Amirreza;Schaefer, Gerald;Wang, Chunliang
恶性黑色素瘤是最具侵袭性的皮肤癌之一。早期发现很重要，因为它能显著提高存活率。因此，准确区分恶性皮肤病变和良性病变(如脂溢性角化病或良性痣)是至关重要的，而准确的皮肤病变图像的计算机化分类对于支持诊断具有重要意义。在这篇文章中，我们提出了一种全自动的计算机方法来从皮肤镜图像中对皮肤损伤进行分类。我们的方法基于一种新的卷积神经网络(CNN)集成方案，该方案结合了体系结构内和体系结构间网络融合。该方法由代表不同特征抽象层次的不同体系结构的多个CNN集合组成。每组CNN由许多预先训练的网络组成，这些网络具有相同的体系结构，但在具有不同设置的皮肤镜皮肤损伤图像上进行微调。利用每个网络的深层特征训练不同的支持向量机分类器。最后，将不同集合的平均预测概率分类向量进行融合，得到最终的预测结果。在ISIC 2017皮肤病变分类挑战赛的600幅测试图像上，提出的算法对黑色素瘤的接收者操作特征曲线下面积为87.3%，对脂溢性角化病的接收者操作特征曲线下面积为95.5%，性能优于挑战的顶级方法，而且比它们更简单。实验结果表明，本文提出的方法对于皮肤镜下皮肤病变图像的特征提取、模型融合和分类是一种可靠的、稳健的方法。(C)2018爱思唯尔有限公司。保留所有权利。
Malignant melanoma is one of the most aggressive forms of skin cancer. Early detection is important as it significantly improves survival rates. Consequently, accurate discrimination of malignant skin lesions from benign lesions such as seborrheic keratoses or benign nevi is crucial, while accurate computerised classification of skin lesion images is of great interest to support diagnosis. In this paper, we propose a fully automatic computerised method to classify skin lesions from dermoscopic images. Our approach is based on a novel ensemble scheme for convolutional neural networks (CNNs) that combines intra-architecture and inter-architecture network fusion. The proposed method consists of multiple sets of CNNs of different architecture that represent different feature abstraction levels. Each set of CNNs consists of a number of pre-trained networks that have identical architecture but are fine-tuned on dermoscopic skin lesion images with different settings. The deep features of each network were used to train different support vector machine classifiers. Finally, the average prediction probability classification vectors from different sets are fused to provide the final prediction. Evaluated on the 600 test images of the ISIC 2017 skin lesion classification challenge, the proposed algorithm yields an area under receiver operating characteristic curve of 87.3% for melanoma classification and an area under receiver operating characteristic curve of 95.5% for seborrheic keratosis classification, outperforming the top-ranked methods of the challenge while being simpler compared to them. The obtained results convincingly demonstrate our proposed approach to represent a reliable and robust method for feature extraction, model fusion and classification of dermoscopic skin lesion images. (C) 2018 Elsevier Ltd. All rights reserved.