A multilevel features selection framework for skin lesion classification
A multilevel features selection framework for skin lesion classification
复制标题
DOI：
10.1186/s13673-020-00216-y
复制
发表时间：
2020-03-31
影响因子：
6.6
通讯作者：
Qadri, Nadia N.
中科院分区：
文献类型：
--
作者：
Akram, Tallha;Lodhi, Hafiz M. Junaid;Qadri, Nadia N.
黑色素瘤被认为是最致命的皮肤癌类型之一，其发生频率在过去几年中有所增加;然而，其早期诊断大大增加了患者的生存机会。在寻求同样的，一些基于计算机的方法，能够诊断皮肤病变的初始阶段，最近已经提出。然而，尽管取得了一些成功，但仍存在一定的差距，因此机器学习界仍然认为这是一个杰出的研究挑战。在这项工作中，我们提出了一个新的框架，皮肤病变分类，它集成了深特征信息，以产生最具鉴别力的特征向量，具有保留原始特征空间的优势。我们利用最近的深度模型进行特征提取，并利用迁移学习。首先，皮肤镜图像被分割，并且病变区域被提取，其随后经受重新训练所选择的深度模型以生成融合的特征向量。在第二阶段，提出了一个用于最具鉴别力的特征选择和降维的框架，熵控制的邻域成分分析（ECNCA）。该层次框架通过选择主成分和提取冗余和不相关的数据来优化融合特征。我们的设计的有效性在四个基准皮肤镜数据集上得到了验证; PH 2，ISIC MSK，ISIC UDA和ISBI-2017。为了验证所提出的方法，与现有技术的公平比较也提供了。仿真结果清楚地表明，所提出的设计是准确的，足以分类皮肤病变与98.8%，99.2%和97.1%和95.9%的准确率与所有四个数据集上所选择的分类器，并利用不到3%的功能。
Melanoma is considered to be one of the deadliest skin cancer types, whose occurring frequency elevated in the last few years; its earlier diagnosis, however, significantly increases the chances of patients' survival. In the quest for the same, a few computer based methods, capable of diagnosing the skin lesion at initial stages, have been recently proposed. Despite some success, however, margin exists, due to which the machine learning community still considers this an outstanding research challenge. In this work, we come up with a novel framework for skin lesion classification, which integrates deep features information to generate most discriminant feature vector, with an advantage of preserving the original feature space. We utilize recent deep models for feature extraction, and by taking advantage of transfer learning. Initially, the dermoscopic images are segmented, and the lesion region is extracted, which is later subjected to retrain the selected deep models to generate fused feature vectors. In the second phase, a framework for most discriminant feature selection and dimensionality reduction is proposed, entropy-controlled neighborhood component analysis (ECNCA). This hierarchical framework optimizes fused features by selecting the principle components and extricating the redundant and irrelevant data. The effectiveness of our design is validated on four benchmark dermoscopic datasets; PH2, ISIC MSK, ISIC UDA, and ISBI-2017. To authenticate the proposed method, a fair comparison with the existing techniques is also provided. The simulation results clearly show that the proposed design is accurate enough to categorize the skin lesion with 98.8%, 99.2% and 97.1% and 95.9% accuracy with the selected classifiers on all four datasets, and by utilizing less than 3% features.