基于深层卷积残差网络集成的黑色素瘤分类方法

doi:10.11896/j.issn.1002-137X.2019.05.038

摘要/Abstract

摘要： 针对黑色素瘤分类识别任务中存在对比度低、肉眼难以区分、信息干扰大、数据量偏少以及数据不均衡等诸多问题,文中提出了一种基于掩盖的数据增强与深度卷积残差网络相结合的集成分类方法。首先根据皮肤病图像的特点,在前人数据增强研究的基础上,提出了两种基于掩盖训练图像部分区域的数据增强方式;其次以这两种数据增强方式为基础,采用深度卷积残差50层(ResNet-50)网络进行特征提取;然后以提取到的特征来构建两个具有一定差异性的分类结构模型,并对其进行集成;最后以国际皮肤影像协作组织(ISIC)2016挑战赛所公布的皮肤病图像数据集为对象,通过一系列实验对提出的方法进行了验证测试。实验结果表明,所提出的集成分类结构模型能弥补单一卷积残差网络在黑色素瘤分类任务中的缺陷,该模型能够在训练样本较少的皮肤病数据集上取得较好的分类结果,多项评估指标均优于ISIC2016挑战赛的前5名。

关键词: 黑色素瘤, 集成学习, 卷积残差网络, 数据增强

Abstract: To solve the classification problems of melanoma,such as low contrast,indistinguishable by the naked eyes,mass information interference,small dataset and data imbalance,this paper proposed an integrated classification method based on mask data augment and deep convolutional residual network.Firstly,according to the characteristics of skin lesion image and the previous researches,two data augmentation methods by masking the partial area of the trainingima-ges were proposed.Secondly,on the basis of these two data augmentation methods,some features were extracted by using deep convolutional residual 50-layer network.Thirdly,two different classification models were constructed and integrated based on these features.Finally,a series of experiments were conducted based on the datasets of Internal Skin Imaging Collaboration (ISIC) 2016 Challenge competition.The experimental results show that the integrated classification structure model can overcome the deficiencies of a single convolution residual network in melanoma classification tasks,and can achieve better classification results than other methods on skin lesion dataset with less training examples,and multiple evaluation indicators in the proposed method are better than the top-5 results in the ISIC2016 Challenge competition.

Key words: Convolution residual network, Data augmentation, Ensemble learning, Melanoma

中图分类号:

TP183

胡海根, 孔祥勇, 周乾伟, 管秋, 陈胜勇. 基于深层卷积残差网络集成的黑色素瘤分类方法[J]. 计算机科学, 2019, 46(5): 247-253. https://doi.org/10.11896/j.issn.1002-137X.2019.05.038

HU Hai-gen, KONG Xiang-yong, ZHOU Qian-wei, GUAN Qiu, CHEN Sheng-yong. Melanoma Classification Method by Integrating Deep Convolutional Residual Network[J]. Computer Science, 2019, 46(5): 247-253. https://doi.org/10.11896/j.issn.1002-137X.2019.05.038

参考文献

[1]JERANT A,JOHNSON J,SHERIDAN C,et al.Early detection and treatment of skin cancer [J].American Family Physician,2000,62(2):357-386.
[2]SIEGEL R L,MILLER K D,JEMAL A.Cancer statistics,2015 [J].CA:A Cancer Journal for Clinicians,2015,65(1):5-29.
[3]XIE F Y,FAN H,YANG L,et al.Melanoma Classification on Dermoscopy Images using a Neural Network Ensemble Model [J].IEEE Transactions on Medical Imaging,2016,36(3):849-858.
[4]SI L,GUO J.Interpretation of clinical practice guidelines formanagement of melanoma in China(new version of 2011) [J].Chinese Clinical Oncology,2012,17(2):172-173.(in Chinese)斯璐,郭军.新版中国黑素瘤诊治指南解读[J].临床肿瘤学杂志,2012,17(2):172-173.
[5]BINDER M,SCHWARZ M,WINKLER A,et al.Epilumines-cence microscopy:a useful tool for the diagnosis of pigmented skin lesions for formally trained dermatologists [J].Archives of Dermatology (ARCH DERMATOL),1995,131(3):286-291.
[6]GUO L L,DING S F.Research Progress in Deep Learning [J].Computer Science,2015,42(5):28-33.(in Chinese)郭丽丽,丁世飞.深度学习研究进展[J].计算机科学,2015,42(5):28-33.
[7]HU H,LUO C,GUAN Q,et al.A fast online multivariableidentification method for greenhouse environment control problems [J].Neurocomputing,2018,312:63-73.
[8]HU H,GUAN Q,CHEN S,et al.Detection and Recognition for Life State of Cell Cancer Using Two-Stage Cascade CNNs [J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2017:1.
[9]WANG X,SHRIVASTAVA A,GUPTA A.A-fast-rcnn:Hardpositive generation via adversary for object detection[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2017:3039-3048.
[10]ZHONG Z,ZHENG L,KANG G,et al.Random Erasing Data Augmentation [J].arXiv Preprint arXiv:1708.04896,2017.
[11]SINGH K K,LEE Y J.Hide-and-seek:Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization [J].arXiv preprint arXiv:1704.04232,2017.
[12]STANLEY R J,STOECKER W V,MOSS R H.A relative color approach to color discrimination for malignant melanoma detection in dermoscopy images [J].Skin Research and Technology (Skin Res Tech),2007,13(1):62-72.
[13]CHENG Y,SWAMISAI R,UMBAUGH S E,et al.Skin lesion classification using relative color features [J].Skin Research and Technology (Skin Res Tech),2008,14(1):53-64.
[14]RAHIL G,ALDEEN M,BAILEY J.Computer-Aided Diagnosis of Melanoma Using Border-and Wavelet-Based Texture Analysis [J].IEEE transactions on information technology in biomedicine:A publication of the IEEE Engineering in Medicine and Biology Society,2012,16(6):1239-1252.
[15]BALLERINI L,FISHER R B,ALDRIDGE B,et al.A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions[M]∥Color Medical Image Analysis.2013.
[16]ALFED N,KHELIFI F,BOURIDANE A.Improving a bag of words approach for skin cancer detection in dermoscopic images[C]∥Proceedings of IEEE International Conference on Decision and Information Technologies (CoDIT).2016:228-232.
[17]PREMALADHA J,RAVICHANDRAN K S.Novel Approaches for Diagnosing Melanoma Skin Lesions Through Supervised and Deep Learning Algorithms [J].Journal of Medical Systems,2016,40(4):1-12.
[18]POMPONIU V,NEJATI H,CHEUNG N M.Deepmole:Deepneural networks for skin mole lesion classification[C]∥Proceedings of IEEE International Conference on Image Processing (ICIP).2016:2623-2627.
[19]ESTEVA A,KUPREL B,NOVOA R A,et al.Dermatologist-level classification of skin cancer with deep neural networks [J].Nature,2017,542(7639):115-118.
[20]YU L,CHEN H,DOU Q,et al.Automated melanoma recognition in dermoscopy images via very deep residual networks [J].IEEE Transactions on Medical Imaging,2017,36(4):994-1004.
[21]YI X,WALIA E,BABYN P.Unsupervised and semi-supervised learning with Categorical Generative Adversarial Networks assisted by Wasserstein distance for dermoscopy image Classification [J].arXiv Preprint arXiv:1804.03700,2018.
[22]HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE Press,2016:770-778.
[23]SVETNIK V,WANG T,TONG C,et al.Boosting:an ensemble learning tool for compound classification and QSAR modeling [J].Journal of Chemical Information & Modeling,2005,45(3):786-799.
[24]FANG M.Study of integration method for multiple classifiers onensemble learning [J].Journal of Systems Engineering and Electronics,2006,28(11):1759-1761.(in Chinese)方敏.集成学习的多分类器动态融合方法研究[J].系统工程与电子技术,2006,28(11):1759-1761.
[25]GUTMAN D,CODELLA N C F,CELEBI E,et al.Skin Lesion Analysis toward Melanoma Detection:A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016,hosted by the International Skin Imaging Collaboration (ISIC) [J].ar-Xiv Preprint arXiv:1605.0139,2016.
[25]GUTMAN D,CODELLA N C F,CELEBI E,et al.Skin Lesion Analysis toward Melanoma Detection:A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016,hosted by the International Skin Imaging Collaboration (ISIC)[J].arXiv Preprint arXiv:1605.0139,2016.
[26]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep co olutional neural networks[C]∥Proceedings of the Advances in Neural Information Processing Systems.South Lake Tahoe,US:2012:1097-1105.
[27]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]∥Proceeding of IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2015:1-9.

相关文章 15

[1]	王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤. 不同数据增强方法对模型识别精度的影响 Influence of Different Data Augmentation Methods on Model Recognition Accuracy 计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210
[2]	常炳国, 石华龙, 常雨馨. 基于深度学习的黑色素瘤智能诊断多模型算法 Multi Model Algorithm for Intelligent Diagnosis of Melanoma Based on Deep Learning 计算机科学, 2022, 49(6A): 22-26. https://doi.org/10.11896/jsjkx.210500197
[3]	林夕, 陈孜卓, 王中卿. 基于不平衡数据与集成学习的属性级情感分类 Aspect-level Sentiment Classification Based on Imbalanced Data and Ensemble Learning 计算机科学, 2022, 49(6A): 144-149. https://doi.org/10.11896/jsjkx.210500205
[4]	康雁, 吴志伟, 寇勇奇, 张兰, 谢思宇, 李浩. 融合Bert和图卷积的深度集成学习软件需求分类 Deep Integrated Learning Software Requirement Classification Fusing Bert and Graph Convolution 计算机科学, 2022, 49(6A): 150-158. https://doi.org/10.11896/jsjkx.210500065
[5]	王宇飞, 陈文. 基于DECORATE集成学习与置信度评估的Tri-training算法 Tri-training Algorithm Based on DECORATE Ensemble Learning and Credibility Assessment 计算机科学, 2022, 49(6): 127-133. https://doi.org/10.11896/jsjkx.211100043
[6]	蔡欣雨, 冯翔, 虞慧群. 自适应权重的级联增强节点的宽度学习算法 Adaptive Weight Based Broad Learning Algorithm for Cascaded Enhanced Nodes 计算机科学, 2022, 49(6): 134-141. https://doi.org/10.11896/jsjkx.210500119
[7]	韩红旗, 冉亚鑫, 张运良, 桂婕, 高雄, 易梦琳. 基于共同子空间分类学习的跨媒体检索研究 Study on Cross-media Information Retrieval Based on Common Subspace Classification Learning 计算机科学, 2022, 49(5): 33-42. https://doi.org/10.11896/jsjkx.210200157
[8]	许华杰, 陈育, 杨洋, 秦远卓. 基于混合样本自动数据增强技术的半监督学习方法 Semi-supervised Learning Method Based on Automated Mixed Sample Data Augmentation Techniques 计算机科学, 2022, 49(3): 288-293. https://doi.org/10.11896/jsjkx.210100156
[9]	任首朋, 李劲, 王静茹, 岳昆. 基于集成回归决策树的lncRNA-疾病关联预测方法 Ensemble Regression Decision Trees-based lncRNA-disease Association Prediction 计算机科学, 2022, 49(2): 265-271. https://doi.org/10.11896/jsjkx.201100132
[10]	陈伟, 李杭, 李维华. 核小体定位预测的集成学习方法 Ensemble Learning Method for Nucleosome Localization Prediction 计算机科学, 2022, 49(2): 285-291. https://doi.org/10.11896/jsjkx.201100195
[11]	线岩团, 高凡雅, 相艳, 余正涛, 王剑. 融合多策略数据增强的低资源依存句法分析方法 Improving Low-resource Dependency Parsing Using Multi-strategy Data Augmentation 计算机科学, 2022, 49(1): 73-79. https://doi.org/10.11896/jsjkx.210900036
[12]	刘振宇, 宋晓莹. 一种可用于分类型属性数据的多变量回归森林 Multivariate Regression Forest for Categorical Attribute Data 计算机科学, 2022, 49(1): 108-114. https://doi.org/10.11896/jsjkx.201200189
[13]	周新民, 胡宜桂, 刘文洁, 孙荣俊. 基于多模态多层级数据融合方法的城市功能识别研究 Research on Urban Function Recognition Based on Multi-modal and Multi-level Data Fusion Method 计算机科学, 2021, 48(9): 50-58. https://doi.org/10.11896/jsjkx.210500220
[14]	许华杰, 张晨强, 苏国韶. 基于深层卷积残差网络的航拍图建筑物精确分割方法 Accurate Segmentation Method of Aerial Photography Buildings Based on Deep Convolutional Residual Network 计算机科学, 2021, 48(8): 169-174. https://doi.org/10.11896/jsjkx.200500096
[15]	暴雨轩, 芦天亮, 杜彦辉, 石达. 基于i_ResNet34模型和数据增强的深度伪造视频检测方法 Deepfake Videos Detection Method Based on i_ResNet34 Model and Data Augmentation 计算机科学, 2021, 48(7): 77-85. https://doi.org/10.11896/jsjkx.210300258

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed