留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

皮肤疾病辅助诊断系统中的数据与方法

杨怡光 王钧程 谢凤英 刘洁

杨怡光, 王钧程, 谢凤英, 刘洁. 皮肤疾病辅助诊断系统中的数据与方法[J]. 协和医学杂志, 2023, 14(1): 168-176. doi: 10.12290/xhyxzz.2022-0413
引用本文: 杨怡光, 王钧程, 谢凤英, 刘洁. 皮肤疾病辅助诊断系统中的数据与方法[J]. 协和医学杂志, 2023, 14(1): 168-176. doi: 10.12290/xhyxzz.2022-0413
YANG Yiguang, WANG Juncheng, XIE Fengying, LIU Jie. Data and Methods in Computer-aided Diagnosis Systems of Skin Diseases[J]. Medical Journal of Peking Union Medical College Hospital, 2023, 14(1): 168-176. doi: 10.12290/xhyxzz.2022-0413
Citation: YANG Yiguang, WANG Juncheng, XIE Fengying, LIU Jie. Data and Methods in Computer-aided Diagnosis Systems of Skin Diseases[J]. Medical Journal of Peking Union Medical College Hospital, 2023, 14(1): 168-176. doi: 10.12290/xhyxzz.2022-0413

皮肤疾病辅助诊断系统中的数据与方法

doi: 10.12290/xhyxzz.2022-0413
基金项目: 

国家自然科学基金 61871011

国家自然科学基金 62071011

国家自然科学基金 82173449

国家自然科学基金 61971443

中央高水平医院临床科研业务费 2022-PUMCH-B-092

中国医学科学院医学与健康科技创新工程 2022-I2M-C & T-A-007

详细信息
    通讯作者:

    谢凤英, E-mail: xfy_73@buaa.edu.cn

    刘洁, E-mail:Liujie04672@pumch.cn

    杨怡光、 王钧程对本文同等贡献

    杨怡光、 王钧程对本文同等贡献

  • 中图分类号: R751;R44

Data and Methods in Computer-aided Diagnosis Systems of Skin Diseases

Funds: 

National Natural Science Foundation of China 61871011

National Natural Science Foundation of China 62071011

National Natural Science Foundation of China 82173449

National Natural Science Foundation of China 61971443

National High Level Hospital Clinical Research Funding 2022-PUMCH-B-092

CAMS Innovation Fund for Medical Sciences 2022-I2M-C & T-A-007

More Information
  • 摘要: 皮肤疾病具有发病率高、诊断困难、危害程度大的特点,加之我国医疗资源短缺,严重影响人们的身体健康和生活质量。近年来,随着计算机辅助诊断(computer-aided diagnosis, CAD)技术的快速发展,基于皮肤镜图像的单模态CAD技术突破了传统诊断方法主观性强且易漏诊、误诊的局限性,但该技术无法充分利用临床诊断场景中的多模态数据优势。而多模态融合CAD技术可帮助人工智能模型学习更加复杂全面的临床特征表达,从而辅助皮肤科医生进行更加精准的诊断。本文在CAD技术常用的数据类型、基于单模态/多模态数据的CAD技术等方面对皮肤疾病CAD系统的研究现状进行综述,并提出未来发展方向,以期为缓解皮肤病诊断困境提供新思路。
    作者贡献:杨怡光和王钧程负责查阅文献、论文撰写及修订;谢凤英和刘洁负责选题设计和论文审校。
    利益冲突:所有作者均声明不存在利益冲突
  • 图  1  皮肤疾病计算机辅助诊断系统

    A.皮肤镜图像采集装置;B. 自动计算机辅助诊断系统界面

    图  2  皮肤影像技术图像

    A.皮肤临床图像;B.皮肤镜图像;C.高频超声图像;D.反射式共聚焦显微镜图像

    图  3  皮肤组织病理表现

    A.表皮病变;B.真皮病变;C.皮下组织病变

    图  4  基于传统机器学习的计算机辅助诊断流程图

    图  5  基于深度学习的计算机辅助诊断流程图

    图  6  双模态皮损影像融合网络框架

    图  7  多模态皮损数据融合网络框架

  • [1] 田燕, 刘玮. 皮肤屏障[J]. 实用皮肤病学杂志, 2013, 6: 346-348. https://www.cnki.com.cn/Article/CJFDTOTAL-SYPF201306012.htm
    [2] 邹先彪. 皮肤影像学与人工智能[J]. 中国医学前沿杂志, 2019, 11: 1-4. https://www.cnki.com.cn/Article/CJFDTOTAL-YXQY201908001.htm
    [3] 田红, 肖桂芝, 田苗, 等. 黑色素瘤治疗药物的研究进展[J]. 现代药物与临床, 2015, 30: 890-896. https://www.cnki.com.cn/Article/CJFDTOTAL-GWZW201507030.htm
    [4] Peng D, Sun J, Wang J, et al. Burden of Skin Disease-China, 1990—2019[J]. China CDC Wkly, 2021, 3: 472. doi:  10.46234/ccdcw2021.123
    [5] Schmid-Saugeon P, Guillod J, Thiran J. Towards a computer-aided diagnosis system for pigmented skin lesions[J]. Comput Med Imaging Graph, 2003, 27: 65-78. doi:  10.1016/S0895-6111(02)00048-4
    [6] Micali G, Lacarrubba F, Massimino D, et al. Dermatos-copy: alternative uses in daily clinical practice[J]. J Am Acad Dermatol, 2011, 64: 1135-1146. doi:  10.1016/j.jaad.2010.03.010
    [7] 崔勇, 杨森, 张学军. 数码技术与皮肤病学[J]. 临床皮肤科杂志, 2008, 37: 61-62. https://www.cnki.com.cn/Article/CJFDTOTAL-LCPF200801042.htm
    [8] 谢凤英. 皮肤镜图像处理技术[M]. 北京: 电子工业出版社, 2015.
    [9] 刘洁, 邹先彪. 实用皮肤镜学[M]. 北京: 人民卫生出版社, 2021.
    [10] Lallas A, Zalaudek I, Argenziano G, et al. Running head: Dermoscopy in general dermatology[J]. Dermatol Clin, 2013, 31: 679-694. doi:  10.1016/j.det.2013.06.008
    [11] 涂鹏, 张群霞. 高频超声在皮肤疾病中的研究进展[J]. 临床超声医学杂志, 2013, 15: 3. https://www.cnki.com.cn/Article/CJFDTOTAL-LCCY201312019.htm
    [12] Kak AC, Slaney M. Principles of computerized tomographic imaging[M]. Soc Ind Appl Math, 2001.
    [13] 肖佳, 郭爱元, 黄健, 等. 反射式共聚焦激光扫描显微镜在皮肤科的应用[J]. 中国麻风皮肤病杂志, 2016, 32: 567-569. https://www.cnki.com.cn/Article/CJFDTOTAL-MALA201609029.htm
    [14] 何黎. 皮肤影像技术概况、应用现状及前景[J]. 皮肤科学通报, 2016, 33: 29-37. https://www.cnki.com.cn/Article/CJFDTOTAL-ZYXW201601009.htm
    [15] 唐莎. 头面部皮肤癌放射治疗的护理[J]. 临床和实验医学杂志, 2008, 7: 1. https://www.cnki.com.cn/Article/CJFDTOTAL-SYLC200806141.htm
    [16] 刘淋红, 李忻悦, 李灵. 1002例皮肤恶性肿瘤回顾性分析[J]. 四川医学, 2021, 42: 444-447. https://www.cnki.com.cn/Article/CJFDTOTAL-SCYX202105003.htm
    [17] 张翰林, 杨子涵, 王远卓, 等. 玫瑰痤疮共病的研究进展[J]. 基础医学与临床, 2021, 41: 1502-1506. https://www.cnki.com.cn/Article/CJFDTOTAL-JCYL202110018.htm
    [18] 中国医疗保健国际交流促进会皮肤科分会, 中国医疗保健国际交流促进会华夏皮肤影像人工智能协作组. 黑素细胞肿瘤皮肤镜特征及组织病理特征相关性专家共识(2020)[J]. 中华皮肤科杂志, 2020, 53: 859-868.
    [19] Kothari S, Phan JH, Stokes TH, et al. Pathology imaging informatics for quantitative analysis of whole-slide images[J]. J Am Med Inform Assoc, 2013, 20: 1099-1108.
    [20] 周思淼. 基于深度学习的基底细胞癌病理图像识别方法研究[D]. 沈阳: 沈阳工业大学, 2021.
    [21] Sankarapandian S, Kohn S, Spurrier V, et al. A pathology deep learning system capable of triage of melanoma specimens utilizing dermatopathologist consensus as ground truth[C]. IEEE International Conference Computer Vision (ICCV). 2021: 629-638.
    [22] 邹先彪. 皮肤镜在皮肤病诊断上的价值[C]. 2012全国中西医结合皮肤性病学术会议论文汇编. 2012: 38.
    [23] 谢凤英, 刘洁, 崔勇, 等. 皮肤镜图像计算机辅助诊断技术[J]. 中国医学文摘: 皮肤科学, 2016, 33: 45-50. https://www.cnki.com.cn/Article/CJFDTOTAL-ZYXW201601011.htm
    [24] Emre Celebi M, Kingravi HA, Iyatomi H, et al. Border detection in dermoscopy images using statistical region merging[J]. Skin Res Technol, 2008, 14: 347-353.
    [25] Xie F, Bovik AC. Automatic segmentation of dermoscopy images using self-generating neural networks seeded by genetic algorithm[J]. Pattern Recognit, 2013, 46: 1012-1019.
    [26] Kasmi R, Mokrani K, Rader RK, et al. Biologically inspired skin lesion segmentation using a geodesic active contour technique[J]. Skin Res Technol, 2016, 22: 208-222.
    [27] Fan H, Xie F, Li Y, et al. Automatic segmentation of dermoscopy images using saliency combined with Otsu threshold[J]. Comput Biol Med, 2017, 85: 75-85.
    [28] Celebi ME, Kingravi HA, Uddin B, et al. A methodological approach to the classification of dermoscopy images[J]. Comput Med Imaging Graph, 2007, 31: 362-373.
    [29] Capdehourat G, Corez A, Bazzano A, et al. Toward a combined tool to assist dermatologists in melanoma detection from dermoscopic images of pigmented skin lesions[J]. Pattern Recognit Lett, 2011, 32: 2187-2196.
    [30] Ferris LK, Harkes JA, Gilbert B, et al. Computer-aided classification of melanocytic lesions using dermoscopic images[J]. J Am Acad Dermatol, 2015, 73: 769-776.
    [31] Xie F, Fan H, Li Y, et al. Melanoma Classification on Dermoscopy Images Using a Neural Network Ensemble Model[J]. IEEE Trans Med Imaging, 2017, 36: 849-858.
    [32] 周航宁, 谢凤英, 姜志国, 等. 基于深度学习的皮肤影像分类[J]. 协和医学杂志, 2018, 9: 15-18. doi:  10.3969/j.issn.1674-9081.2018.01.004
    [33] Nasr-Esfahani E, Samavi S, Karimi N, et al. Melanoma detection by analysis of clinical images using convolutional neural network[C]. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016: 1373-1376.
    [34] Yu L, Chen H, Dou Q, et al. Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks[J]. IEEE Trans Med Imaging, 2017, 36: 994-1004.
    [35] Adegun AA, Viriri S. Deep learning-based system for automatic melanoma detection[J]. IEEE Access, 2019, 8: 7160-7172.
    [36] Jojoa Acosta MF, Caballero Tovar LY, Garcia-Zapirain MB, et al. Melanoma diagnosis using deep learning techniques on dermatoscopic images[J]. BMC Med Imaging, 2021, 21: 1-11.
    [37] Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 542: 115-118.
    [38] Gessert N, Sentker T, Madesta F, et al. Skin lesion classification using cnns with patch-based attention and diagnosis-guided loss weighting[J]. IEEE Trans Biomed Eng, 2019, 67: 495-503.
    [39] Yang Y, Wang J, Xie F, et al. A Convolutional Neural Network Trained with Dermoscopic Images of Psoriasis Performed on par with 230 Dermatologists[J]. Comput Biol Med, 2021: 104924.
    [40] Wang G, Li W, Ourselin S, et al. Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks[C]. International MICCAI brainlesion workshop, 2017: 178-190.
    [41] Zhou C, Ding C, Lu Z, et al. One-pass multi-task convolutional neural networks for efficient brain tumor segmentation[C]. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2018: 637-645.
    [42] Dolz J, Gopinath K, Yuan J, et al. HyperDense-Net: a hyper-densely connected CNN for multi-modal image segmentation[J]. IEEE Trans Med Imaging, 2018, 38: 1116-1126.
    [43] Iandola F, Moskewicz M, Karayev S, et al. DenseNet: Implementing efficient convnet descriptor pyramids[J]. Eprint Arxiv, 2014.
    [44] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]. International Conference on Medical image computing and computer-assisted intervention, 2015: 234-241.
    [45] Dolz J, Desrosiers C, Ben Ayed I. IVD-Net: Intervertebral disc localization and segmentation in MRI with a multi-modal UNet[C]. International workshop and challenge on computational methods and clinical applications for spine imaging, 2018: 130-143.
    [46] Kamnitsas K, Bai W, Ferrante E, et al. Ensembles of multiple models and architectures for robust brain tumour segmentation[C]. International MICCAI brainlesion workshop, 2017: 450-462.
    [47] Yap J, Yolland W, Tschandl P. Multimodal skin lesion classification using deep learning[J]. Exp Dermatol, 2018, 27: 1261-1267.
    [48] Bi L, Feng DD, Fulham M, et al. Multi-label classifica-tion of multi-modality skin lesion via hyper-connected convolutional neural network[J]. Pattern Recognit, 2020, 107: 107502.
    [49] Kawahara J, Daneshvar S, Argenziano G, et al. Seven-point checklist and skin lesion classification using multitask multimodal neural nets[J]. IEEE J Biomed Health Inform, 2018, 23: 538-546.
    [50] Tang P, Yan X, Nan Y, et al. FusionM4Net: A multi-stage multi-modal learning algorithm for multi-label skin lesion classification[J]. Med Image Anal, 2022, 76: 102307.
    [51] 王诗琪, 刘洁, 朱晨雨, 等. 皮肤科医师与深度卷积神经网络诊断色素痣和脂溢性角化病皮肤镜图像比较[J]. 中华皮肤科杂志, 2018, 51: 486-489.
    [52] Zhu CY, Wang YK, Chen HP, et al. A deep learning based framework for diagnosing multiple skin diseases in a clinical environment[J]. Front Med, 2021, 8: 626369.
    [53] 刘兆睿, 张漪澜, 谢凤英, 等. 基于皮肤镜图像智能分析的早期蕈样肉芽肿诊断模型构建[J]. 协和医学杂志, 2021, 12: 689-697. doi:  10.12290/xhyxzz.2021-0496
    [54] Zhang Y, Tino P, Leonardis A, et al. A survey on neural network interpretability[J]. IEEE Trans Emerg Top Comput Intell, 2021, PP: 1-17.
  • 加载中
图(7)
计量
  • 文章访问数:  472
  • HTML全文浏览量:  65
  • PDF下载量:  60
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-07-31
  • 录用日期:  2022-08-08
  • 网络出版日期:  2022-12-30
  • 刊出日期:  2023-01-30

目录

    /

    返回文章
    返回

    【温馨提醒】近日,《协和医学杂志》编辑部接到作者反映,有多名不法人员冒充期刊编辑发送见刊通知,鼓动作者添加微信,从而骗取版面费的行为。特提醒您,本刊与作者联系的方式均为邮件通知或电话,稿件进度通知邮箱为:mjpumch@126.com,编辑部电话为:010-69154261,请提高警惕,谨防上当受骗!如有任何疑问,请致电编辑部核实。谢谢!