计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (16): 31-48.DOI: 10.3778/j.issn.1002-8331.2112-0125

• 热点与综述 • 上一篇    下一篇

皮肤肿瘤图像自动分类的研究进展

王慧,戚倩倩,李雪,孙卫佳,刘莹,姚春丽   

  1. 1.长春工业大学 计算机科学与工程学院,长春 130012
    2.吉林大学第二医院 皮肤科,长春 130041
  • 出版日期:2022-08-15 发布日期:2022-08-15

Research Progress in Automatic Classification of Skin Lesions Image

WANG Hui, QI Qianqian, LI Xue, SUN Weijia, LIU Ying, YAO Chunli   

  1. 1.College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China
    2.Department of Dermatology, The Second Hospital of Jilin University, Changchun 130041, China
  • Online:2022-08-15 Published:2022-08-15

摘要: 皮肤恶性肿瘤对患者健康有极大的威胁,由于现有诊断技术存在精准性差及有创操作等局限性,导致皮肤恶性肿瘤的临床诊断精度低,误诊率高,诊疗效率低下。使用计算机算法进行图像自动分类可以有效提高临床诊断效率。对近年来国内外相关研究工作进行了系统性归纳,总结了皮肤肿瘤图像自动分类模型常用的皮肤图像数据集和评估指标。对目前计算机技术在皮肤肿瘤诊断方面的常用模型及效果进行了详细的阐述,对比分析了各种方法的优势、局限及适用范围,并对未来发展趋势进行了展望。

关键词: 皮肤肿瘤, 人工智能, 皮肤图像分类, 智能诊断, 皮肤图像数据集

Abstract: Skin malignant lesions pose a great threat to patients’ health. Due to the limitations of existing diagnostic techniques such as poor accuracy and invasive operations, the clinical diagnosis of skin malignant lesions has low precision, high misdiagnosis rate, and low efficiency of diagnosis and treatment. The use of computer algorithms for automatic image classification can effectively improve the efficiency of clinical diagnosis. This paper systematically summarizes the related research work at home and abroad in recent years, and summarizes the skin image datasets and evaluation criteria commonly used for automatic skin lesion image classification model. The common models and effects of computer technology in skin lesion diagnosis are elaborated, the advantages, limitations and applicability of various methods are compared and analyzed, and the future development trend is prospected.

Key words: skin neoplasms, artificial intelligence, skin image classification, intelligent diagnosis, skin image dataset