法医学杂志

法医学杂志 ›› 2022, Vol. 38 ›› Issue (3): 350-354.DOI: 10.12116/j.issn.1004-5619.2020.201009

• 论著 • 上一篇    下一篇

基于数据挖掘算法的骨盆损伤判别模型

王飞翔1(), 姬锐2, 张鹿鸣3, 王鹏3, 刘太昂3, 宋鲁杰4, 汪茂文1, 周智露1,5, 郝虹霞1,6, 夏文涛1()   

  1. 1.司法鉴定科学研究院 上海市法医学重点实验室 司法部司法鉴定重点实验室 上海市司法鉴定专业技术服务平台，上海 200063
    2.武汉大学人民医院生殖医学中心，湖北 武汉 430072
    3.启东赢维信息科技有限公司，江苏 启东 226200
    4.上海交通大学附属第六人民医院，上海 200233
    5.贵州医科大学法医学院，贵州 贵阳 550009
    6.佳木斯大学基础医学院 微生态-免疫调节网络与相关疾病重点实验室，黑龙江 佳木斯 154007
  • 收稿日期:2020-10-21 发布日期:2022-06-25 出版日期:2022-06-28
  • 通讯作者: 夏文涛
  • 作者简介:夏文涛，男，研究员，主任法医师，主要从事法医临床学鉴定及研究；E-mail：xiawt@ssfjd.cn
    王飞翔（1980—），男，主任法医师，主要从事法医临床学鉴定及研究；E-mail：wangfx@ssfjd.cn
  • 基金资助:
    国家重点研发计划资助项目(2022YFC3302001);上海市法医学重点实验室资助项目(21DZ2270800);司法部司法鉴定重点实验室资助项目;上海市司法鉴定专业技术服务平台资助项目(19DZ2292700);国家标准资助项目(20214464-T-315)

Pelvic Injury Discriminative Model Based on Data Mining Algorithm

Fei-xiang WANG1(), Rui JI2, Lu-ming ZHANG3, Peng WANG3, Tai-ang LIU3, Lu-jie SONG4, Mao-wen WANG1, Zhi-lu ZHOU1,5, Hong-xia HAO1,6, Wen-tao XIA1()   

  1. 1.Shanghai Key Laboratory of Forensic Medicine，Key Laboratory of Forensic Science，Ministry of Justice，Shanghai Forensic Service Platform，Academy of Forensic Science，Shanghai 200063，China
    2.Reproductive Medical Center，People’s Hospital of Wuhan University，Wuhan 430072，China
    3.Qidong Yingwei Information Technology Co. ，Ltd. ，Qidong 226200，Jiangsu Province，China
    4.The Sixth People’s Hospital Affiliated to Shanghai Jiaotong University，Shanghai 200233，China
    5.Department of Forensic Medicine, Guizhou Medical University, Guizhou, 550009
    6.Key Laboratory of Microecology-immune Regulatory Network and Related Diseases, School of Basic Medicine, Jiamusi University, Kiamusze 154007, Heilongjiang Province, China
  • Received:2020-10-21 Online:2022-06-25 Published:2022-06-28
  • Contact: Wen-tao XIA

RichHTML

11

PDF (PC)

521

摘要：

目的 利用主成分分析、偏最小二乘法对基于骨盆CT图像提取的特性信息进行降维，利用降维的数据建立判别骨盆是否受伤的支持向量机分类判别模型，评估其应用的可行性。 方法 将采集的正常和受伤骨盆CT图像146例分别随机提取80%作为训练集，用于模型拟合；剩余20%作为测试集，用于模型准确性的检验。通过CT图像输入、图像预处理、特征提取、特征降维、特征选择、参数选择、模型建立和模型比较等步骤，建立骨盆是否受伤的判别模型。 结果 偏最小二乘法降维方法优于主成分分析降维方法，支持向量机模型优于朴素贝叶斯模型。基于12个偏最小二乘因子建立的骨盆是否受伤支持向量机分类判别模型的建模集、留一法交叉验证和测试集结果准确率分别为100%、100%和93.33%。 结论 基于CT图像建立的骨盆是否受伤数据挖掘模型在评估骨盆损伤中具有比较高的准确性，为骨盆损伤的自动快速识别奠定基础。

关键词: 法医学, 骨盆, 计算机体层成像, 主成分分析法, 偏最小二乘法, 支持向量机

Abstract:

Objective To reduce the dimension of characteristic information extracted from pelvic CT images by using principal component analysis （PCA） and partial least squares （PLS） methods. To establish a support vector machine （SVM） classification and identification model to identify if there is pelvic injury by the reduced dimension data and evaluate the feasibility of its application. Methods Eighty percent of 146 normal and injured pelvic CT images were randomly selected as training set for model fitting， and the remaining 20% was used as testing set to verify the accuracy of the test， respectively. Through CT image input， preprocessing， feature extraction， feature information dimension reduction， feature selection， parameter selection， model establishment and model comparison， a discriminative model of pelvic injury was established. Results The PLS dimension reduction method was better than the PCA method and the SVM model was better than the naive Bayesian classifier （NBC） model. The accuracy of the modeling set， leave-one-out cross validation and testing set of the SVM classification model based on 12 PLS factors was 100%， 100% and 93.33%， respectively. Conclusion In the evaluation of pelvic injury， the pelvic injury data mining model based on CT images reaches high accuracy， which lays a foundation for automatic and rapid identification of pelvic injuries.

Key words: forensic medicine, pelvis, computed tomography, principal component analysis, partial least squares, support vector machine

中图分类号: