期刊文献+

基于机器学习方法的前列腺癌DWI多参数分析及其应用 被引量:1

Multi-Parameter Analysis and Application of Diffusion Weighted Imaging in Prostate Cancer Based on Machine Learning
下载PDF
导出
摘要 探究使用机器学习方法,提升对扩散加权成像(DWI)多参数图的前列腺癌(PCa)诊断的准确性。对39例前列腺癌患者、56例良性患者,进行磁共振扩散加权图像的采集,并使用传统单指数模型(Mono)、拉伸指数模型(SEM)、弥散张量成像(DTI)模型、弥散峰度成像(DKI)模型以及体内素不相干运动扩散(IVIM)模型等5种重建模型,得到共计16个参数图,而后对于每一个参数图进行直方图分析,得到相关图像特征后使用机器学习的方法进行分类。使用支持向量机和随机森林两种分类器对前列腺病变进行良恶性分类,随机森林分类器的AUC值可以达到0.98,具有较高的分类性能。另外,对特征进行重要性排序后,发现DKI参数图是肿瘤分类的重要指标。
作者 孙晓梦 万遂人 Sun Xiaomeng;Wan Suiren(School of Biomedical Engineering,Southeast University Nanjing 210096,China)
出处 《中国生物医学工程学报》 CAS CSCD 北大核心 2019年第4期508-512,共5页 Chinese Journal of Biomedical Engineering
关键词 扩散加权成像 前列腺癌 机器学习 diffusion weighted imaging prostate cancer machine learning
  • 相关文献

参考文献5

二级参考文献52

  • 1张继斌,沈钧康,许建铭,李晓兵,须同禄,陆之安,秦明明.前列腺癌MR灌注成像与肿瘤血管生成相关性研究[J].临床放射学杂志,2004,23(6):485-488. 被引量:14
  • 2Zhang J,Jing H,Han X,Huang Z,Cao Z,Liu Q.Diffusionweighted imaging of prostate cancer on 3T MR:Relationship between apparent diffusion coefficient values and Ki-67expression. Academic Radiology . 2013
  • 3Tamada T,Kanomata N,Sone T,Jo Y,Miyaji Y,Higashi H,Yamamoto A,Ito K.High b-value (2,000 s/mm2)diffusionweighted magnetic resonance imaging in prostate cancer at 3Tesla:comparison with 1,000 s/mm2 for tumor conspicuity and discrimination of aggressiveness. PLo S One . 2014
  • 4Suo S,Chen X,Wu L,Zhang X,Yao Q,Fan Y,Wang H,Xu J.Non-Gaussian water diffusion kurtosis imaging of prostate cancer. Magnetic Resonance Imaging . 2014
  • 5Kuru TH,Roethke MC,Stieltjies B,et al.Intravoxel incoherent motion IVIM diffusion imaging in prostate cancer-what does it add. Journal of Computer Assisted Tomography . 2014
  • 6Li C,Chen M,Li S,et al.Detection of prostate cancer in peripheral zone:comparison of MR diffusion tensor imaging,quantitative dynamic contrast-enhanced MRI,and the two techniques combined at 3.0 T. Acta Radiologica . 2014
  • 7Rosenkrantz AB1,Prabhu V,Sigmund EE, et al.Utility of diffusional kurtosis imaging as a marker of adverse pathologic outcomes among prostate cancer active surveillance candidates undergoing radical prostatectomy. American Journal of Roentgenology . 2013
  • 8Th?rmer Gregor,Otto Josephin,Reiss-Zimmermann Martin,Seiwerts Matthias,Moche Michael,Garnov Nikita,Franz Toni,Do Minh,Stolzenburg Jens-Uwe,Horn Lars-Christian,Kahn Thomas,Busse Harald.Diagnostic value of ADC in patients with prostate cancer: influence of the choice of b values. European Radiology . 2012
  • 9Tamura C,Shinmoto H,Soga S,et al.Diffusion kurtosis imaging study of prostate cancer:preliminary findings. Journal of magnetic resonance imaging . 2014
  • 10Vargas HA,Akin 0,Franiel T,et al.Diffusion-weighted endorectal MR imaging at 3 T for prostate cancer:tumor detection and assessment of aggressiveness. Radiology . 2011

共引文献52

同被引文献11

引证文献1

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部