|Table of Contents|

Differential diagnosis of clinically significant prostate cancer using a machine learning model based on magnetic resonance apparent diffusion coefficient imaging

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2023 22
Page:
4202-4206
Research Field:
Publishing date:

Info

Title:
Differential diagnosis of clinically significant prostate cancer using a machine learning model based on magnetic resonance apparent diffusion coefficient imaging
Author(s):
LIN Xiangjin1; ZHU Guangbin1; 2; ZHANG Churuo3; DU Guoxin1; 2; LUO Jinwen1; 2; GUAN Yubao1; 2
1.The Fifth Clinical School,Guangzhou Medical University，Guangdong Guangzhou 510700,China;2.Department of Medical Imaging,the Fifth Affiliated Hospital of Guangzhou Medical University，Guangdong Guangzhou 510700,China;3.The Second Clinical School，Guangzhou Medical University，Guangdong Guangzhou 510700,China.
Keywords:
clinically significant prostate cancer; clinically insignificant prostate cancer; magnetic resonance imaging; apparent diffusion coefficient; machine learning model
PACS:
R737.25
DOI:
10.3969/j.issn.1672-4992.2023.22.019
Abstract:
Objective:To investigate the clinical application value of machine learning model based on magnetic resonance apparent diffusion coefficient imaging for clinically significant prostate cancer.Methods：Magnetic resonance examination data of 182 patients with prostate cancer confirmed by pathology from October,2017 to December,2022 in our hospital were retrospectively analyzed,including 126 cases of clinically significant prostate cancer (CsPCa),56 cases of clinically insignificant prostate cancer (CiPCa).ITK-SNAP software was used to segment the area of interest in magnetic resonance ADC image.Pyradiomics software package was used to extract the image omics features including First Order,Shape,GLCM,GLSZM,GLRLM,GLDM and NGTDM.The consistency test,the least absolute shrinkage and selection operator (LASSO) were used to select the best features.These patients were randomly divided into training group and verification group in a ratio of 7∶3.Build model of Logistic regression (LR).The area under the curve (AUC) was used to verify its value in differential diagnosis.Results：A total of 1 835 image omics features were extracted from ADC images.15 best features were selected to construct the Logistic regression machine learning model.The accuracy of training set and test set was 0.727 and 0.700 respectively.The area under the curve was 0.768 (95% confidence interval:0.700~0.837) and 0.719 (95% confidence interval:0.562~0.875) respectively.The specificity was 0.902 and 0.875 respectively.The positive prediction values were 0.683 and 0.636 respectively.The negative prediction values were 0.739 and 0.718 respectively.The accuracy was 0.683 and 0.636 respectively.Conclusion：The logistic regression machine learning model of magnetic resonance apparent diffusion coefficient imaging of prostate cancer provides potentially effective information for the identification of clinically significant prostate cancer.

References:

[1] 朱光斌,罗锦文,邓义,等.磁共振动态增强定量参数和ADC值对前列腺癌的临床诊断价值［J］.中国医学计算机成像杂志,2021,27(04):308-312. ZHU GB,LUO JW,DENG Y,et al.Diagnostic value of quantitative analysis of ADC value and DCE-MRI parameters for prostate cancer［J］.Chin Comput Med Imag,2021,27(04):308-312.
[2] BAJGIRAN AM,MIRAK SA,SUNG K,et al.Apparent diffusion coefficient (ADC) ratio versus conventional ADC for detecting clinically significant prostate cancer with 3-T MRI［J］.Am J Roentgenol,2019,213(3):W134-W142.
[3] UEDA T,OHNO Y,SHINOHARA M,et al.Reverse encoding distortion correction for diffusion-weighted MRI:efficacy for improving image quality and ADC evaluation for differentiating malignant from benign areas in suspected prostatic cancer patients［J］.Eur J Radiol,2023，162:110764.
[4]白铁阳,王心田,姜波,等.探讨1.5T磁共振动态增强扫描结合DWI和ADC在前列腺增生与前列腺癌鉴别诊断中的价值［J］.中国临床医学影像杂志,2022,33(02):127-129. BAI TY,WANG XT,JIANG B,et al.The diagnostic value of 1.5T dynamic contrast-enhanced magnetic resonance scanning combined with DWI and ADC in the differentiation of benign prostatic hyperplasia and prostatic cancer［J］.J Chin Clin Med Imaging,2022,33(02):127-129.
[5] XING P,CHEN L,YANG Q,et al.Differentiating prostate cancer from benign prostatic hyperplasia using whole-lesion histogram and texture analysis of diffusion- and T2-weighted imaging［J］.Cancer Imaging,2021,21(1):54.
[6] TAKAYAMA Y,KISHIMOTO R,HANAOKA S,et al.ADC value and diffusion tensor imaging of prostate cancer:changes in carbon-ion radiotherapy［J］.J Magn Reson Imaging,2008,27(6):1331-1335.
[7] 陈凤喜,冯俊榜,成杰,等.基于原发灶的磁共振ADC图、T2WI影像组学模型预测前列腺癌骨转移的价值［J］.磁共振成像,2023,14(02):61-67. CHEN FX,FENG JB,CHENG J,et al.The value of ADC map and T2WI radiomics analysis of the primary tumor for prediction of bone metastases in prostate cancer［J］.Chin J Magn Reson Imaging,2023,14(02):61-67.
[8] SHAISH H,KANG SK,ROSENKRANTZ AB.The utility of quantitative ADC values for differentiating high-risk from low-risk prostate cancer:a systematic review and meta-analysis［J］.Abdom Radiol (NY),2017,42(1):260-270.
[9] 黄松,盛伟华,李烨,等.MRI扩散加权定量参数ADC值与前列腺癌Gleason评分及血清PSA相关性分析［J］.中国CT和MRI杂志,2022,20(12):124-126. HUANG S,SHENG WH,LI Y,et al.Correlation analysis of MRI diffusion weighted imaging quantitative parameter ADC value,prostate cancer gleason score and serum PSA［J］.Chinese Journal of CT And MRI,2022,20(12):124-126.
[10] WOO S,KIM SY,CHO JY,et al.Preoperative evaluation of prostate cancer aggressiveness:using ADC and ADC ratio in determining Gleason score［J］.Am J Roentgenol,2016,207(1):114-120.
[11] HE D,WANG X,FU C,et al.MRI-based radiomics models to assess prostate cancer,extracapsular extension and positive surgical margins［J］.Cancer Imaging,2021,21(1):46.
[12] 王晴晴,代志清,刘高峰.T2WI联合ADC值诊断前列腺癌的价值及与危险程度、PSA的关系［J］.分子诊断与治疗杂志,2022,14(02):304-308. WANG QQ，DAI ZQ，LIU GF.Value of T2WI combined with ADC value in diagnosis of prostate cancer and its relationship with risk level and PSA［J］.J Mol Diagn Ther,2022,14(02):304-308.
[13] 郑丹,孙艳虹,吴娟.血清t-PSA、f-PSA、f-PSA/t-PSA及铁蛋白检测在前列腺癌诊断中的意义［J］.实验与检验医学,2018,36(04):578-581. ZHENG D,SUN YH,WU J.The significance of serum t-PSA,f-PSA,f-PSA/t-PSA,and ferritin detection in the diagnosis of prostate cancer［J］.Experimental and Laboratory Medicine,2018,36(04):578-581.
[14] WANG X,HIELSCHER T,RADTKE JP,et al.Comparison of single-scanner single-protocol quantitative ADC measurements to ADC ratios to detect clinically significant prostate cancer［J］.Eur J Radiol,2021,136:109538.
[15] 一诺,王雅菁,王鹏,等.磁共振表观扩散系数鉴别前列腺癌预后相关风险分层的应用研究［J］.磁共振成像,2022,13(12):104-110. YI N,WANG YJ,WANG P,et al.Application of MRI apparent diffusion coefficient in identifying prognostic risk stratification of prostate cancer［J］.Chin J Magn Reson Imaging,2022,13(12):104-110.
[16] 刘艳,徐青青,陆洋,等.基于T_2WI及ADC图影像组学模型对前列腺癌和前列腺增生的鉴别诊断价值［J］.临床放射学杂志,2021,40(11):2168-2173. LIU Y,XU QQ,LU Y,et al.The study on the value of radiomics model based on T2WI and ADC in distinguishing prostate cancer and benign prostatic hyperplasia［J］.Journal of Clinical Radiology,2021,40(11):2168-2173.

Memo

Memo:
广州医科大学科研能力提升计划(编号：02-410-2302087XM)；本科生创新能力提升项目(编号：02-408-2304-02XM)；广州医科大学第五临床学院本科生创新能力提升计划项目（编号：2022JXA011）
Last Update: 1900-01-01