Premium
Risk Stratification of Prostate Cancer Using the Combination of Histogram Analysis of Apparent Diffusion Coefficient Across Tumor Diffusion Volume and Clinical Information: A Pilot Study
Author(s) -
Zhang Zhao,
Xu Huazhi,
Xue Yingnan,
Li Jiance,
Ye Qiong
Publication year - 2019
Publication title -
journal of magnetic resonance imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.563
H-Index - 160
eISSN - 1522-2586
pISSN - 1053-1807
DOI - 10.1002/jmri.26235
Subject(s) - effective diffusion coefficient , medicine , receiver operating characteristic , prostate cancer , confidence interval , logistic regression , nuclear medicine , percentile , mann–whitney u test , prostatectomy , mathematics , magnetic resonance imaging , statistics , radiology , cancer
Background The effectiveness of quantitative MRI and clinical information in the risk stratification of prostate cancer (PCa) patients was evaluated separately in previous research; however, the differentiation power of combining quantitative MRI and clinical information has yet to be investigated. Purpose To investigate the power of combining histogram analysis of apparent diffusion coefficient (ADC) of tumor diffusion volume (tDv) with clinical information for the differentiation of low‐grade (Gleason score [GS] ≤6) and high‐grade (GS ≥7) PCa. Study Type Retrospective. Population Fifty‐nine PCa patients who underwent preoperative diffusion‐weighted imaging (DWI) (acquired with b = 0, 1000 mm 2 /s) and followed by radical prostatectomy within 6 months. Sequences T 2 ‐weighted, DWI, and ADC images at 3.0T. Assessment tDv defined with different ADC thresholds were analyzed for each patient and combined with age and prostate‐specific antigen (PSA) level. Binary logistic regression with backward feature selection was applied to determine the best discrimination and corresponding combination of parameters. Statistical Tests Kolmogorov–Smirnov test; independent samples t ‐test; Mann–Whitney U ‐test; Spearman's rank correlation; receiver operating characteristic (ROC) analysis; binary logistical regression. Results PSA and the 10 th percentile ADC value of tDv defined with different diffusion thresholds were significantly different between low‐grade and high‐grade PCa groups ( P < 0.05 for all). Median ADC of tDv based on a threshold of 1.008 × 10 −3 mm 2 /s exhibited the best performance (AUC = 0.86, 95% confidence interval [CI]: 0.75–0.94), whereas binary logistic regression with backward feature selection achieved 97.20% accuracy with AUC = 0.978 (95% CI: 0.929–0.997). Data Conclusion The discriminatory power of a single histogram variable of ADC in tDv was not significantly superior to that of a single clinical parameter. The combination of histogram analysis of ADC of tDv and clinical information using logistic regression might significantly improve the risk stratification of PCa and achieve reasonably high accuracy. Level of Evidence: 4 Technical Efficacy : Stage 2 J. Magn. Reson. Imaging 2019;49:556–564.