Development and testing quantitative metrics from multi-parametric magnetic resonance imaging that predict Gleason score for prostate tumors

Quantitative Imaging in Medicine and Surgery

article

Rulon Mayer¹  Charles B. Simone II³  Baris Turkbey⁴  Peter Choyke⁴ 

[1] University of Pennsylvania;OncoScore;New York Proton Center;National Institutes of Health

关键词: Supervised target detection;    adaptive cosine estimator;    prostate cancer (PCa);    multi-parametric magnetic resonance imaging (multi-parametric MRI);    Gleason score;    histology of wholemount prostatectomy;   

DOI  :  10.21037/qims-21-761

学科分类：外科医学

来源: AME Publications

【 摘 要 】

Background: Radiologists currently subjectively examine multi-parametric magnetic resonance imaging (MRI) to detect possible clinically significant lesions using the Prostate Imaging Reporting and Data System (PI-RADS) protocol. The assessment of imaging, however, relies on the experience and judgement of radiologists creating opportunity for inter-reader variability. Quantitative metrics, such as z-score and signal to clutter ratio (SCR), are therefore needed. Methods: Multi-parametric MRI (T1, T2, diffusion, dynamic contrast-enhanced images) were resampled, rescaled, translated, and stitched to form spatially registered multi-parametric cubes for patients undergoing radical prostatectomy. Multi-parametric signatures that characterize prostate tumors were inserted into z-score and SCR. The multispectral covariance matrix was computed for the outlined normal prostate. The z-score from each MRI image was computed and summed. To reduce noise in the covariance matrix, following matrix decomposition, the noisy eigenvectors were removed. Also, regularization and modified regularization was applied to the covariance matrix by minimizing the discrimination score. The filtered and regularized covariance matrices were inserted into the SCR calculation. The z-score and SCR were quantitatively compared to Gleason scores from clinical pathology assessment of the histology of sectioned wholemount prostates. Results: Twenty-six consecutive patients were enrolled in this retrospective study. Median patient age was 60 years (range, 49 to 75 years), median prostate-specific antigen (PSA) was 5.8 ng/mL (range, 2.3 to 23.7 ng/mL), and median Gleason score was 7 (range, 6 to 9). A linear fit of the summed z-score against Gleason score found a correlation of R=0.48 and a P value of 0.015. A linear fit of the SCR from regularizing covariance matrix against Gleason score found a correlation of R=0.39 and a P value of 0.058. The SCR employing the modified regularizing covariance matrix against Gleason score found a correlation of R=0.52 and a P value of 0.007. A linear fit of the SCR from filtering out 3 and 4 eigenvectors from the covariance matrix against Gleason score found correlations of R=0.50 and 0.44, respectively, and P values of 0.011 and 0.027, respectively. Conclusions: Z-score and SCR using filtered and regularized covariance matrices derived from spatially registered multi-parametric MRI correlates with Gleason score with highly significant P values.

【 授权许可】

All Rights reserved