Final Gleason Score Prediction Using Discriminant Analysis and Support Vector Machine Based on Preoperative Multiparametric MR Imaging of Prostate Cancer at 3T

Abstract

Objective. This study aimed at evaluating linear discriminant analysis (LDA) and support vector machine (SVM) classifiers for estimating final Gleason score preoperatively using multiparametric magnetic resonance imaging (mp-MRI) and clinical parameters. Materials and Methods. Thirty-three patients who underwent mp-MRI on a 3T clinical MR scanner and radical prostatectomy were enrolled in this study. The input features for classifiers were age, the presence of a palpable prostate abnormality, prostate specific antigen (PSA) level, index lesion size, and Likert scales of T2 weighted MRI (T2w-MRI), diffusion weighted MRI (DW-MRI), and dynamic contrast enhanced MRI (DCE-MRI) estimated by an experienced radiologist. SVM based recursive feature elimination (SVM-RFE) was used for eliminating features. Principal component analysis (PCA) was applied for data uncorrelation. Results. Using a standard PCA before final Gleason score classification resulted in mean sensitivities of 51.19% and 64.37% and mean specificities of 72.71% and 39.90% for LDA and SVM, respectively. Using a Gaussian kernel PCA resulted in mean sensitivities of 86.51% and 87.88% and mean specificities of 63.99% and 56.83% for LDA and SVM, respectively. Conclusion. SVM classifier resulted in a slightly higher sensitivity but a lower specificity than LDA method for final Gleason score prediction for prostate cancer for this limited patient population.

Prostate cancer classification with multiparametric MRI transfer learning model

“…Each case includes a T2w transaxial image, a T2w sagittal image, and an ADC map. The annotations include two‐class labels: clinically high‐grade cancer (Gleason score = 4 + 3, 4 + 4, 3 + 5, 5 + 3) and low‐grade cancer (Gleason score = 3 + 3, 3 + 4) . To be specific, our dataset consists of 123 cases with high‐grade cancer and 98 cases with low‐grade cancer.…”

“…Many methods have been proposed to classify prostate cancer. Most of them utilized conventional machine‐learning techniques, which typically extract low‐level radiomics features to characterize images and train a separate classifier . Fehr et al .…”

“…Secondly, different MRI sequences reveal different aspects of prostate cancer, and an effective way of integrating independent sets of information must be in place. For example, the apparent diffusion coefficient (ADC) values have negative correlation with the Gleason score of prostate carcinoma . T2‐weighted (T2w) sequence is optimal for depicting the zonal anatomy of the prostate and can be used for a detailed assessment of the prostatic fossa and seminal vesicles .…”

Development of a 2D Image Reconstruction and Viewing System for Histological Images from Multiple Tissue Blocks: Towards High-Resolution Whole-Organ 3D Histological Images

“…The JI will yield its maximum value, 1, when the source image A is the same as the reference image B, and 0 when the two binary images A and B are totally different. In our experiment, the binary images of the 2D reconstructed histology image (A) and gross image (B) were derived using discriminant analysis [26]. …”

Role of MRI in the Risk Assessment of Primary Prostate Cancer

“…52 There have been several approaches described to address this problem, including histogram and texture analysis 29,31,53 -55 and more advanced DWI-and post-processing techniques. [56][57][58]61 Although there has been some progress in reducing the overlap with some of these approaches, the problem is far from solved, and additional refinements or new approaches are warranted. An alternative use of the ADC-value is as a biological marker to predict the prognosis of PCa patients.…”