Simplified Luminal Water Imaging for the Detection of Prostate Cancer From Multiecho T₂ MR Images

Abstract

Background Luminal water imaging (LWI) suffers less from imaging artifacts than the diffusion‐weighted imaging used in multiparametric MRI of the prostate. LWI obtains multicompartment tissue information from a multiecho T2 dataset. Purpose To compare a simplified LWI technique with apparent diffusion coefficient (ADC) in classifying lesions based on groupings of PI‐RADS v2 scores. Secondary aims were to investigate whether LWI differentiates between histologically confirmed tumor and normal tissue as effectively as ADC, and whether LWI is correlated with the multicompartment parameters of the vascular, extracellular, and restricted diffusion for cytometry in tumors (VERDICT) diffusion model. Study Type A subset of a larger prospective study. Population In all, 65 male patients aged 49–79 were scanned. Field Strength/Sequence A 32‐echo T2 and a six b‐value diffusion sequence (0, 90, 500, 1500, 2000, 3000 s/mm2) at 3T. Assessment Regions of interest were placed by a board‐certified radiologist in areas of lesion and benign tissue and given PI‐RADS v2 scores. Statistical Tests Receiver operating characteristic and logistic regression analyses were performed. Results LWI classifies tissue as PI‐RADS 1,2 or PI‐RADS 3,4,5 with an area under curve (AUC) value of 0.779, compared with 0.764 for ADC. LWI differentiated histologically confirmed malignant from nonmalignant tissue with AUC, sensitivity, and specificity values of 0.81, 75%, and 87%, compared with 0.75, 83%, and 67% for ADC. The microstructural basis of the LWI technique is further suggested by the correspondence with the VERDICT diffusion‐based microstructural imaging technique, with α, A1, A2, and LWF showing significant correlations. Data Conclusion LWI alone can predict PI‐RADS v2 score groupings and detect histologically confirmed tumors with an ability similar to ADC alone without the limitations of diffusion‐weighted MRI. This is important, given that ADC has an advantage in these tests as it already informs PI‐RADS v2 scoring. LWI also provides multicompartment information that has an explicit biophysical interpretation, unlike ADC. Level of Evidence: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:910–917.

Radiomic and Genomic Machine Learning Method Performance for Prostate Cancer Diagnosis: Systematic Literature Review

“…Figure 3 shows the subgroup analysis among studies that employed internal cross-validation techniques (subgroup 1) [ 46 - 49 , 51 , 54 , 55 , 59 ], split validation approaches (subgroup 2) [ 44 , 50 , 52 , 53 , 56 , 57 ], and no validation (subgroup 3) [ 45 , 58 ]. The heterogeneity for subgroups 1 and 2 was around 80% ( P <.001).…”

“…Figure 4 shows the subgroup analysis for regression-based models (subgroup 1) [ 45 , 48 , 49 , 51 , 56 - 58 ], tree-based models (subgroup 2) [ 46 , 53 , 59 ], and DL methods (subgroup 3) [ 44 , 47 , 50 , 52 , 55 ]. One study was not included [ 54 ], as it was the only study employing a support vector machine model.…”

“…A data set was defined as unbalanced if it had more than 30% of the total observations in one specific class rather than the other (PCa and controls) and did not apply any correction on performance (eg, synthetic minority oversampling technique [SMOTE] or voting techniques). The heterogeneity of subgroup 1 [ 36 , 44 , 51 , 53 ] was around 58% ( P =.005). As a result, among the several covariates, the imbalance covariate was the only one by which the heterogeneity could be partially resolved.…”

“…Therefore, Devine et al [ 51 ], Wang et al [ 36 ], Mazaheri et al [ 53 ], and Zhao et al [ 44 ] were excluded from the coupled forest plot ( Figure 7 ).…”

Joint estimation of relaxation and diffusion tissue parameters for prostate cancer grading with relaxation-VERDICT MRI

“…However, VERDICT is currently limited in estimating only diffusion parameters without accounting for the inherent relaxation properties of the tissue. (12)(13)(14)(15)(16)(17)(18)(19) This leads to questionable accuracy of microstructural parameters, which likely limits their sensitivity. In addition to the potential of diffusion parameters, relaxometry parameters such as T2 relaxation time have also shown capability to discriminate Gleason grades 3 and 4.…”