Application evaluation of DCE‑MRI combined with quantitative analysis of DWI for the diagnosis of prostate cancer

Abstract

The present study aimed to investigate the value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) combined with quantitative analysis of diffusion weighted imaging (DWI) for the diagnosis of prostate cancer (PCa). A total of 81 patients with prostatic diseases, including PCa (n=44) and benign prostatic hyperplasia (BPH, n=37), were imaged with T1 weighted imaging (T1WI), T2 weighted imaging (T2WI), DWI and DCE-MRI. The blood vessel permeability parameters volume transfer rate constant (K trans ), back flow rate constant (K ep ), extravascular extracellular space volume fraction (V e ), plasma volume fraction (V p ) and apparent diffusion coefficient (ADC) were measured, and compared between the two groups. The efficiency of these tools for the diagnosis of PCa was analyzed by receiver operating characteristic curve analysis. The efficiency of ADC combined with blood vessel permeability parameters in the diagnosis of PCa was analyzed by logistic regression. The correlation between these parameters and the Gleason score was evaluated by Spearman correlation analysis in the PCa group. The results demonstrated that, compared with the BPH group, K trans , K ep , V e and V p were higher, and ADC was lower in the PCa group (P<0.05). The combination of K ep and ADC offered the highest diagnosis efficiency [area under the curve (AUC=0.939)]. However, the combination of three parameters did not significantly improve the diagnostic efficiency. A subtle improvement in diagnostic efficiency was observed when four parameters (K trans + K ep + V e + ADC) were combined (AUC=0.940), which was significantly higher than with one parameter. The ADC value of the PCa group was negatively correlated with the primary Gleason pattern, secondary Gleason pattern and the total Gleason score in PCa (r=−0.665, −0.456 and −0.714, respectively; P<0.001). The V p in the PCa group was slightly negatively correlated with the primary Gleason pattern of PCa (r=−0.385; P<0.05); however, no significant correlation was found with secondary Gleason pattern and the total Gleason score. The present study revealed that the combination of DCE-MRI quantitative analysis and DWI was efficient for PCa diagnosis. This may be because DCE-MRI and DWI can noninvasively detect water motility in tumor tissues and alterations in permeability during tumor neovascularization. The present study demonstrated that K ep and ADC values may be used as predictive parameters for PCa diagnosis, which may help differentiate benign from malignant prostate lesions.

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.…”

“…Those studies [44][45][46][47][48][49][50][51][52][53][54] employed multiple lesions for each patient enrolled in the study. Subgroup 2 gathered those studies [55][56][57][58][59] that enrolled two distinct groups (PCa and controls) and employed a patient-based ML approach. The heterogeneity in the subgroups was greater than 70% (subgroup 1: P<.001, subgroup 2: P=.002).…”

“…Accuracy measures of radiomic studies for the systematic review. ANN: artificial neural networks; LDA: linear discriminant analysis; RF: random forest; SNCSAE: stacked nonnegativity constraint sparse autoencoders; LR: logistic regression; DCNN: deep convolutional neural networks; LASSO: least absolute shrinkage and selection operator; DNN: deep neural networks; SVM: support vector machine; CART: classification and regression tree.Figure3shows the subgroup analysis among studies that employed internal cross-validation techniques (subgroup 1)[46][47][48][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).…”

68Ga-PSMA-11 PET/CT combining ADC value of MRI in the diagnosis of naive prostate cancer

“…These findings were consistent with other studies. [ 27 – 30 ] SUV max /ADC may be used as a predictive parameter for PCa, to help distinguish benign from malignant prostatic lesions.…”