Voxel‐level Classification of Prostate Cancer on Magnetic Resonance Imaging: Improving Accuracy Using Four‐Compartment Restriction Spectrum Imaging

Abstract

Background Diffusion magnetic resonance imaging (MRI) is integral to detection of prostate cancer (PCa), but conventional apparent diffusion coefficient (ADC) cannot capture the complexity of prostate tissues and tends to yield noisy images that do not distinctly highlight cancer. A four‐compartment restriction spectrum imaging (RSI4) model was recently found to optimally characterize pelvic diffusion signals, and the model coefficient for the slowest diffusion compartment, RSI4‐C1, yielded greatest tumor conspicuity. Purpose To evaluate the slowest diffusion compartment of a four‐compartment spectrum imaging model (RSI4‐C1) as a quantitative voxel‐level classifier of PCa. Study Type Retrospective. Subjects Forty‐six men who underwent an extended MRI acquisition protocol for suspected PCa. Twenty‐three men had benign prostates, and the other 23 men had PCa. Field Strength/Sequence A 3 T, multishell diffusion‐weighted and axial T2‐weighted sequences. Assessment High‐confidence cancer voxels were delineated by expert consensus, using imaging data and biopsy results. The entire prostate was considered benign in patients with no detectable cancer. Diffusion images were used to calculate RSI4‐C1 and conventional ADC. Classifier images were also generated. Statistical Tests Voxel‐level discrimination of PCa from benign prostate tissue was assessed via receiver operating characteristic (ROC) curves generated by bootstrapping with patient‐level case resampling. RSI4‐C1 was compared to conventional ADC for two metrics: area under the ROC curve (AUC) and false‐positive rate for a sensitivity of 90% (FPR90). Statistical significance was assessed using bootstrap difference with two‐sided α = 0.05. Results RSI4‐C1 outperformed conventional ADC, with greater AUC (mean 0.977 [95% CI: 0.951–0.991] vs. 0.922 [0.878–0.948]) and lower FPR90 (0.032 [0.009–0.082] vs. 0.201 [0.132–0.290]). These improvements were statistically significant (P < 0.05). Data Conclusion RSI4‐C1 yielded a quantitative, voxel‐level classifier of PCa that was superior to conventional ADC. RSI classifier images with a low false‐positive rate might improve PCa detection and facilitate clinical applications like targeted biopsy and treatment planning. Evidence Level 3 Technical Efficacy Stage 2

Correcting B0 inhomogeneity-induced distortions in whole-body diffusion MRI of bone

“…For DWI b-value images that were collected in multiple directions (i.e., b -value images 500, 1000, 2000) volumes for each b -value were averaged prior to the analysis detailed below. All DWI volumes were also corrected for gradient non-linearity and eddy currents 20 – 23 .…”

ReIGNITE RT Boost: An international study testing the accuracy and feasibility of using restriction spectrum imaging (RSI) MRI to guide intraprostatic tumor target volume for radiotherapy boost

“…We previously developed a quantitative diffusion MRI biomarker for PCa, called the Restriction Spectrum Imaging restriction score (RSIrs), that significantly improves diagnostic utility over conventional MRI. 6,7 RSI is a sophisticated but practical approach that models tissue microcompartments to highlight the restricted intracellular diffusion characteristic of higher-grade PCa. 8 We hypothesized that using RSIrs maps would improve radiation oncologists' accuracy for PCa tumor delineation.…”

Optimal protocol design for diffusion-weighted imaging of the prostate: an estimation theory examination of parameter estimate variance

“…Diffusion-weighted imaging (DWI) is routinely used to aid in the detection and characterization of prostate cancer (1). While conventional DWI remains largely limited to assessment of relative signal intensity and monoexponential apparent diffusion coefficient (ADC), sophisticated multicompartmental modeling techniques better quantify physiologically meaningful parameters from DWI data (2)(3)(4)(5)(6). Compared to conventional DWI, these multicompartmental approaches require more scan time per patient in order to obtain measurements at additional b-values and/or echo times (TEs).…”