Signal Intensity of High B-value Diffusion-weighted Imaging for the Detection of Prostate Cancer

The Classification Power of Classical and Intra-voxel Incoherent Motion (IVIM) Fitting Models of Diffusion-weighted Magnetic Resonance Images: An Experimental Study

This study aims at investigating the classification power of different b-values of the diffusion-weighted magnetic resonance images (DWI) as indicator of prostate cancer. This paper investigates several techniques for analyzing data from DWI acquired at a range of b-values for the purpose of detecting prostate cancer. In the first phase of experiments, we analyze the available data by producing two main parametric maps using two common models, namely: the intra-voxel incoherent motion (IVIM) model and the mono-exponential ADC model. Accordingly, we evaluated the benign/malignant tissue classification potential of several parametric maps produced using different combinations of b-values and fitting models. In the second phase, we utilized the maps that performed best in the first phase of experiments to design a machine learning-based computer-assisted diagnosis system for the detection of early stage prostate cancer. The system performance was cross-validated using data from 20 patients. On a fivefold cross-validation scheme, a maximum accuracy and an area under the receiver operating characteristic (AUC) of 90% and 0.978, respectively, was achieved by a system that uses ADC maps fitted using the mono-exponential model at 11 different b-values. The results suggest that the proposed machine learning-based diagnosis system is potentially powerful in differentiating between malignant and benign prostate tissues when combined with carefully generated ADC maps.

Detection of High-Grade Prostate Cancer With a Super High B-value (4000 s/mm2) in Diffusion-Weighted Imaging Sequences by Magnetic Resonance Imaging

Introduction: High-grade adenocarcinoma of the prostate tends to have denser glandular structures and a prominent desmoplastic reaction, which could be detected by magnetic resonance imaging (MRI) with a super-high b-value in diffusion-weighted imaging (DWI) sequence, to differentiate it from low-grade carcinomas.

Objective: To evaluate the diagnostic validity of the diffusion sequence with values ​​of b4000 s/mm2 for the diagnosis of high-grade prostate cancer (Gleason score ≥ 7).

Materials and methods: It is a retrospective analytical study of male patients who have undergone a prostate biopsy and count with a prostate MRI with a DWI sequence of a super-high b-value (4000 s/mm2).

Results: The sensitivity of the diffusion sequence with b4000 s/mm2 values ​​to classify as positive for prostate cancer was 57.14% as compared to biopsy. The specificity of the diffusion sequence with b4000 s/mm2 values ​​classifying patients with prostate carcinoma as negative was 84.62%. The probability that the diffusion sequence with b4000 s/mm2 values ​​classifies patients with prostate cancer was 80%. The probability that the diffusion sequence with b4000 s/mm2 values ​​does not classify patients with prostate cancer was 64.71%. The proportion of patients adequately classified with prostate cancer using the diffusion sequence with b4000 s/mm2 values ​​was 70.37%.

Conclusions: The study shows that using the diffusion sequence with values of b4000 s/mm2 is an optimal value that serves as a tool to be able to decant those high-risk carcinomas with those of low risk; however, it is not a definitive method of diagnosis that could replace the performance of a biopsy. Since the study sample was limited, these results cannot be interpreted as reliable for diagnosing high-grade prostate cancer and should encourage future studies on a larger scale population to obtain significant evidence for a non-invasive diagnostic tool with a better cost-benefit for the patient.