Deep Learning Network for Segmentation of the Prostate Gland With Median Lobe Enlargement in T2-weighted MR Images: Comparison With Manual Segmentation Method.

PURPOSE: Aim of this study was to evaluate a fully automated deep learning network named Efficient Neural Network (ENet) for segmentation of prostate gland with median lobe enlargement compared to manual segmentation. MATERIALS AND METHODS: One-hundred-three patients with median lobe enlargement on prostate MRI were retrospectively included. Ellipsoid formula, manual segmentation and automatic segmentation were used for prostate volume estimation using T2 weighted MRI images. ENet was used for automatic segmentation; it is a deep learning network developed for fast inference and high accuracy in augmented reality and automotive scenarios. Student t-test was performed to compare prostate volumes obtained with ellipsoid formula, manual segmentation, and automated segmentation. To provide an evaluation of the similarity or difference to manual segmentation, sensitivity, positive predictive value (PPV), dice similarity coefficient (DSC), volume overlap error (VOE), and volumetric difference (VD) were calculated. RESULTS: Differences between prostate volume obtained from ellipsoid formula versus manual segmentation and versus automatic segmentation were statistically significant (P < 0.049318 and P < 0.034305, respectively), while no statistical difference was found between volume obtained from manual versus automatic segmentation (P = 0.438045). The performance of ENet versus manual segmentations was good providing a sensitivity of 93.51%, a PPV of 87.93%, a DSC of 90.38%, a VOE of 17.32% and a VD of 6.85%. CONCLUSION: The presence of median lobe enlargement may lead to MRI volume overestimation when using the ellipsoid formula so that a segmentation method is recommended. ENet volume estimation showed great accuracy in evaluation of prostate volume similar to that of manual segmentation.

Radiomics and Prostate MRI: Current Role and Future Applications.

Multiparametric prostate magnetic resonance imaging (mpMRI) is widely used as a triage test for men at a risk of prostate cancer. However, the traditional role of mpMRI was confined to prostate cancer staging. Radiomics is the quantitative extraction and analysis of minable data from medical images; it is emerging as a promising tool to detect and categorize prostate lesions. In this paper we review the role of radiomics applied to prostate mpMRI in detection and localization of prostate cancer, prediction of Gleason score and PI-RADS classification, prediction of extracapsular extension and of biochemical recurrence. We also provide a future perspective of artificial intelligence (machine learning and deep learning) applied to the field of prostate cancer.

Role of apparent diffusion coefficient values in prostate diseases characterization on diffusion-weighted magnetic resonance imaging.

BACKGROUND: To evaluate if normal and pathological prostate tissue can be distinguished by using apparent diffusion coefficient (ADC) values on magnetic resonance imaging (MRI) and to understand if it is possible to differentiate among pathological prostate tissues using ADC values. METHODS: Our population consisted in 81 patients (mean age 65.4 years) in which 84 suspicious areas were identified. Regions of interest were placed over suspicious areas, detected on MRI, and over areas with normal appearance, and ADC values were recorded. Statistical differences between ADC values of suspicious and normal areas were evaluated. Histopathological diagnosis, obtained from targeted biopsy using MRI-US fusion biopsies in 39 patients and from prostatectomy in 42 patients, were correlated to ADC values. RESULTS: Histopathological diagnosis revealed 58 cases of prostate cancer (PCa), 19 patients with indolent PCa (Gleason Score ≤6) and 39 patients with clinically significant PCa (Gleason Score ≥7), 16 of high-grade prostatic intraepithelial neoplasia (HG-PIN) and 10 of atypical small acinar proliferation (ASAP). Significant statistical differences between mean ADC values of normal prostate tissue versus PCa (P<0.00001), HG-PIN (P<0.00001) and ASAP (P<0.00001) were found. Significant differences were observed between mean ADC values of PCa versus HG-PIN (P<0.00001) and ASAP (P<0.00001) with many overlapping values. Differences between mean ADC values of HG-PIN versus ASAP (P=0.015) were not significant. Significant differences of ADC values were also observed between patients with indolent and clinically significant PCa (P<0.00001). CONCLUSIONS: ADC values allow differentiation between normal and pathological prostate tissue and between indolent and clinically significant PCa but do not allow a definite differentiation between PCa, HG-PIN, and ASAP.

The cheating liver: imaging of focal steatosis and fatty sparing.

Focal steatosis and fatty sparing are a frequent finding in liver imaging, and can mimic solid lesions. Liver regional variations in the degree of fat accumulation can be related to vascular anomalies, metabolic disorders, use of certain drugs or coexistence of hepatic masses. CT and MRI are the modalities of choice for the noninvasive diagnosis of hepatic steatosis. Knowledge of CT and MRI appearance of focal steatosis and fatty sparing is crucial for an accurate diagnosis, and to rule-out other pathologic processes. This paper will review the CT and MRI techniques for the diagnosis of hepatic steatosis and the CT and MRI features of common and uncommon causes of focal steatosis and fatty sparing.