Fully automated quantification of in vivo viscoelasticity of prostate zones using magnetic resonance elastography with Dense U-net segmentation.

Magnetic resonance elastography (MRE) for measuring viscoelasticity heavily depends on proper tissue segmentation, especially in heterogeneous organs such as the prostate. Using trained network-based image segmentation, we investigated if MRE data suffice to extract anatomical and viscoelastic information for automatic tabulation of zonal mechanical properties of the prostate. Overall, 40 patients with benign prostatic hyperplasia (BPH) or prostate cancer (PCa) were examined with three magnetic resonance imaging (MRI) sequences: T2-weighted MRI (T2w), diffusion-weighted imaging (DWI), and MRE-based tomoelastography, yielding six independent sets of imaging data per patient (T2w, DWI, apparent diffusion coefficient, MRE magnitude, shear wave speed, and loss angle maps). Combinations of these data were used to train Dense U-nets with manually segmented masks of the entire prostate gland (PG), central zone (CZ), and peripheral zone (PZ) in 30 patients and to validate them in 10 patients. Dice score (DS), sensitivity, specificity, and Hausdorff distance were determined. We found that segmentation based on MRE magnitude maps alone (DS, PG: 0.93 ± 0.04, CZ: 0.95 ± 0.03, PZ: 0.77 ± 0.05) was more accurate than magnitude maps combined with T2w and DWI_b (DS, PG: 0.91 ± 0.04, CZ: 0.91 ± 0.06, PZ: 0.63 ± 0.16) or T2w alone (DS, PG: 0.92 ± 0.03, CZ: 0.91 ± 0.04, PZ: 0.65 ± 0.08). Automatically tabulated MRE values were not different from ground-truth values (P>0.05). In conclusion, MRE combined with Dense U-net segmentation allows tabulation of quantitative imaging markers without manual analysis and independent of other MRI sequences and can thus contribute to PCa detection and classification.

Automatic prostate and prostate zones segmentation of magnetic resonance images using DenseNet-like U-net.

Magnetic resonance imaging (MRI) provides detailed anatomical images of the prostate and its zones. It has a crucial role for many diagnostic applications. Automatic segmentation such as that of the prostate and prostate zones from MR images facilitates many diagnostic and therapeutic applications. However, the lack of a clear prostate boundary, prostate tissue heterogeneity, and the wide interindividual variety of prostate shapes make this a very challenging task. To address this problem, we propose a new neural network to automatically segment the prostate and its zones. We term this algorithm Dense U-net as it is inspired by the two existing state-of-the-art tools-DenseNet and U-net. We trained the algorithm on 141 patient datasets and tested it on 47 patient datasets using axial T2-weighted images in a four-fold cross-validation fashion. The networks were trained and tested on weakly and accurately annotated masks separately to test the hypothesis that the network can learn even when the labels are not accurate. The network successfully detects the prostate region and segments the gland and its zones. Compared with U-net, the second version of our algorithm, Dense-2 U-net, achieved an average Dice score for the whole prostate of 92.1± 0.8% vs. 90.7 ± 2%, for the central zone of [Formula: see text]% vs. [Formula: see text] %, and for the peripheral zone of 78.1± 2.5% vs. [Formula: see text]%. Our initial results show Dense-2 U-net to be more accurate than state-of-the-art U-net for automatic segmentation of the prostate and prostate zones.

In Vivo Quantification of Water Diffusion, Stiffness, and Tissue Fluidity in Benign Prostatic Hyperplasia and Prostate Cancer.

OBJECTIVES: Water diffusion, tissue stiffness, and viscosity characterize the biophysical behavior of tumors. However, little is known about how these parameters correlate in prostate cancer (PCa). Therefore, we paired tomoelastography of the prostate with diffusion-sensitive magnetic resonance imaging for the quantitative mapping of biophysical parameters in benign prostatic hyperplasia (BPH) and PCa. MATERIALS AND METHODS: Multifrequency magnetic resonance imaging elastography with tomoelastography processing was performed at 60, 70, and 80 Hz using externally placed compressed-air drivers. Shear-wave speed (SWS) and loss angle (φ) were analyzed as surrogate markers of stiffness and viscosity-related fluidity in the normal peripheral zone (PZ), hyperplastic transition zone (TZ), which is consistent with BPH, and PCa lesions. The SWS and φ were correlated with the normalized apparent diffusion coefficient (nADC). RESULTS: Thirty-nine men (median age/range, 67/49-88 years), 25 with BPH and 14 with biopsy-proven PCa, were prospectively enrolled in this institutional review board-approved study. The SWS in PCa (3.1 ± 0.6 m/s) was higher than in TZ (2.8 ± 0.3 m/s, P = 0.004) or tended to be higher than in PZ (2.8 ± 0.4 m/s, P = 0.025). Similarly, φ in PCa (1.1 ± 0.1 rad) was higher than in TZ (0.9 ± 0.2 m/s, P < 0.001) and PZ (0.9 ± 0.1 rad, P < 0.001), whereas nADC in PCa (1.3 ± 0.3) was lower than in TZ (2.2 ± 0.4, P < 0.001) and PZ (3.1 ± 0.7, P < 0.001). Pooled nADC was inversely correlated with φ (R = -0.6, P < 0.001) but not with SWS. TZ and PZ only differed in nADC (P < 0.001) but not in viscoelastic properties. Diagnostic differentiation of PCa from normal prostate tissues, as assessed by area under the curve greater than 0.9, was feasible using nADC and φ but not SWS. CONCLUSIONS: Tomoelastography provides quantitative maps of tissue mechanical parameters of the prostate. Prostate cancer is characterized by stiff tissue properties and reduced water diffusion, whereas, at the same time, tissue fluidity is increased, suggesting greater mechanical friction inside the lesion. This biophysical signature correlates with known histopathological features including increased cell density and fibrous protein accumulation.

Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network.

OBJECTIVE: To present a deep learning-based approach for semi-automatic prostate cancer classification based on multi-parametric magnetic resonance (MR) imaging using a 3D convolutional neural network (CNN). METHODS: Two hundred patients with a total of 318 lesions for which histological correlation was available were analyzed. A novel CNN was designed, trained, and validated using different combinations of distinct MRI sequences as input (e.g., T2-weighted, apparent diffusion coefficient (ADC), diffusion-weighted images, and K-trans) and the effect of different sequences on the network's performance was tested and discussed. The particular choice of modeling approach was justified by testing all relevant data combinations. The model was trained and validated using eightfold cross-validation. RESULTS: In terms of detection of significant prostate cancer defined by biopsy results as the reference standard, the 3D CNN achieved an area under the curve (AUC) of the receiver operating characteristics ranging from 0.89 (88.6% and 90.0% for sensitivity and specificity respectively) to 0.91 (81.2% and 90.5% for sensitivity and specificity respectively) with an average AUC of 0.897 for the ADC, DWI, and K-trans input combination. The other combinations scored less in terms of overall performance and average AUC, where the difference in performance was significant with a p value of 0.02 when using T2w and K-trans; and 0.00025 when using T2w, ADC, and DWI. Prostate cancer classification performance is thus comparable to that reported for experienced radiologists using the prostate imaging reporting and data system (PI-RADS). Lesion size and largest diameter had no effect on the network's performance. CONCLUSION: The diagnostic performance of the 3D CNN in detecting clinically significant prostate cancer is characterized by a good AUC and sensitivity and high specificity. KEY POINTS: • Prostate cancer classification using a deep learning model is feasible and it allows direct processing of MR sequences without prior lesion segmentation. • Prostate cancer classification performance as measured by AUC is comparable to that of an experienced radiologist. • Perfusion MR images (K-trans), followed by DWI and ADC, have the highest effect on the overall performance; whereas T2w images show hardly any improvement.