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

Nader Aldoj,Patrick Asbach,Ingolf Sack,Anja Hennemuth,Marc Dewey,Federico Biavati

doi:10.1038/s41598-022-05878-5

Abstract

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.

Highlights

Magnetic resonance elastography (MRE) for measuring viscoelasticity heavily depends on proper tissue segmentation, especially in heterogeneous organs such as the prostate
The purpose of this study was to test whether MRE-based tomoelastography data are sufficient to extract anatomic and viscoelastic information for automatic tabulation of zonal mechanical properties of the prostate and to compare MRE-based image segmentation with information extracted by convolutional neural networks (CNNs) from other magnetic resonance imaging (MRI) pulse sequences typically acquired in clinical practice
Our study shows that Dense U-net segmentation of prostate zones based on MRE data allows automated tabulation of quantitative imaging markers for the total prostate and for the central and peripheral zones

Summary

Introduction

Magnetic resonance elastography (MRE) for measuring viscoelasticity heavily depends on proper tissue segmentation, especially in heterogeneous organs such as the prostate. 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. The purpose of this study was to test whether MRE-based tomoelastography data are sufficient to extract anatomic and viscoelastic information for automatic tabulation of zonal mechanical properties of the prostate and to compare MRE-based image segmentation with information extracted by CNNs from other MRI pulse sequences typically acquired in clinical practice

Objectives

Methods

Conclusion