Deep Learning-Based Post-Processing of Real-Time MRI to Assess and Quantify Dynamic Wrist Movement in Health and Disease.

Karl Ludger Radke,Dirk Klee,Simon Thelen,Gerald Antoch,Christoph Schleich,Miriam Frenken,Justus Schock,Hans-Jörg Wittsack,Anja Müller-Lutz,Lena Marie Wollschläger,Jens Frahm,Sven Nebelung,Daniel Benjamin Abrar,Matthias Boschheidgen

doi:10.3390/diagnostics11061077

Abstract

While morphologic magnetic resonance imaging (MRI) is the imaging modality of choice for the evaluation of ligamentous wrist injuries, it is merely static and incapable of diagnosing dynamic wrist instability. Based on real-time MRI and algorithm-based image post-processing in terms of convolutional neural networks (CNNs), this study aims to develop and validate an automatic technique to quantify wrist movement. A total of 56 bilateral wrists (28 healthy volunteers) were imaged during continuous and alternating maximum ulnar and radial abduction. Following CNN-based automatic segmentations of carpal bone contours, scapholunate and lunotriquetral gap widths were quantified based on dedicated algorithms and as a function of wrist position. Automatic segmentations were in excellent agreement with manual reference segmentations performed by two radiologists as indicated by Dice similarity coefficients of 0.96 ± 0.02 and consistent and unskewed Bland–Altman plots. Clinical applicability of the framework was assessed in a patient with diagnosed scapholunate ligament injury. Considerable increases in scapholunate gap widths across the range-of-motion were found. In conclusion, the combination of real-time wrist MRI and the present framework provides a powerful diagnostic tool for dynamic assessment of wrist function and, if confirmed in clinical trials, dynamic carpal instability that may elude static assessment using clinical-standard imaging modalities.

Highlights

Intercarpal ligament injuries are frequent clinical entities, lead to malalignment of the carpal bones, and constitute the most common cause of carpal instability [1,2,3,4], increasing the risk of developing osteoarthritis [5,6]
Automatic segmentations of the carpus and forearm were in excellent agreement with the manual reference segmentations
Based on the linear mixed model (LMM), we found that in the healthy volunteers, the factors wrist angle, side, and height significantly influenced the SL or LT gap widths, respectively, across the ROM (Table S2)

Summary

Introduction

Intercarpal ligament injuries are frequent clinical entities, lead to malalignment of the carpal bones, and constitute the most common cause of carpal instability [1,2,3,4], increasing the risk of developing osteoarthritis [5,6]. In clinical MRI exams, the wrist is immobilized to prevent movement artefacts and insufficient image quality and, imaged in a merely static configuration, which renders the diagnosis of complex carpal instability patterns impossible [1]. To overcome these diagnostic shortcomings, several dynamic and fast-imaging techniques have been introduced such as parallel imaging methods such as generalized autocalibrating partial parallel acquisition (GRAPPA) [11] and sensitivity encoding (SENSE) [12], undersampling techniques combined with special image reconstruction pipelines such as k-t

Objectives

Methods

Results

Discussion

Conclusion