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

High-resolution volumetric dynamic magnetic resonance imaging of the wrist using an 8-channel flexible receive coil

OBJECTIVE

Real-time imaging is useful for the evaluation of wrist instability. However, currently available real-time magnetic resonance imaging (MRI) methods are limited due to their 2D nature or provide insufficient temporal resolution and image quality for quantitative kinematic analysis. This work introduces a novel approach for volumetric dynamic MRI of the wrist joint during active motion and demonstrates the feasibility of tracking carpal bone motion.

MATERIALS AND METHODS

A flexible 8-element 3 T wrist receive coil and 3D-printed support platform for guiding motion were designed for dynamic wrist imaging. 2D real-time images were acquired using a fat-saturated FLASH sequence with radial sampling and reconstructed with the GRASP algorithm. Corresponding volumetric dynamic wrist images were obtained by assembling 2D real-time images into 3D snapshots using autodetected MRI-visible markers for slice alignment. The proposed method was demonstrated for radial-ulnar deviation on five healthy volunteers.

RESULTS

The flexible wrist coil provided high SNR while allowing a wide range of wrist movements. 2D real-time wrist images were acquired with a temporal resolution of 48 ms/frame with negligible streaking artifacts. Carpal bones and metacarpal bones were properly aligned in the assembled dynamic volumes for all five subjects. The excellent bone-to-tissue contrast enabled accurate segmentation of the individual carpal bones on the assembled dynamic volumes.

CONCLUSION

This work introduces a novel wrist coil and demonstrates that real-time volumetric dynamic examination of the moving wrist is feasible. The achieved image quality and high temporal resolution could enable automatic segmentation of carpal bones and quantitative kinematic assessment for evaluating wrist instability.

Measurement of Scapholunate Joint Space Width on Real-Time MRI-A Feasibility Study

INTRODUCTION

The scapholunate interosseous ligament is pivotal for wrist stability, and its impairment can result in instability and joint degeneration. This study explores the application of real-time MRI for dynamic assessment of the scapholunate joint during wrist motion with the objective of determining its diagnostic value in efficacy in contrast to static imaging modalities.

MATERIALS AND METHODS

Ten healthy participants underwent real-time MRI scans during wrist ab/adduction and fist-clenching maneuvers. Measurements were obtained at proximal, medial, and distal landmarks on both dynamic and static images with statistical analyses conducted to evaluate the reliability of measurements at each landmark and the concordance between dynamic measurements and established static images. Additionally, inter- and intraobserver variabilities were evaluated.

RESULTS

Measurements of the medial landmarks demonstrated the closest agreement with static images and exhibited the least scatter. Distal landmark measurements showed a similar level of agreement but with increased scatter. Proximal landmark measurements displayed substantial deviation, which was accompanied by an even greater degree of scatter. Although no significant differences were observed between the ab/adduction and fist-clenching maneuvers, both inter- and intraobserver variabilities were significant across all measurements.

CONCLUSIONS

This study highlights the potential of real-time MRI in the dynamic assessment of the scapholunate joint particularly at the medial landmark. Despite promising results, challenges such as measurement variability need to be addressed. Standardization and integration with advanced image processing methods could significantly enhance the accuracy and reliability of real-time MRI, paving the way for its clinical implementation in dynamic wrist imaging studies.

Artificial intelligence powered advancements in upper extremity joint MRI: A review

Magnetic resonance imaging (MRI) is an indispensable medical imaging examination technique in musculoskeletal medicine. Modern MRI techniques achieve superior high-quality multiplanar imaging of soft tissue and skeletal pathologies without the harmful effects of ionizing radiation. Some current limitations of MRI include long acquisition times, artifacts, and noise. In addition, it is often challenging to distinguish abutting or closely applied soft tissue structures with similar signal characteristics. In the past decade, Artificial Intelligence (AI) has been widely employed in musculoskeletal MRI to help reduce the image acquisition time and improve image quality. Apart from being able to reduce medical costs, AI can assist clinicians in diagnosing diseases more accurately. This will effectively help formulate appropriate treatment plans and ultimately improve patient care. This review article intends to summarize AI's current research and application in musculoskeletal MRI, particularly the advancement of DL in identifying the structure and lesions of upper extremity joints in MRI images.

Dynamic assessment of scapholunate ligament status by real-time magnetic resonance imaging: an exploratory clinical study

OBJECTIVE

Clinical-standard MRI is the imaging modality of choice for the wrist, yet limited to static evaluation, thereby potentially missing dynamic instability patterns. We aimed to investigate the clinical benefit of (dynamic) real-time MRI, complemented by automatic analysis, in patients with complete or partial scapholunate ligament (SLL) tears.

MATERIAL AND METHODS

Both wrists of ten patients with unilateral SLL tears (six partial, four complete tears) as diagnosed by clinical-standard MRI were imaged during continuous active radioulnar motion using a 1.5-T MRI scanner in combination with a custom-made motion device. Following automatic segmentation of the wrist, the scapholunate and lunotriquetral joint widths were analyzed across the entire range of motion (ROM). Mixed-effects model analysis of variance (ANOVA) followed by Tukey's posthoc test and two-way ANOVA were used for statistical analysis.

RESULTS

With the increasing extent of SLL tear, the scapholunate joint widths in injured wrists were significantly larger over the entire ROM compared to those of the contralateral healthy wrists (p<0.001). Differences between partial and complete tears were most pronounced at 5°-15° ulnar abduction (p<0.001). Motion patterns and trajectories were altered. Complete SLL deficiency resulted in complex alterations of the lunotriquetral joint widths.

CONCLUSION

Real-time MRI may improve the functional diagnosis of SLL insufficiency and aid therapeutic decision-making by revealing dynamic forms of dissociative instability within the proximal carpus. Static MRI best differentiates SLL-injured wrists at 5°-15° of ulnar abduction.

Evaluation of a newly designed deep learning-based algorithm for automated assessment of scapholunate distance in wrist radiography as a surrogate parameter for scapholunate ligament rupture and the correlation with arthroscopy

PURPOSE

Not diagnosed or mistreated scapholunate ligament (SL) tears represent a frequent cause of degenerative wrist arthritis. A newly developed deep learning (DL)-based automated assessment of the SL distance on radiographs may support clinicians in initial image interpretation.

MATERIALS AND METHODS

A pre-trained DL algorithm was specifically fine-tuned on static and dynamic dorsopalmar wrist radiography (training data set n = 201) for the automated assessment of the SL distance. Afterwards the DL algorithm was evaluated (evaluation data set n = 364 patients with n = 1604 radiographs) and correlated with results of an experienced human reader and with arthroscopic findings.

RESULTS

The evaluation data set comprised arthroscopically diagnosed SL insufficiency according to Geissler's stages 0-4 (56.5%, 2.5%, 5.5%, 7.5%, 28.0%). Diagnostic accuracy of the DL algorithm on dorsopalmar radiography regarding SL integrity was close to that of the human reader (e.g. differentiation of Geissler's stages ≤ 2 versus > 2 with a sensitivity of 74% and a specificity of 78% compared to 77% and 80%) with a correlation coefficient of 0.81 (P < 0.01).

CONCLUSION

A DL algorithm like this might become a valuable tool supporting clinicians' initial decision making on radiography regarding SL integrity and consequential triage for further patient management.

Deep Learning-Based Denoising of CEST MR Data: A Feasibility Study on Applying Synthetic Phantoms in Medical Imaging

Chemical Exchange Saturation Transfer (CEST) magnetic resonance imaging (MRI) provides a novel method for analyzing biomolecule concentrations in tissues without exogenous contrast agents. Despite its potential, achieving a high signal-to-noise ratio (SNR) is imperative for detecting small CEST effects. Traditional metrics such as Magnetization Transfer Ratio Asymmetry (MTRasym) and Lorentzian analyses are vulnerable to image noise, hampering their precision in quantitative concentration estimations. Recent noise-reduction algorithms like principal component analysis (PCA), nonlocal mean filtering (NLM), and block matching combined with 3D filtering (BM3D) have shown promise, as there is a burgeoning interest in the utilization of neural networks (NNs), particularly autoencoders, for imaging denoising. This study uses the Bloch-McConnell equations, which allow for the synthetic generation of CEST images and explores NNs efficacy in denoising these images. Using synthetically generated phantoms, autoencoders were created, and their performance was compared with traditional denoising methods using various datasets. The results underscored the superior performance of NNs, notably the ResUNet architectures, in noise identification and abatement compared to analytical approaches across a wide noise gamut. This superiority was particularly pronounced at elevated noise intensities in the in vitro data. Notably, the neural architectures significantly improved the PSNR values, achieving up to 35.0, while some traditional methods struggled, especially in low-noise reduction scenarios. However, the application to the in vivo data presented challenges due to varying noise profiles. This study accentuates the potential of NNs as robust denoising tools, but their translation to clinical settings warrants further investigation.

Methodology for quantitative evaluation of mandibular condyles motion symmetricity from real-time MRI in the axial plane

Diagnosis of temporomandibular disorders is currently based on clinical examination and static MRI. Real-time MRI enables tracking of condylar motion and, thus, evaluation of their motion symmetricity (which could be associated with temporomandibular joint disorders). The purpose of this work is to propose an acquisition protocol, an image processing approach, and a set of parameters enabling objective assessment of motion asymmetry; to check the reliability and find the limitations of the approach, and to verify if the automatically calculated parameters are associated with the motion symmetricity. A rapid radial FLASH sequence was used to acquire a dynamic set of axial images for 10 subjects. One more subject was involved to estimate the dependence of the motion parameters on the slice placement. The images were segmented with a semi-automatic approach based on U-Net convolutional neural network, and the condyles' mass centers were projected on the mid-sagittal axis. Resulting projection curves were used for the extraction of various motion parameters including latency, velocity peak delay, and maximal displacement between the right and the left condyle. These automatically calculated parameters were compared with the physicians' scores. The proposed segmentation approach allowed a reliable center of mass tracking. Latency and velocity peak delay were found to be invariant to the slice position, and maximal displacement difference considerably varied. The automatically calculated parameters demonstrated a significant correlation with the experts' scores. The proposed acquisition and data processing protocol enables the automatizable extraction of quantitative parameters that characterize the symmetricity of condylar motion.

AI-driven and automated MRI sequence optimization in scanner-independent MRI sequences formulated by a domain-specific language

Introduction

The complexity of Magnetic Resonance Imaging (MRI) sequences requires expert knowledge about the underlying contrast mechanisms to select from the wide range of available applications and protocols. Automation of this process using machine learning (ML) can support the radiologists and MR technicians by complementing their experience and finding the optimal MRI sequence and protocol for certain applications.

Methods

We define domain-specific languages (DSL) both for describing MRI sequences and for formulating clinical demands for sequence optimization. By using various abstraction levels, we allow different key users exact definitions of MRI sequences and make them more accessible to ML. We use a vendor-independent MRI framework (gammaSTAR) to build sequences that are formulated by the DSL and export them using the generic file format introduced by the Pulseq framework, making it possible to simulate phantom data using the open-source MR simulation framework JEMRIS to build a training database that relates input MRI sequences to output sets of metrics. Utilizing ML techniques, we learn this correspondence to allow efficient optimization of MRI sequences meeting the clinical demands formulated as a starting point.

Results

ML methods are capable of capturing the relation of input and simulated output parameters. Evolutionary algorithms show promising results in finding optimal MRI sequences with regards to the training data. Simulated and acquired MRI data show high correspondence to the initial set of requirements.

Discussion

This work has the potential to offer optimal solutions for different clinical scenarios, potentially reducing exam times by preventing suboptimal MRI protocol settings. Future work needs to cover additional DSL layers of higher flexibility as well as an optimization of the underlying MRI simulation process together with an extension of the optimization method.

Adaptive IoU Thresholding for Improving Small Object Detection: A Proof-of-Concept Study of Hand Erosions Classification of Patients with Rheumatic Arthritis on X-ray Images

In recent years, much research evaluating the radiographic destruction of finger joints in patients with rheumatoid arthritis (RA) using deep learning models was conducted. Unfortunately, most previous models were not clinically applicable due to the small object regions as well as the close spatial relationship. In recent years, a new network structure called RetinaNets, in combination with the focal loss function, proved reliable for detecting even small objects. Therefore, the study aimed to increase the recognition performance to a clinically valuable level by proposing an innovative approach with adaptive changes in intersection over union (IoU) values during training of Retina Networks using the focal loss error function. To this end, the erosion score was determined using the Sharp van der Heijde (SvH) metric on 300 conventional radiographs from 119 patients with RA. Subsequently, a standard RetinaNet with different IoU values as well as adaptively modified IoU values were trained and compared in terms of accuracy, mean average accuracy (mAP), and IoU. With the proposed approach of adaptive IoU values during training, erosion detection accuracy could be improved to 94% and an mAP of 0.81 ± 0.18. In contrast Retina networks with static IoU values achieved only an accuracy of 80% and an mAP of 0.43 ± 0.24. Thus, adaptive adjustment of IoU values during training is a simple and effective method to increase the recognition accuracy of small objects such as finger and wrist joints.

Performance of a deep convolutional neural network for MRI-based vertebral body measurements and insufficiency fracture detection

OBJECTIVES

The aim is to validate the performance of a deep convolutional neural network (DCNN) for vertebral body measurements and insufficiency fracture detection on lumbar spine MRI.

METHODS

This retrospective analysis included 1000 vertebral bodies in 200 patients (age 75.2 ± 9.8 years) who underwent lumbar spine MRI at multiple institutions. 160/200 patients had ≥ one vertebral body insufficiency fracture, 40/200 had no fracture. The performance of the DCNN and that of two fellowship-trained musculoskeletal radiologists in vertebral body measurements (anterior/posterior height, extent of endplate concavity, vertebral angle) and evaluation for insufficiency fractures were compared. Statistics included (a) interobserver reliability metrics using intraclass correlation coefficient (ICC), kappa statistics, and Bland-Altman analysis, and (b) diagnostic performance metrics (sensitivity, specificity, accuracy). A statistically significant difference was accepted if the 95% confidence intervals did not overlap.

RESULTS

The inter-reader agreement between radiologists and the DCNN was excellent for vertebral body measurements, with ICC values of > 0.94 for anterior and posterior vertebral height and vertebral angle, and good to excellent for superior and inferior endplate concavity with ICC values of 0.79-0.85. The performance of the DCNN in fracture detection yielded a sensitivity of 0.941 (0.903-0.968), specificity of 0.969 (0.954-0.980), and accuracy of 0.962 (0.948-0.973). The diagnostic performance of the DCNN was independent of the radiological institution (accuracy 0.964 vs. 0.960), type of MRI scanner (accuracy 0.957 vs. 0.964), and magnetic field strength (accuracy 0.966 vs. 0.957).

CONCLUSIONS

A DCNN can achieve high diagnostic performance in vertebral body measurements and insufficiency fracture detection on heterogeneous lumbar spine MRI.

KEY POINTS

• A DCNN has the potential for high diagnostic performance in measuring vertebral bodies and detecting insufficiency fractures of the lumbar spine.

Lorentzian-Corrected Apparent Exchange-Dependent Relaxation (LAREX) Ω-Plot Analysis-An Adaptation for qCEST in a Multi-Pool System: Comprehensive In Silico, In Situ, and In Vivo Studies

Based on in silico, in situ, and in vivo studies, this study aims to develop a new method for the quantitative chemical exchange saturation transfer (qCEST) technique considering multi-pool systems. To this end, we extended the state-of-the-art apparent exchange-dependent relaxation (AREX) method with a Lorentzian correction (LAREX). We then validated this new method with in situ and in vivo experiments on human intervertebral discs (IVDs) using the Kendall-Tau correlation coefficient. In the in silico experiments, we observed significant deviations of the AREX method as a function of the underlying exchange rate (kba) and fractional concentration (fb) compared to the ground truth due to the influence of other exchange pools. In comparison to AREX, the LAREX-based Ω-plot approach yielded a substantial improvement. In the subsequent in situ and in vivo experiments on human IVDs, no correlation to the histological reference standard or Pfirrmann classification could be found for the fb (in situ: τ = −0.17 p = 0.51; in vivo: τ = 0.13 p = 0.30) and kba (in situ: τ = 0.042 p = 0.87; in vivo: τ = −0.26 p = 0.04) of Glycosaminoglycan (GAG) with AREX. In contrast, the influence of interfering pools could be corrected by LAREX, and a moderate to strong correlation was observed for the fractional concentration of GAG for both in situ (τ = −0.71 p = 0.005) and in vivo (τ = −0.49 p < 0.001) experiments. The study presented here is the first to introduce a new qCEST method that enables qCEST imaging in systems with multiple proton pools.

A review on deep learning MRI reconstruction without fully sampled k-space

BACKGROUND

Magnetic resonance imaging (MRI) is an effective auxiliary diagnostic method in clinical medicine, but it has always suffered from the problem of long acquisition time. Compressed sensing and parallel imaging are two common techniques to accelerate MRI reconstruction. Recently, deep learning provides a new direction for MRI, while most of them require a large number of data pairs for training. However, there are many scenarios where fully sampled k-space data cannot be obtained, which will seriously hinder the application of supervised learning. Therefore, deep learning without fully sampled data is indispensable.

MAIN TEXT

In this review, we first introduce the forward model of MRI as a classic inverse problem, and briefly discuss the connection of traditional iterative methods to deep learning. Next, we will explain how to train reconstruction network without fully sampled data from the perspective of obtaining prior information.

CONCLUSION

Although the reviewed methods are used for MRI reconstruction, they can also be extended to other areas where ground-truth is not available. Furthermore, we may anticipate that the combination of traditional methods and deep learning will produce better reconstruction results.