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

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.

Scapholunate Ligament Injury: Reviewing the Concept and the Challenges Ahead

The article's abstract is no available.

Scapholunate Ligament Injury and the Effect of Scaphoid Lengthening

Objective We hypothesized that lengthening the scaphoid in a model of scapholunate ligament injury (SLI) will result in correction of radiographic markers of dorsal intercalated segment instability (DISI) deformity. Materials and Methods An SLI with DISI deformity was created by sectioning the SL ligament, the palmar radiocarpal ligaments, and scapho-trapezio-trapezoid ligaments of a cadaveric upper extremity (n = 5). The wrist was radiographed in both anteroposterior and lateral planes to confirm creation of SLI and DISI. The scaphoid was then osteotomized at its waist. A series of grafts (1–8 mm) were then placed at the osteotomy site. Radiographs were completed at each length. The main outcome measures were scapholunate interval (SL, mm), scapholunate angle (SLA, degrees), and radiolunate angle (RLA, degrees). These values, measured following the insertion of varying graft lengths, were compared with baseline measurements taken “post-injury” status. Results The ability to create an SLI with DISI was confirmed in the postinjury group with a statistically significant change in RLA, SLA, and SL compared with preinjury. With osteotomy and progressive insertion of spacers, the values improved into the accepted normal ranges for RLA (6 mm) and SLA (4 mm) with scaphoid lengthening. Conclusions In this cadaveric model of SL injury, radiographic markers of DISI were returned to within normal ranges with scaphoid osteotomy and lengthening. Clinical Relevance The results of this study add insight into wrist kinematics in our injury model and may represent a potential future direction for surgical treatment of SLI.

Radiographic Diagnosis of Scapholunate Diastasis in Distal Radius Fractures: Implications for Surgical Practice

Background Radiographic diagnosis of scapholunate ligament injury (SLI) in the setting of distal radius fractures (DRFs) is challenging. It remains unclear to what extent radiographic diagnosis of SLI by a radiologist influences surgical decision-making regarding treatment of SLI. Purpose We aimed to (1) identify the number of times that concerns for the possibility of concurrent SLI in the setting of a DRF had been raised by the radiologists, (2) identify how often the radiologist's diagnosis was confirmed by the treating surgeon, and (3) how many of the patients with a radiographic concern for SLI by the radiologist received operative treatment for the SLI. Patients and Methods Based on Current Procedural Terminology codes, we identified 2,923 patients that were operatively treated for their DRF in 1 of 3 participating institutions in an urban city in the United States. We reviewed the medical charts of 654 patients who had a mention of scapholunate ligament (SL) distance in their radiography, surgery, or clinical notes. We then measured the SL distance and recorded patient, diagnosis, and treatment characteristics of all these patients. Results A total of 200 out of 2,923 patients (6.8%) received a radiological diagnosis of SLI. In seven of these patients (3.5%), the surgeon confirmed the diagnosis of the radiologist. Four patients (2%) had operative repair of their SLI. Conclusion Radiologists demonstrate a low threshold to identify SLI in the setting of DRFs, while the number of SLIs identified by the treating surgeon is a remarkably smaller number. Level of Evidence Level II, prognostic study.