Background: To evaluate paraspinal back muscles of asymptomatic subjects using qualitative and quantitative analysis on CT and MRI and correlate the results with demographic data.Methods: Twenty-nine asymptomatic subjects were enrolled prospectively (age: mean 34.31, range 23–50; 14 men, 15 women) from August 2016 to April 2017. Qualitative analysis of muscles was done using Goutallier’s system on CT and MRI. Quantitative analysis entailed cross sectional area (CSA) on CT and MRI, Hounsfield unit (HU) on CT, fat fraction using two-point Dixon technique on MRI. Three readers independently analyzed the images; intra- and inter-observer agreements were measured. Linear regression and Spearman’s analyses were used for correlation with demographic data.Results: CSA values were significantly higher in men (p < 0.001). Fat fraction was higher (22.53% vs. 14.35%) and HU lower (36.00 vs. 47.43) in women (p < 0.001). Intra- and inter-observer reliabilities of the two methods were greater than 0.8, except for CSA of L5/S1 on MRI; however, regarding quantitative analysis, decreasing HU and increasing fat fraction were correlated with increasing age, female gender and lower lumbar segment (p < 0.001).Conclusion: MRI and CT can be reliably used for qualitative and quantitative analysis of paraspinal back muscles, regarding fat content. Fat fraction and HU showed highest reliabilities.

Background: This study aimed to evaluate the co-administration effect of atelocollagen combined with hyaluronic acid (HA) injections for treatment of full-thickness rotator cuff tear (RCT).Methods: Eighty patients who underwent arthroscopic rotator cuff repair for full-thickness RCT from March 2018 to November 2019 were enrolled. The patients were randomly allocated to the following groups: combined atelocollagen and HA injection (group I, n=28), only HA injection (group II, n=26), and no injection (group III, n=26). Clinical outcomes were assessed at 3, 6, and 12 months after surgery using the American Shoulder and Elbow Surgeons score, visual analog scale pain, functional scores (pain visual analog scale, function visual analog score), and range of motion. Magnetic resonance imaging was performed 12 months after surgery to evaluate rotator cuff integrity.Results: Preoperative demographic data and postoperative clinical outcomes did not differ significantly among the three groups (p>0.05). However, in group I, the number of steroid injections after surgery was significantly lower than that in the other groups (p=0.011). The retear rate on follow-up magnetic resonance imaging was significantly higher in group II (9.5%, n=2) and group III (13.6%, n=3) than in group I (0%) (p=0.021).Conclusions: Co-administration of atelocollagen and HA improves healing of the rotator cuff and increases the integrity of the rotator cuff repair site. This study provides encouraging evidence for use of combined atelocollagen-HA injections to treat patients with full-thickness RCT.

Hwang J, et al. Korean J Radiol. 2020 Jul;21:e115. https://doi.org/10.3348/kjr.2019.0893

Objective: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise.Methods: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics—compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)—from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model.Results: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees.Conclusion: The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.

This study aimed to develop a deep learning (DL) algorithm for automated detection and localization of posterior ligamentous complex (PLC) injury in patients with acute thoracolumbar (TL) fracture on magnetic resonance imaging (MRI) and evaluate its diagnostic performance. In this retrospective multicenter study, using midline sagittal T2-weighted image with fracture (± PLC injury), a training dataset and internal and external validation sets of 300, 100, and 100 patients, were constructed with equal numbers of injured and normal PLCs. The DL algorithm was developed through two steps (Attention U-net and Inception-ResNet-V2). We evaluate the diagnostic performance for PLC injury between the DL algorithm and radiologists with different levels of experience. The area under the curves (AUCs) generated by the DL algorithm were 0.928, 0.916 for internal and external validations, and by two radiologists for observer performance test were 0.930, 0.830, respectively. Although no significant difference was found in diagnosing PLC injury between the DL algorithm and radiologists, the DL algorithm exhibited a trend of higher AUC than the radiology trainee. Notably, the radiology trainee's diagnostic performance significantly improved with DL algorithm assistance. Therefore, the DL algorithm exhibited high diagnostic performance in detecting PLC injuries in acute TL fractures.