The supraspinatus occupation ratios of both the ≥ 50% articular- and bursal-side partial-thickness rotator cuff tears were low and the infraspinatus occupation ratio of the ≥ 50% bursal-side partial-thickness rotator cuff tears was low

Development and clinical validation of deep learning for auto-diagnosis of supraspinatus tears

BACKGROUND

Accurately diagnosing supraspinatus tears based on magnetic resonance imaging (MRI) is challenging and time-combusting due to the experience level variability of the musculoskeletal radiologists and orthopedic surgeons. We developed a deep learning-based model for automatically diagnosing supraspinatus tears (STs) using shoulder MRI and validated its feasibility in clinical practice.

MATERIALS AND METHODS

A total of 701 shoulder MRI data (2804 images) were retrospectively collected for model training and internal test. An additional 69 shoulder MRIs (276 images) were collected from patients who underwent shoulder arthroplasty and constituted the surgery test set for clinical validation. Two advanced convolutional neural networks (CNN) based on Xception were trained and optimized to detect STs. The diagnostic performance of the CNN was evaluated according to its sensitivity, specificity, precision, accuracy, and F1 score. Subgroup analyses were performed to verify its robustness, and we also compared the CNN's performance with that of 4 radiologists and 4 orthopedic surgeons on the surgery and internal test sets.

RESULTS

Optimal diagnostic performance was achieved on the 2D model, from which F1-scores of 0.824 and 0.75, and areas under the ROC curves of 0.921 (95% confidence interval, 0.841-1.000) and 0.882 (0.817-0.947) were observed on the surgery and internal test sets. For the subgroup analysis, the 2D CNN model demonstrated a sensitivity of 0.33-1.000 and 0.625-1.000 for different degrees of tears on the surgery and internal test sets, and there was no significant performance difference between 1.5 and 3.0 T data. Compared with eight clinicians, the 2D CNN model exhibited better diagnostic performance than the junior clinicians and was equivalent to senior clinicians.

CONCLUSIONS

The proposed 2D CNN model realized the adequate and efficient automatic diagnoses of STs, which achieved a comparable performance of junior musculoskeletal radiologists and orthopedic surgeons. It might be conducive to assisting poor-experienced radiologists, especially in community scenarios lacking consulting experts.

Comparison of Arthroscopic Debridement and Repair in the Treatment of Ellman Grade II Bursal-side Partial-thickness Rotator Cuff Tears: A Prospective Randomized Controlled Trial

Objective

To compare the effects of arthroscopic debridement and repair in treating Ellman grade II bursal‐side partial‐thickness rotator cuff tears.

Methods

This is a single‐center, prospective, randomized controlled trial. From September 2017 to April 2019, 78 patients underwent arthroscopic debridement (35 patients) or repair (43 patients) due to Ellman grade II bursal‐side partial‐thickness rotator cuff tears. Twenty‐six men and 52 women were included in the study, with an average age of 56.31 years (range, 42 to 74 years). After the acromioplasty was formed, the debridement group only performed stump refreshing and surrounding soft tissue cleaning, while the repair group converted the partial tears into full‐thickness tears and then sutured them by single row or suture bridge technique. The visual analogue scale (VAS), Constant‐Murley shoulder (CMS), American Shoulder and Elbow Surgeons (ASES), and University of California, Los Angeles (UCLA) scores were used to evaluate clinical results preoperatively and at 6, 12, and 18 months postoperatively. Magnetic resonance imaging was used to assess the integrity of the rotator cuff, muscle atrophy, and fat infiltration.

Results

A total of 85 patients met the inclusion criteria and were randomly divided into the debridement group (41 patients) and the repair group (43 patients). During the 18‐month follow‐up period, a total of seven patients were lost to follow‐up. The functional scores of both groups were significantly improved: the VAS score decreased 5.06 and 4.63 in the debridement group (5.77 preoperative to 0.71 postoperative) and the repair group (5.49 to 0.86) (P < 0.05). Moreover, the CMS, ASES, UCLA scores increased 51.63, 58.24, 20.57 in debridement group (39.46 to 91.09, 34.14 to 92.38, 13.29 to 33.86), and increased 48.14, 60.53, 20.93 in repair group (43.63 to 91.77, 33.10 to 93.63, 12.58 to 33.51) (P < 0.05). No significant differences were found in functional scores between the two groups at 6, 12, and 18 months postoperatively (P > 0.05). The magnetic resonance imaging showed no re‐tears, and no difference was observed in the degree of muscle atrophy and fat infiltration between the two groups (P > 0.05). Except for four cases of shoulder stiffness, no other obvious surgery‐related complications were found.

Conclusion

For Ellman grade II bursal‐side partial‐thickness rotator cuff tears, both the debridement and repair groups achieved good results during 18‐month follow‐ups, with no difference between the two groups.

Clinical short-term outcomes of articular-sided and bursal-sided partial-thickness rotator cuff tears of less than 50% in a single surgeon series: A protocol of randomized controlled trial

BACKGROUND

There have been no published randomized clinical trial to assess the clinical outcomes between the articular-sided and bursal-sided tears. Therefore, a comparative analysis of evaluating and comparing the functional outcomes following arthroscopic repair of bursal-sided versus articular-sided partial-thickness rotator cuff tearsis essential.

METHODS

This study is a present randomized controlled trial which is conducted in our hospital. Consecutive patients with symptomatic articular-sided or bursal-sided partial-thickness rotator cuff tears underwent arthroscopic repair between June 2020 and January 2022. The institutional review board approved the study proposal (with number 10012030), and informed consent was obtained from all patients. Inclusion criteria were existence of an articular- or bursal-sided tear involving <50% of the tendon thickness-confirmed intraoperatively and treated with arthroscopic debridement with or without other decompression surgery (acromioplasty/distal clavicle resection)-and a minimum follow-up of 2 years. All patients followed the same postoperative rehabilitation program. The patients were assessed at baseline preoperatively, and at 1 year and 2 years postoperatively. Outcome parameters were measured at each respective follow-up, which included active range of motion in forward flexion and abduction of the affected shoulder, pain score as measured on the Numeric Pain Rating Scale, as well as outcome scores in terms of the Constant-Murley Score, and Oxford Shoulder Score.

RESULTS

Table 1 and Table 2 describe the data indicators that this article wants to evaluate and collect.

CONCLUSIONS

We hypothesize that both groups of patients will show improvement in range of motion, functional outcome scores, and pain at 2 years, and that results would be similar between the two groups.

TRIAL REGISTRATION

This study protocol was registered in Research Registry (researchregistry6496).

A comparative study of arthroscopic débridement versus repair for Ellman grade II bursal-side partial-thickness rotator cuff tears

HYPOTHESIS

We aimed to report the clinical outcomes of arthroscopic débridement vs. repair for Ellman grade II bursal-side partial-thickness rotator cuff tears.

METHODS

Patients who presented with Ellman grade II bursal-side partial-thickness rotator cuff tears from September 2015 to August 2017 were included. On the basis of preoperative findings and patient preference, 20 patients underwent débridement whereas 26 underwent arthroscopic repair. The visual analog scale (VAS), Constant-Murley shoulder, American Shoulder and Elbow Surgeons, and University of California-Los Angeles scores were assessed. Magnetic resonance imaging and B-mode ultrasonography were performed preoperatively and at 6, 12, and 24 months postoperatively.

RESULTS

All 46 patients were available throughout follow-up. At 2 years postoperatively, the VAS score had improved from 6.42 ± 1.56 to 0.65 ± 0.51 in the débridement group and from 6.26 ± 1.32 to 0.75 ± 0.42 in the repair group. The VAS score differed significantly between the 2 groups at 6 months postoperatively. All patient-reported outcomes improved in both groups. The American Shoulder and Elbow Surgeons score (P = .009), Constant-Murley shoulder score (P = .014), and University of California-Los Angeles score (P = .030) differed significantly between the 2 groups (higher in the débridement group) at 6 months postoperatively. Finally, 44 patients having intact tendon repairs with no interval worsening of partial-thickness tears underwent postoperative scheduled magnetic resonance imaging and B-mode ultrasonography examinations.

CONCLUSION

Arthroscopic débridement and repair of Ellman grade II bursal-side partial-thickness rotator cuff tears achieved comparable clinical scores and low retear rates during 2 years of follow-up. However, débridement achieved better results, especially within 6 months postoperatively, and achieved a favorable prognosis up to 2 years postoperatively.

Relation of Superficial and Deep Layers of Delaminated Rotator Cuff Tear to Supraspinatus and Infraspinatus Insertions

BACKGROUND

It remains unclear whether the deep layer of the rotator cuff is an articular layer of the supraspinatus (SS) or infraspinatus (IS), rotator cable, or superior capsule. Therefore, this study aimed to analyse the relationship between occupation ratios and delamination patterns of rotator cuff tears (RCTs). We hypothesised that the deep layers are related to the occupation ratios of the deep SS and IS sections.

MATERIALS AND METHODS

A total of 265 patients with RCTs were retrospectively enrolled between 2013 and 2017 and divided into four groups: A, non-delaminated tear; B, delaminated tear with the deep layer equally retracted to the superficial layer; C, delaminated tear with the deep layer more retracted; D, delaminated tear with the superficial layer more retracted. Muscle volume was evaluated by measurement of each occupation ratio of the SS and IS, and the IS muscle was additionally divided into two areas, deep and superficial.

RESULTS

The SS occupation ratio was significantly lower in group C than in the other groups (p = 0.009). Conversely, comparison of the IS occupation ratios revealed no significant intergroup differences. The occupation ratio of the superficial IS was significantly lower in group D than in the other groups (p = 0.003). In group C, the occupation ratios of the deep IS section were significantly decreased according to RCT size (p = 0.034).

CONCLUSION

Our findings demonstrate that the superficial layers are related to the IS superficial section and the deep layers to the SS and IS deep sections.

LEVEL OF STUDY

IV.

Restoration of supraspinatus and infraspinatus deep plane occupation ratios was greater in delaminated tears than in non-delaminated tears after rotator cuff repair

Total 132 patients who underwent arthroscopic suture bridge repair were divided into two groups: group A, non-delaminated tears; group B, deep layer, more retracted, delaminated tears. In addition, group B were divided into two subgroups: group I (≤2-cm) and group II (>2-cm). Muscle volume was evaluated by measuring the occupation ratio and restoration of the rotator cuff muscle was defined as the difference between the preoperative and postoperative occupation ratios. The restoration of the SS and IS deep plane occupation ratios was greater in >2-cm-sized delaminated tears than in ≤2-cm-sized delaminated and non-delaminated tears.