Automatic Calculation of Cervical Spine Parameters Using Deep Learning: Development and Validation on an External Dataset.

STUDY DESIGN: Retrospective data analysis. OBJECTIVES: This study aims to develop a deep learning model for the automatic calculation of some important spine parameters from lateral cervical radiographs. METHODS: We collected two datasets from two different institutions. The first dataset of 1498 images was used to train and optimize the model to find the best hyperparameters while the second dataset of 79 images was used as an external validation set to evaluate the robustness and generalizability of our model. The performance of the model was assessed by calculating the median absolute errors between the model prediction and the ground truth for the following parameters: T1 slope, C7 slope, C2-C7 angle, C2-C6 angle, Sagittal Vertical Axis (SVA), C0-C2, Redlund-Johnell distance (RJD), the cranial tilting (CT) and the craniocervical angle (CCA). RESULTS: Regarding the angles, we found median errors of 1.66° (SD 2.46°), 1.56° (1.95°), 2.46° (SD 2.55), 1.85° (SD 3.93°), 1.25° (SD 1.83°), .29° (SD .31°) and .67° (SD .77°) for T1 slope, C7 slope, C2-C7, C2-C6, C0-C2, CT, and CCA respectively. As concerns the distances, we found median errors of .55 mm (SD .47 mm) and .47 mm (.62 mm) for SVA and RJD respectively. CONCLUSIONS: In this work, we developed a model that was able to accurately predict cervical spine parameters from lateral cervical radiographs. In particular, the performances on the external validation set demonstrate the robustness and the high degree of generalizability of our model on images acquired in a different institution.

External validation of the deep learning system "SpineNet" for grading radiological features of degeneration on MRIs of the lumbar spine.

BACKGROUND: Magnetic resonance imaging (MRI) is used to detect degenerative changes of the lumbar spine. SpineNet (SN), a computer vision-based system, performs an automated analysis of degenerative features in MRI scans aiming to provide high accuracy, consistency and objectivity. This study evaluated SN's ratings compared with those of an expert radiologist. METHOD: MRIs of 882 patients (mean age, 72 ± 8.8 years) with degenerative spinal disorders from two previous trials carried out in our spine center between 2011 and 2019, were analyzed by an expert radiologist. Lumbar segments (L1/2-L5/S1) were graded for Pfirrmann Grades (PG), Spondylolisthesis (SL) and Central Canal Stenosis (CCS). SN's analysis for the equivalent parameters was generated. Agreement between methods was analyzed using kappa (κ), Spearman correlation (ρ) and Lin's concordance correlation (ρc) coefficients and class average accuracy (CAA). RESULTS: 4410 lumbar segments were analyzed. κ statistics showed moderate to substantial agreement in PG between the radiologist and SN depending on spinal level (range κ 0.63-0.77, all levels together 0.72; range CAA 45-68%, all levels 55%), slight to substantial agreement for SL (range κ 0.07-0.60, all levels 0.63; range CAA 47-57%, all levels 56%) and CCS (range κ 0.17-0.57, all levels 0.60; range CAA 35-41%, all levels 43%). SN tended to record more pathological features in PG than did the radiologist whereas the contrary was the case for CCS. SL showed an even distribution between methods. CONCLUSION: SN is a robust and reliable tool with the ability to grade degenerative features such as PG, SL or CCS in lumbar MRIs with moderate to substantial agreement compared to the current gold-standard, the radiologist. It is a valuable alternative for analyzing MRIs from large cohorts for diagnostic and research purposes.

Impact of Sports Activity on Medium-Term Clinical and Radiological Outcome after Reverse Shoulder Arthroplasty in Cuff Deficient Arthropathy; An Institutional Register-Based Analysis.

There is a lack of consensus on what physicians can recommend and what patients can expect concerning sports activity after reverse shoulder arthroplasty (RSA). The purpose of this retrospective register-based observational study was to investigate the association between participation in sports or physical activity involving the upper extremity and 5-year clinical and radiological outcomes for primary RSA patients. We screened the institutional arthroplasty registry for patients reporting the type and level of sports postoperatively after primary, unilateral RSA due to rotator cuff deficiency. One hundred thirty-eight patients with clinical and radiological outcomes documented at a minimum 5-year follow-up were divided into three groups comprising those who participated regularly in: sports mainly involving the upper extremity (sports upper extremities, SUE, n = 49), sports mainly involving the lower extremities (sports lower extremities, SLE, n = 21), and those who did not participate in sports at all (no sports, NS, n = 68). The participants had a mean age of 72 years (standard deviation (SD) 8) and were overall predominantly female patients (62%). Primary clinical outcomes included the Constant Score (CS) and Shoulder Pain and Disability Index (SPADI). Secondary radiographs were analyzed for radiolucent lines (RLL), signs of glenoid or humeral prosthesis loosening, bone resorption, bone formation, and scapular notching. A total number of 8 senior surgeons were involved in treatment of patients, and two types of prosthesis were used. The SUE group had non-significantly higher mean scores for CS (75 points) and SPADI (88 points) compared to SLE (71 and 78 points, respectively) and NS patients (66 and 78 points, respectively) (p ≥ 0.286). The incidence of RLL around the humeral diaphysis was higher in NS compared to SUE patients (32% versus 12%, respectively) (p = 0.025); all other radiological parameters were similar between the groups. There were no cases of loosening in the SUE group that led to revision surgery. Patients engaging in sports activities involving the upper extremity show similarly good functional scores 5 years post-RSA as the other groups, without additional signs of implant loosening as a result of increased shoulder use.

Glenoid Component Loosening in Anatomic Total Shoulder Arthroplasty: Association between Radiological Predictors and Clinical Parameters-An Observational Study.

The mechanisms of glenoid component loosening in anatomic total shoulder arthroplasty (aTSA) are still unclear, and it remains undetermined which specific radiographic features are associated with clinical outcomes. Patients with primary osteoarthritis who underwent aTSA with a stemless implant and a pegged glenoid between January 2011 and December 2016 were extracted from a local registry. Anteroposterior radiographs were evaluated at six, 12, 24 months, and five years post-TSA for lateral humeral offset (LHO), joint gap (JG), acromiohumeral distance (AHD), and radiolucency (modified Franklin score); 147 patients were included. Mixed-model linear regression was used. Both constant score (CS) and subjective shoulder value (SSV) markedly decreased at five years follow-up compared to one year (p < 0.001 for both). AHD, LHO, and JG all showed a consistent and statistically significant decline over time, with the joint gap decreasing by half. Consistently, smaller JG and AHD were correlated with lower SSV (p = 0.03 and p = 0.07, respectively). Massive loosening was associated with a 14.5 points lower SSV (p < 0.01). Finally, narrowing of the JG was significantly correlated with increased radiolucency (p < 0.001) and tended toward worse SSV (p = 0.06). In summary, radiographic parameters displaying medialization and cranialization after aTSA with a cemented pegged glenoid are useful predictors of impaired shoulder function.

Muir-Torre Syndrome: A Case Associated with an Infrequent Gene Mutation.

Muir-Torre syndrome is a rare, autosomal dominant genodermatosis characterized by the presence of at least one sebaceous gland neoplasm, associated with an underlying visceral malignancy. Muir-Torre syndrome is believed to be a subtype of Lynch Syndrome. Affected individuals are found to have germline mutations predominantly in DNA mismatch repair gene MSH2, and much less frequently, MLH1. The authors report the case of a 55-year-old woman presenting with multiple cutaneous neoplasms including sebaceoma, basal cell carcinoma, and squamous cell carcinoma; personal history of colorectal and endometrial cancer; and family history of colorectal cancer; found to have a deletion at mismatch repair gene MLH1. It is important to recognize the role of these less common gene deletions in producing the Muir-Torre syndrome phenotype, and consider the correlation of cutaneous manifestations with internal disease. The authors discuss the clinical presentation of Muir-Torre syndrome, methods of diagnosis, and the importance of regular medical surveillance to detect and prevent disease progression in Muir-Torre syndrome patients and their family members.

Piebaldism in children.

Piebaldism is a rare autosomal-dominant disorder of melanocyte development characterized by congenital poliosis and stable patches of leukoderma. Initially, these clinical features may be the presenting signs of various syndromes or associated diseases, which should be considered in the differential diagnosis. We present the case of a 14-year-old adolescent girl with piebaldism, along with a review of the pathogenesis, diagnosis, and management of this disease entity.

Short-term HFD does not alter lipolytic function of adipocytes.

A short bout of high fat diet (HFD) impairs glucose tolerance and hepatic insulin sensitivity. We recently identified adipose tissue inflammation and resulting dysfunctional adipose tissue-liver cross-talk as an early event in the development of HFD-induced hepatic insulin resistance. In particular, reducing white adipose tissue (WAT) inflammation by adipocyte-specific depletion of Fas/CD95 protected mice from developing hepatic insulin resistance but not hepatic steatosis. Herein, we expanded our previous work and determined the impact of four days of HFD on lipolytic activity of isolated adipocytes. Compared with chow-fed mice, the degree of basal and isoproterenol-stimulated free fatty acid (FFA) and glycerol release was similar in HFD-fed animals. Moreover, insulin's ability to suppress lipolysis remained intact, suggesting retained insulin sensitivity. Despite unaltered lipolysis, circulating FFA concentrations were greatly increased in non-fasted HFD-fed mice. In conclusion, a short-term HFD challenge does not affect lipolytic function of adipocytes. The observed increase of circulating FFA levels in randomly fed animals may rather be the result of increased dietary fat supply.