Prediction of osteoporosis using MRI and CT scans with unimodal and multimodal deep-learning models.

PURPOSE: Osteoporosis is the systematic degeneration of the human skeleton, with consequences ranging from a reduced quality of life to mortality. Therefore, the prediction of osteoporosis reduces risks and supports patients in taking precautions. Deep-learning and specific models achieve highly accurate results using different imaging modalities. The primary purpose of this research was to develop unimodal and multimodal deep-learning-based diagnostic models to predict bone mineral loss of the lumbar vertebrae using magnetic resonance (MR) and computed tomography (CT) imaging. METHODS: Patients who received both lumbar dual-energy X-ray absorptiometry (DEXA) and MRI (n = 120) or CT (n = 100) examinations were included in this study. Unimodal and multimodal convolutional neural networks (CNNs) with dual blocks were proposed to predict osteoporosis using lumbar vertebrae MR and CT examinations in separate and combined datasets. Bone mineral density values obtained by DEXA were used as reference data. The proposed models were compared with a CNN model and six benchmark pre-trained deep-learning models. RESULTS: The proposed unimodal model obtained 96.54%, 98.84%, and 96.76% balanced accuracy for MRI, CT, and combined datasets, respectively, while the multimodal model achieved 98.90% balanced accuracy in 5-fold cross-validation experiments. Furthermore, the models obtained 95.68%-97.91% accuracy with a hold-out validation dataset. In addition, comparative experiments demonstrated that the proposed models yielded superior results by providing more effective feature extraction in dual blocks to predict osteoporosis. CONCLUSION: This study demonstrated that osteoporosis was accurately predicted by the proposed models using both MR and CT images, and a multimodal approach improved the prediction of osteoporosis. With further research involving prospective studies with a larger number of patients, there may be an opportunity to implement these technologies into clinical practice.

The relationship of proximal lateral collateral ligament hyperintensity with knee joint ligament and meniscus pathologies.

BACKGROUND: Hyperintensity in the proximal lateral collateral ligament (LCL) is often confusing. This appearance may be alone or accompany other pathologies. PURPOSE: To investigate the relationship between the signal intensity (SI) change in the proximal LCL and the knee joint pathologies. MATERIAL AND METHODS: The knee MRI scans taken between 2020 and 2022 were queried retrospectively. Patients with acute trauma, instability, knee surgery, or high-grade osteoarthritis were excluded. Included patients were divided into two groups as normal SI and increased SI according to proximal LCL. The difference in ligamentous and meniscal pathologies between the two groups was analyzed using a chi-square test. Inter-observer agreement analysis was performed on 50 randomly selected patients. RESULTS: A total of 351 patients (139 men [39.6%], 212 women [60.4%]; median age = 37 years; interquartile range = 67 years) were included. There were 114 (32.5%) LCLs with normal SI and 237 (67.5%) LCLs with increased SI. Normal SI and increased SI groups had a significant difference in terms of joint side, median age, patellar tendon SI, anterior cruciate ligament SI, and medial collateral ligament SI (P = 0.004, P = 0.004, P = 0.001, P = 0.011, P = 0.004, respectively). A significant difference between the results of two separate LCL examinations in coronal + axial and coronal-only planes (P <0.001). Inter-observer agreement was found to be good to excellent. CONCLUSION: Hyperintensity in the proximal LCL was more common on the right joint side, in older patients, and patients with hyperintensity in the proximal patellar tendon, anterior cruciate ligament, and medial collateral ligament. Evaluating the LCL only in the coronal plane overestimates the hyperintensity.

Can orbital artery resistive indexes detect complications of diabetes in the prediabetic phase?

AIM: Prediabetic patients have generalized microvascular dysfunction, which leads to end-organ damage, just like diabetes. Therefore, prediabetes is not just a mild elevation in blood sugar, and early detection and prevention of possible complications should be the main goal. Color Doppler imaging (CDI) provides morphologic and vascular information on various diseases. The Resistive Index (RI) is a widely used measure of resistance to arterial flow and is calculated from the CDI. CDI evaluation of vessels in the retrobulbar region may be the first sign of micro- and macrovascular complications. METHOD: Consecutively, 55 prediabetic patients and 33 healthy subjects were recruited for the study. Prediabetic patients were divided into three groups according to their fasting and postprandial blood glucose values. The groups included an impaired fasting glucose (IFG) group (n = 15), an impaired glucose tolerance (IGT) group (n = 13), and an IFG+IGT group (n = 27). The RI of the ophthalmic artery, posterior ciliary artery, and central retinal artery were measured in all patients. RESULTS: The orbital artery, central retinal artery, and posterior cerebral artery mean RI of prediabetic patients (0.76 ± 0.06, 0.69 ± 0.03, and 0.69 ± 0.04, respectively) were significantly higher than those of the healthy group (0.66 ± 0.04, 0.63 ± 0.04, and 0.66 ± 0.04, respectively; p < 0.001; Student's t-test). The mean ophthalmic artery RI of the healthy, IFG, IGT, and IFG+IGT groups were 0.66 ± 0.39, 0.7 ± 0.27, 0.72 ± 0.29, and 0.82 ± 0.16, respectively, with a significant difference between the groups (p < 0.001, ANOVA). The mean central retinal artery RI of the healthy, IFG, IGT, and IFG+IGT groups were 0.63 ± 0.04, 0.66 ± 0.02, 0.7 ± 0.02, and 0.71 ± 0.02, respectively (p < 0.001, post-hoc Tukey). The mean posterior cerebral artery RI of the healthy, IFG, IGT, and IFG+IGT groups were 0.66 ± 0.04, 0.66 ± 0.04, 0.69 ± 0.03, and 0.71 ± 0.03, respectively, with a significant difference between the groups (p < 0.001 Fisher ANOVA). CONCLUSION: Increased RI may be the first sign of developing retinopathy, as well as the first sign of microangiopathies occurring simultaneously in the coronary, cerebral, and renal vessels. Precautions to be taken during the prediabetic stage can prevent many possible complications.

Relationship between Radiological Measurement of Subcoracoid Impingement and Subscapularis Tendon Lesions.

Background: The value of radiological measurements of subcoracoid impingement such as the coracohumeral interval in predicting subscapularis tendon injuries is controversial. We aimed to assess the relationship between radiological measurements of subcoracoid impingement and subscapularis tendon lesions in young and middle-aged adults. Methods: This study was designed as a retrospective cohort study. Patients between the ages of 18-55 years without a history of shoulder surgery or major trauma were included and patients with arthritis, instability, or retracted rotator cuff tears were excluded from the study. Magnetic resonance images were evaluated and patients were grouped into two according to the subscapularis tendon condition: normal or pathologic. Glenoid version, axial coracohumeral distance, coracoglenoid angle, coracoid index, sagittal coracoid-glenoid tubercule distance, and axial coracoacromial inclination-glenoid version difference were measured for all patients. Measurement findings were compared between the groups. Correlation analysis was performed for age and radiologic measurements. A p < 0.05 was considered statistically significant for all tests. Results: A total of 298 patients, 107 women (35.1%) and 191 men (64.9%), with a mean age of 34.46 ± 10.10 years (range, 18-55 years) were examined in the study. Subscapularis tendon pathology was noted in 85 patients (28.5%). The diagnosed pathologies were tendinosis in 48 patients (56.5%), partial tears in 28 (32.9%), and full thickness tears in 9 (10.6%). A significant relationship was observed between increasing age and subscapularis tendon lesions (p = 0.001). There was no statistically significant relationship between subscapularis pathology and calculated measurements. Axial coracohumeral distance and coracoglenoid angle measurements showed a statistically significantly negative correlation with age. A positive correlation was found between axial coracohumeral distance and coracoglenoid angle measurements (p < 0.001) and also between glenoid version and coracoid index measurements (p = 0.004). Axial coracohumeral distance and coracoglenoid angle measurements showed a negative correlation with glenoid version and coracoid index measurements (p < 0.05). Conclusions: In this study, the coracohumeral distance and coracoglenoid angle decreased and the incidence of subscapularis tendon lesions increased as the age progressed. However, no relationship was found between radiological measurements and subscapularis tendon lesions.

Severe Hypokalemia and Rhabdomyolysis Caused by Conn Syndrome.

ABSTRACT: Hypokalemia is a common electrolyte abnormality. Generally being asymptomatic, muscular fatigue, paresis and arrhythmia can be seen as the severity of hypokalemia increases. Severe rhabdomyolysis and neuromuscular findings can be seen in severe hypokalemia cases. Presence of hypokalemia can be a precursor of secondary hypertension in hypertensive patients, and also should bring hyperaldosteronism into consideration. Mild hypokalemia is usually seen in primary hype-raldosteronism. However, deficient potassium levels are also seen in some cases. We have shared the case of a hypertensive patient, who presented to the emergency department with findings of rhabdomyo-lysis and neuromuscular findings secondary to severe hypokalemia. The potassium level of our patient was 1.3 mmol, and it was one of the lowest potassium levels reported up to today.