Search

The utilization of artificial intelligence (AI) is expanding significantly within medical research and, to some extent, in clinical practice. Deep learning (DL) applications, which use large convolutional neural networks (CNN), hold considerable potential, especially in optimizing radiological evaluations. However, training DL algorithms to clinical standards requires extensive datasets, and their processing is labor-intensive. In this study, we developed an annotation tool named DLLabelsCT that utilizes CNN models to accelerate the image analysis process. To validate DLLabelsCT, we trained a CNN model with a ResNet34 encoder and a UNet decoder to segment the pancreas on an open-access dataset and used the DL model to assist in annotating a local dataset, which was further used to refine the model. DLLabelsCT was also tested on two external testing datasets. The tool accelerates annotation by 3.4 times compared to a completely manual annotation method. Out of 3,715 CT scan slices in the testing datasets, 50% did not require editing when reviewing the segmentations made by the ResNet34-UNet model, and the mean and standard deviation of the Dice similarity coefficient was 0.82±0.24. DLLabelsCT is highly accurate and significantly saves time and resources. Furthermore, it can be easily modified to support other deep learning models for other organs, making it an efficient tool for future research involving larger datasets. [ABSTRACT FROM AUTHOR]

Background: The reliability and diagnostic accuracy of commonly used diagnostic imaging modalities in the classification of lumbosacral transitional vertebrae (LSTV) are poorly known, and comparative studies are scarce. Purpose: To compare the diagnostic performance of conventional radiography (CR), computed tomography (CT), and magnetic resonance imaging (MRI) in classifying LSTVs. Material and Methods: In this retrospective cross-sectional study, a total of 852 patients undergoing lumbar imaging studies using all three modalities were initially assessed for the presence of LSTV using CT scans. In total, 100 patients with LSTV anatomy were identified. Four readers performed blinded and independent evaluations of these 100 patients on each modality, and an experienced fellowship-trained radiologist performed a gold standard read using all three modalities. Inter-reader reliability metrics were analyzed in comparison to the gold standard. Statistical software R (4.2.1) was used for the analyses. Results: We found superior diagnostic efficacy for CT: the sensitivity, specificity, accuracy, and balanced accuracy were 76%, 93%, 77%, and 84%, respectively. For MRI, the metrics were 54%, 88%, 56%, and 68%, and for CR 32%, 85%, 42%, and 59%, respectively. Inter-reader reliability was found to be good for CT (κ = 0.63–0.71) and fair for both CR (κ = 0.16–0.32) and MRI (κ = 0.24–0.56). Conclusion: CT had the highest diagnostic performance in all measured metrics with good inter-reader reliability. MRI and CR showed fairly poor sensitivity and accuracy, and thus consideration should be used when classifying LSTVs with these two modalities. [ABSTRACT FROM AUTHOR]

Background: Obesity is a significant risk factor for osteoarthritis (OA). The most effective treatment for morbid obesity is bariatric surgery. Purpose: To study the effects of potential surgically induced weight loss on knee articular cartilage and OA symptoms of obese patients over a 12‐month follow‐up. Study Type: Prospective longitudinal cohort study. Subjects: 45 obese patients (38 female, BMI = 42.3 ± 6.5 kg/m2) who underwent gastric bypass (intervention group), and 46 age‐matched conservative‐care controls (37 female, BMI = 39.8 ± 4.6 kg/m2). Field Strength/Sequence: Multiecho spin echo sequence at 3 T. Assessment: Knee cartilage T2 measurements and WOMAC Indices were measured presurgery and after 12 months. The intervention group was split into successful (≥20% total weight loss (TWL)) and unsuccessful (<20% TWL) weight loss groups. T2 and WOMAC indices were also measured in controls at baseline and after 12 months. Changes among the three groups were analyzed. Statistical Tests: Analysis of variance (significance level 0.05). Results: Twenty‐six (58%) intervention patients achieved ≥20% TWL. The <20% TWL group demonstrated significantly more T2 reduction in the deep lateral femur over 12 months compared with the ≥20% TWL group (−3.83 ± 8.18 msec vs. 2.47 ± 6.54 msec, respectively), whereas no significant differences were observed on the medial femoral compartment (P = 0.385, P = 0.551, and P = 0.511 for bulk, superficial and deep regions, respectively). Changes in WOMAC indices over 12 months were significantly greater in the ≥20% TWL group compared with controls. In the <20% TWL group, pain significantly improved over 12 months compared with controls, while stiffness and function changes were not statistically significant (P = 0.063 and P = 0.051, respectively). Data Conclusion: Cartilage matrix, measured by T2, showed improvement on lateral femoral cartilage with <20% TWL compared with ≥20% TWL. Bariatric surgery provided significant improvements in knee symptoms with ≥20% TWL compared with conservative WL. This effect is also seen to some extent with <20% TWL compared with conservative WL. Level of Evidence: 2 Technical Efficacy: Stage 4 [ABSTRACT FROM AUTHOR]

At the quadrangular joint (QAJ) of the carpus, a rare bony protuberance called carpal boss (CB) may occur. This bone abnormality may be due to osteophytes development or os styloideum. Symptomatic patients may complain pain, swelling, and restrictions in hand motion. These symptoms result from joint degenerative‐inflammatory changes, development of ganglion cyst/bursitis, or tendons pathology. Correct diagnosis and appropriate management can be achieved through high‐resolution ultrasonography (HR‐US). The purpose of this review is to define the pathology spectrum around and within the QAJ in CB. The role of HR‐US is highlighted and the standard technique for the QAJ assessment is described. [ABSTRACT FROM AUTHOR]

Background: Magnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast‐weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could significantly decrease the imaging time. Purpose: To improve clinical utility of MRF by synthesizing contrast‐weighted MR images from the quantitative data provided by MRF, using U‐nets that were trained for the synthesis task utilizing L1‐ and perceptual loss functions, and their combinations. Study Type: Retrospective. Population: Knee joint MRI data from 184 subjects from Northern Finland 1986 Birth Cohort (ages 33–35, gender distribution not available). Field Strength and Sequence: A 3 T, multislice‐MRF, proton density (PD)‐weighted 3D‐SPACE (sampling perfection with application optimized contrasts using different flip angle evolution), fat‐saturated T2‐weighted 3D‐space, water‐excited double echo steady state (DESS). Assessment: Data were divided into training, validation, test, and radiologist's assessment sets in the following way: 136 subjects to training, 3 for validation, 3 for testing, and 42 for radiologist's assessment. The synthetic and target images were evaluated using 5‐point Likert scale by two musculoskeletal radiologists blinded and with quantitative error metrics. Statistical Tests: Friedman's test accompanied with post hoc Wilcoxon signed‐rank test and intraclass correlation coefficient. The statistical cutoff P <0.05 adjusted by Bonferroni correction as necessary was utilized. Results: The networks trained in the study could synthesize conventional images with high image quality (Likert scores 3–4 on a 5‐point scale). Qualitatively, the best synthetic images were produced with combination of L1‐ and perceptual loss functions and perceptual loss alone, while L1‐loss alone led to significantly poorer image quality (Likert scores below 3). The interreader and intrareader agreement were high (0.80 and 0.92, respectively) and significant. However, quantitative image quality metrics indicated best performance for the pure L1‐loss. Data Conclusion: Synthesizing high‐quality contrast‐weighted images from MRF data using deep learning is feasible. However, more studies are needed to validate the diagnostic accuracy of these synthetic images. Evidence Level: 4. Technical Efficacy: Stage 1. [ABSTRACT FROM AUTHOR]

Objectives: To determine the diagnostic performance of ultrasonography (US) for evaluation of the ankle joint osteoarthritic (OA) changes. Cone‐beam computed tomography (CT) was used as the gold standard and US performance was compared with conventional radiography (CR). As a secondary aim, associations between the imaging findings and ankle symptoms were assessed. Methods: US was performed to 51 patients with ankle OA. Every patient had prior ankle CR and underwent cone‐beam CT during the same day as US examination. On US, effusion/synovitis, osteophytes, talar cartilage damage, and tenosynovitis were evaluated. Comparison to respective imaging findings on CR and cone‐beam CT was then performed. Single radiologist blinded to other modalities assessed all the imaging studies. Symptoms questionnaire, the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), was available for 48 patients. Results: US detected effusion/synovitis of the talocrural joint with 45% sensitivity and 90% specificity. For the detection of anterior talocrural osteophytes, US sensitivity was 78% and specificity 79%. For the medial talocrural osteophytes, they were 39 and 83%, and for the lateral talocrural osteophytes 54 and 100%, respectively. Considering cartilage damage of the talus, US yielded a low sensitivity of 18% and high specificity of 97%. Overall, the performance of US was only moderate and comparable to CR. The imaging findings showed only weak associations with ankle symptoms. Conclusions: The ability of US to detect ankle OA is only moderate. Interestingly, performance of CR also remained moderate. The associations between imaging findings and WOMAC score seem to be weak in ankle OA. [ABSTRACT FROM AUTHOR]