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.

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.

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.

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.

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.

Gastric metastasis from renal cell carcinoma (RCC) is extremely rare, occurring in 0.2% of all RCC cases. Owing to its low prevalence, metachronous gastric metastasis from RCC may be underdiagnosed, and the imaging findings have not been well-established. Herein we present a case of metastatic RCC manifesting as a gastric polyp in a 70-year-old female along with a literature review on the imaging findings of gastric metastases from RCC. In patients presenting with gastric hyper-enhancing polypoid masses, metastasis from RCC should be considered as a differential diagnosis.

Background: This study aimed to assess the diagnostic feasibility of radiomics analysis based on magnetic resonance (MR)-proton density fat fraction (PDFF) for grading hepatic steatosis in patients with suspected non-alcoholic fatty liver disease (NAFLD). Methods: This retrospective study included 106 patients with suspected NAFLD who underwent a hepatic parenchymal biopsy. MR-PDFF and MR spectroscopy were performed on all patients using a 3.0-T scanner. Following whole-volume segmentation of the MRPDFF images, 833 radiomic features were analyzed using a commercial program. Radiologic features were analyzed, including median and mean values of the multiple regions of interest and variable clinical features. A random forest regressor was used to extract the important radiomic, radiologic, and clinical features. The model was trained using 20 repeated 10-fold cross-validations to classify the NAFLD steatosis grade. The area under the receiver operating characteristic curve (AUROC) was evaluated using a classifier to diagnose steatosis grades. Results: The levels of pathological hepatic steatosis were classified as low-grade steatosis (grade, 0–1; n = 82) and high-grade steatosis (grade, 2–3; n = 24). Fifteen important features were extracted from the radiomic analysis, with the three most important being wavelet-LLL neighboring gray tone difference matrix coarseness, original first-order mean, and 90th percentile. The MR spectroscopy mean value was extracted as a more important feature than the MR-PDFF mean or median in radiologic measures. Alanine aminotransferase has been identified as the most important clinical feature. The AUROC of the classifier using radiomics was comparable to that of radiologic measures (0.94 ± 0.09 and 0.96 ± 0.08, respectively). Conclusion MR-PDFF-derived radiomics may provide a comparable alternative for grading hepatic steatosis in patients with suspected NAFLD.

Background: The purpose of this study was to compare the histologic outcomes of rotator cuff (RC) repair with demineralized bone matrix (DBM) augmentation and those without DBM augmentation and to evaluate the role of DBM for tendon-to-bone (TB) healing in a rabbit model. Methods: Twenty-six adult male New Zealand white rabbits were randomly allocated to the control group (n = 13) or the DBM group (n = 13). Repair was performed 8 weeks after complete transection of the right supraspinatus tendon of all rabbits. In the control group, RC repair was achieved by a standard transosseous technique. In the DBM group, RC repair was achieved using the same technique, and DBM was interposed between the cuff and bone. After 8 weeks, the RC tendon entheses from all rabbits were processed for gross and histologic examination. Results: On gross TB healing, 2 of 11 specimens in the control group were unhealed and no specimen was grossly unhealed in the DBM group (p = 0.421). In the control group, the tendon midsubstance was disorganized with randomly and loosely arranged collagen fibers and rounded fibroblastic nuclei. The TB interface was predominantly fibrous with small regions of fibrocartilage, especially mineralized fibrocartilage. In the DBM group, the tendon midsubstance appeared normal and comprised densely arranged collagen fibers, with orientated crimped collagen fibers running in the longitudinal direction of the tendon. These fibers were interspersed with elongated fibroblast nuclei. The TB interface consisted of organized collagen fibers with large quantities of fibrocartilage and mineralized fibrocartilage. Conclusions The use of DBM for TB interface healing in rabbit experiments showed good results in gross and histologic analysis. However, it is difficult to draw a solid conclusion because the sample size is small. Further evaluation in the in vivo setting is necessary to determine clinical recommendations.

Background: The purpose of this study was to compare the histologic outcomes of rotator cuff (RC) repair with demineralized bone matrix (DBM) augmentation and those without DBM augmentation and to evaluate the role of DBM for tendon-to-bone (TB) healing in a rabbit model. Methods: Twenty-six adult male New Zealand white rabbits were randomly allocated to the control group (n = 13) or the DBM group (n = 13). Repair was performed 8 weeks after complete transection of the right supraspinatus tendon of all rabbits. In the control group, RC repair was achieved by a standard transosseous technique. In the DBM group, RC repair was achieved using the same technique, and DBM was interposed between the cuff and bone. After 8 weeks, the RC tendon entheses from all rabbits were processed for gross and histologic examination. Results: On gross TB healing, 2 of 11 specimens in the control group were unhealed and no specimen was grossly unhealed in the DBM group (p = 0.421). In the control group, the tendon midsubstance was disorganized with randomly and loosely arranged collagen fibers and rounded fibroblastic nuclei. The TB interface was predominantly fibrous with small regions of fibrocartilage, especially mineralized fibrocartilage. In the DBM group, the tendon midsubstance appeared normal and comprised densely arranged collagen fibers, with orientated crimped collagen fibers running in the longitudinal direction of the tendon. These fibers were interspersed with elongated fibroblast nuclei. The TB interface consisted of organized collagen fibers with large quantities of fibrocartilage and mineralized fibrocartilage. Conclusions The use of DBM for TB interface healing in rabbit experiments showed good results in gross and histologic analysis. However, it is difficult to draw a solid conclusion because the sample size is small. Further evaluation in the in vivo setting is necessary to determine clinical recommendations.

A 48-year-old man visited the emergency room with right hip pain that started abruptly while walking out of the bathroom. Computed tomography showed an intraosseous mass in the femoral neck. The patient had a 15-year history of gout and had numerous bilateral tophi in his hands, feet, knees, and elbows. After operation, we diagnosed a pathological fracture due to intraosseous tophi. Patients with hip pain who have many subcutaneous tophi and long-standing gout should be diagnosed carefully. Peri-hip joint pain caused by gout is uncommon, however, if a patient complains of pain, a simple X-ray may be required. If intraosseous tophi are present, appropriate treatment (e.g., strict hyperuricemia control with or without prophylactic internal fixation), may be required before fracture occurs.
Arthralgia ; Elbow ; Emergency Service, Hospital ; Femoral Neck Fractures ; Femur Neck ; Foot ; Fractures, Spontaneous ; Gout ; Hand ; Hip ; Humans ; Hyperuricemia ; Knee ; Middle Aged ; Walking