Search Results (125)

Background/Objectives: Elbow fractures are the most common injuries in children and are frequently evaluated with plain radiographs in the acute setting. As dedicated pediatric radiology services are not widely available, diagnosis of fractures could be delayed. Since 2023, ChatGPT-4 has offered image analysis capabilities, which has untapped potential for radiographic analysis. This study represents the first evaluation of ChatGPT-4o, a multimodal large language model, in interpreting pediatric elbow radiographs for fracture detection, thereby demonstrating its potential as a generalist AI tool distinct from domain-specific pediatric models. Methods: A curated set of 200 pediatric elbow radiographs (100 normal, 100 abnormal with at least one fracture site, 105 right elbow, and 95 left elbow radiographs) acquired between October 2023 and March 2024 at a tertiary pediatric hospital were analyzed in this case–control study. Each anonymized radiograph was evaluated by ChatGPT-4o via a standardized prompt. ChatGPT-4o’s prediction outputs (fracture vs. no fracture) were subsequently compared against verified radiology reports (ground-truth). Diagnostic performance metrics such as sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and F1 score were calculated. Results: ChatGPT-4o achieved an overall accuracy of 85% in detecting elbow fractures on pediatric radiographs, with a sensitivity of 87% and specificity of 82%. PPVs and NPVs were 83% and 86%, respectively. The F1 score was 0.85. ChatGPT-4o correctly identified the fracture site in 68 (78%) of the 87 studies in which it had detected fractures accurately. Cohen’s kappa coefficient was 0.69, indicating substantial agreement with actual diagnoses. Conclusions: This study highlights the utility and potential applications of ChatGPT-4o as a valuable point-of-care tool in aiding the detection of pediatric elbow fractures in emergency settings, particularly where specialist access is limited. Full article

Background/Objectives: Lumbosacral transitional vertebra (LSTV) is a common anatomical variant, but its identification on plain radiographs is often inconsistent. This inconsistency can lead to clinical complications such as chronic low back pain, misinterpretation of spinal parameters, and an increased risk of wrong-level surgery. This study aimed to develop and validate a deep learning-based artificial intelligence (AI) model for the automated detection of LSTV on plain lumbar radiographs. Methods: This retrospective observational study included a total of 3116 standing lumbar lateral radiographs. The presence or absence of lumbosacral transitional vertebra (LSTV) was definitively established using whole-spine imaging, CT, or MRI. Multiple deep learning architectures, including DINOv2, CLIP (ViT-B/32), and ResNet-50, were initially evaluated for binary classification of LSTV. Among these, the ResNet-50 model with partial fine-tuning achieved the best test performance and was subsequently selected for fivefold cross-validation using the training set. Model performance was assessed using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC), and interpretability was evaluated using gradient-weighted class activation mapping (Grad-CAM). Results: On the independent test set of 313 radiographs, the final model demonstrated robust diagnostic performance. It achieved an accuracy of 76.4%, a sensitivity of 85.1%, a specificity of 61.9%, and an AUC of 0.84. The model correctly identified 166 out of 195 LSTV cases and 73 out of 118 normal cases. Conclusions: This AI-based system offers a highly accurate and reliable method for the automated detection of LSTV on plain radiographs. It shows strong potential as a clinical decision-support tool to reduce diagnostic errors, improve pre-operative planning, and enhance patient safety. Full article

Objective: Bilateral facetectomy (BF) within minimally invasive transforaminal lumbar interbody fusion (MI-TLIF) remains debated regarding its advantages over unilateral facetectomy (UF) in restoring segmental lordosis, addressing spondylolisthesis and decompressing both neural foramina. The evidence is limited. We sought to determine the benefits of contralateral facetectomy on radiographic and clinical outcomes. Methods: We conducted a single-center retrospective analysis on patients with lumbar degenerative disease who underwent single-level percutaneous instrumentation and MI-TLIF with either UF or BF. Plain radiographs, CT and MRI were utilized for comparative radiographic analysis. Various intraoperative and clinical parameters were evaluated to assess surgical effort and clinical outcomes. Results: We included 81 UF and 23 BF cases; complete radiological data were available for 27 and 13 patients, respectively. Both techniques demonstrated a comparable increase in segmental lordosis (UF 2.1° ± 5.3° vs. BF 4.3° ± 5.4°, p > 0.1), which is below the study’s minimum detectable effect (MDE ≈ 5.1° at 80% power). Spondylolisthesis reduction was similar, with UF achieving a mean of 2.8 ± 2.2 mm and BF 2.4 ± 1.9 mm (p > 0.1). Mean posterior disc height did not differ significantly between groups (p > 0.1). The mean intraoperative blood loss was significantly higher with BF (803 ± 347 mL) compared to UF (437 ± 207 mL, p < 0.001). The mean duration of surgery was significantly longer for BF (240 ± 48 min) compared to UF (197 ± 37 min, p = 0.001). Conclusions: This study found no evidence of a large advantage of BF over UF in restoring segmental lordosis, spondylolisthesis and posterior disc height in monosegmental MI-TLIF surgery. Given the higher blood loss and longer operative time observed with BF, its use should be selective for specific indications. Full article

Background: Sacral and pelvic insufficiency fractures (SIFs and PIFs) are increasingly recognized yet frequently underdiagnosed complications after adult spinal deformity (ASD) surgery, particularly in patients undergoing long-segment spinal fusion to the sacrum or pelvis. Methods: We present a representative case of sacral and pelvic insufficiency fractures following extensive spinal fusion, highlighting diagnostic and therapeutic challenges. In addition, a systematic review of the literature was performed according to PRISMA guidelines through PubMed, MEDLINE, and Scopus databases, including studies up to December 2024. Data regarding demographics, risk factors, diagnostic modalities, management strategies, and outcomes were extracted and narratively synthesized. Results: A total of 21 studies comprising 89 patients were included. The majority were elderly postmenopausal women with osteoporosis and additional risk factors such as chronic corticosteroid therapy or high body mass index. Diagnosis was frequently delayed due to low sensitivity of plain radiographs, whereas computed tomography was the most reliable modality. Management was surgical in 49 patients (55%)—most commonly extension of fixation to the pelvis or use of S2-alar-iliac screws—with favorable fracture healing reported in most cases. Conservative treatment, employed in 40 patients (45%), included bracing, restricted activity, and bone health optimization, also leading to healing in the majority of cases. Conclusions: Sacral and pelvic insufficiency fractures represent an underrecognized but clinically significant complication after ASD surgery. Early recognition through cross-sectional imaging (CT/MRI) is crucial, and both surgical and conservative approaches can be effective if tailored to patient and fracture characteristics. Full article

Introduction: Ankylosing spondylitis (AS) is a chronic inflammatory disorder that causes progressive ossification and fusion of the spine, particularly in the cervical region. This results in a rigid spinal column that is highly susceptible to unstable fractures, even after low-energy trauma. Cervical fractures in AS are often complex, extending through multiple spinal segments, and are associated with a high risk of neurological compromise. Esophageal injury associated with such fractures is rare but clinically significant, as the anatomical vicinity of the esophagus makes it vulnerable to direct trauma, delayed perforation, or secondary damage from fracture displacement and hardware failure. Aim: The purpose of this review is to present and highlight the clinical relevance of esophageal injury in cervical spine trauma among patients with AS, emphasizing the diagnostic challenges and surgical treatment in order to improve outcomes. Results: Esophageal injuries in the context of AS-related cervical trauma are frequently overlooked due to subtle clinical manifestations such as dysphagia, subcutaneous emphysema, or covert signs of mediastinitis. Plain radiographs are insufficient to identify such complications; advanced imaging modalities are often required for detection. Management is complex and usually demands a multidisciplinary approach, involving both stabilization of the cervical spine and repair of the esophagus. Despite treatment efforts, these patients remain at increased risk for morbidity and mortality, mainly due to infection and sepsis. Conclusions: Esophageal injury in cervical spine trauma associated with AS is an uncommon but life-threatening condition. Early recognition, comprehensive radiologic evaluation, and careful surgical planning are crucial for optimal management. Heightened clinical suspicion and awareness of this rare complication are essential to improve diagnostic accuracy and patient outcomes. Full article

Background/Objectives: The clinical management of adolescent idiopathic scoliosis (AIS) is hindered by the inability to accurately predict curve progression. Although skeletal maturity and the initial Cobb angle are established predictors of progression, their combined predictive accuracy remains limited. This study aimed to develop a robust and interpretable artificial intelligence (AI) system using deep learning (DL) models to predict the progression of scoliosis using only standing frontal radiographs. Methods: We conducted a multicenter study involving 542 patients with AIS. After excluding 52 borderline progression cases (6–9° progression in the Cobb angle), 294 and 196 patients were assigned to progression (≥10° increase) and non-progression (≤5° increase) groups, respectively, considering a 2-year follow-up. Frontal whole spinal radiographs were preprocessed using histogram equalization and divided into two regions of interest (ROIs) (ROI 1, skull base–femoral head; ROI 2, C7–iliac crest). Six pretrained DL models, including convolutional neural networks (CNNs) and transformer-based models, were trained on the radiograph images. Gradient-weighted class activation mapping (Grad-CAM) was further performed for model interpretation. Results: Ensemble models outperformed individual ones, with the average ensemble model achieving area under the curve (AUC) values of 0.769 for ROI 1 and 0.755 for ROI 2. Grad-CAM revealed that the CNNs tended to focus on the local curve apex, whereas the transformer-based models demonstrated global attention across the spine, ribs, and pelvis. Models trained on ROI 2 performed comparably with respect to those using ROI 1, supporting the feasibility of image standardization without a loss of accuracy. Conclusions: This study establishes the clinical potential of transformer-based DL models for predicting the progression of scoliosis using only plain radiographs. Our multicenter approach, high AUC values, and interpretable architectures support the integration of AI into clinical decision-making for the early treatment of AIS. Full article

Background and Clinical Significance: Scapular stress fractures are exceptionally rare in athletes and are notoriously difficult to diagnose due to their subtle presentation and poor sensitivity on initial radiographs. This case report describes the diagnostic challenge of a scapular body stress fracture in an elite boxer who initially presented with wrist pain. Case Presentation: A 19-year-old right-hand-dominant female elite boxer presented with a three-month history of bilateral wrist pain. Initial examination and MRI were consistent with a triangular fibrocartilage complex (TFCC) injury. Despite conservative management, her symptoms persisted, and she subsequently developed mechanical right shoulder pain and a sensation of instability. Physical examination revealed scapular dyskinesis, with a positive push-up test and weakness on punch protraction. Plain radiographs of the scapula were unremarkable. Point-of-care musculoskeletal ultrasound (MSK US) identified a cortical irregularity at the medial scapular border. A subsequent computed tomography (CT) scan obtained at three-month follow-up definitively confirmed a stress fracture at this site. Treatment focused on scapular stabilization via prolotherapy and activity modification, leading to symptomatic resolution and a successful return to sport. Conclusions: This case underscores the importance of evaluating the entire kinetic chain in athletes presenting with focal complaints. It demonstrates the utility of MSK US as an effective initial screening tool for cortical stress fractures and highlights the necessity of CT for definitive confirmation. Clinicians should maintain a high index of suspicion for scapular stress injuries in overhead athletes with unexplained shoulder dysfunction. Full article

Objective: To develop and validate a ResNet-50-based deep learning model for automatic detection of osteomyelitis (DFO) in plain radiographs of patients with diabetic foot ulcers (DFUs). Research Design and Methods: This retrospective study included 168 patients with type one or type two diabetes and clinical suspicion of DFO confirmed via a surgical bone biopsy. An experienced clinician and a pretrained ResNet-50 model independently interpreted the radiographs. The model was developed using Python-based frameworks with ChatGPT assistance for coding. The diagnostic performance was assessed against the histopathological findings, calculating sensitivity, specificity, the positive predictive value (PPV), the negative predictive value (NPV), and the likelihood ratios. Agreement between the AI model and the clinician was evaluated using Cohen’s kappa coefficient. Results: The AI model demonstrated high sensitivity (92.8%) and PPV (0.97), but low-level specificity (4.4%). The clinician showed 90.2% sensitivity and 37.8% specificity. The Cohen’s kappa coefficient between the AI model and the clinician was −0.105 (p = 0.117), indicating weak agreement. Both the methods tended to classify many cases as DFO-positive, with 81.5% agreement in the positive cases. Conclusions: This study demonstrates the potential of IA to support the radiographic diagnosis of DFO using a ResNet-50-based deep learning model. AI-assisted radiographic interpretation could enhance early DFO detection, particularly in high-prevalence settings. However, further validation is necessary to improve its specificity and assess its utility in primary care. Full article

Pneumothorax is a potentially life-threatening condition defined as the collapse of the lung due to air leakage into the chest cavity. Delays in the diagnosis of pneumothorax can lead to severe complications and even mortality. A significant challenge in pneumothorax diagnosis is the shortage of radiologists, resulting in the absence of written reports in plain X-rays and, consequently, impacting patient care. In this paper, we propose an automatic triage system for pneumothorax detection in X-ray images based on deep learning. We address this problem from the perspective of multi-source domain adaptation where different datasets available on the Internet are used for training and testing. In particular, we use datasets which contain chest X-ray images corresponding to different conditions (including pneumothorax). A convolutional neural network (CNN) with an EfficientNet architecture is trained and optimized to identify radiographic signs of pneumothorax using those public datasets. We present the results using cross-dataset validation, demonstrating the robustness and generalization capabilities of our multi-source solution across different datasets. The experimental results demonstrate the model’s potential to assist clinicians in prioritizing and correctly detecting urgent cases of pneumothorax using different integrated deployment strategies. Full article

Background/Objectives: Additive manufacturing (AM) enables the production of cementless acetabular cups with porous surfaces that facilitate early osseointegration. Directed energy deposition (DED), a form of AM, allows the direct welding of porous structures onto metal substrates without requiring a vacuum environment, offering advantages over conventional powder bed fusion methods. Despite growing interest in DED, no prospective clinical studies evaluating DED-based acetabular components have been published to date. This study assessed short-term outcomes of a DED-based 3D-printed acetabular cup in total hip arthroplasty (THA). Methods: A total of 120 patients who underwent primary cementless THA using the Corentec Mirabo Z^® acetabular cup were prospectively enrolled. Among them, 124 hips from 100 patients who had completed a minimum of 24 months of follow-up were included in the analysis. Clinical outcomes were assessed using the Harris hip score (HHS), WOMAC, EQ-5D-5L, and pain NRS. Radiographic evaluation included measurements of cup position, osseointegration, and detection of interfacial or polar gaps on CT and plain radiographs. Implant-related complications were also recorded. Results: At a mean follow-up of 34.6 months, the implant survival rate was 99.3%, with one revision due to suspected osseointegration failure. The HHS improved from 56.6 to 91.4 at 24 months, and the NRS decreased from 6.2 to 1.1 (both p < 0.001). Interfacial gaps were observed in 58.1% of cases on CT, though most were <1 mm and not clinically significant. Common postoperative issues included greater trochanteric pain syndrome, squeaking, and iliotibial band tightness, all of which were resolved with conservative treatment. Conclusions: DED-based 3D-printed acetabular cups demonstrated favorable short-term clinical and radiographic outcomes, with high survivorship and reliable early osseointegration in cementless THA. Full article

Background/Objectives: Akin osteotomy, in the context of corrective surgery for hallux valgus, is an effective tool available to surgeons. However, few studies have thoroughly investigated the anatomical and technical characteristics to be considered in order to perform an optimal osteotomy. This cross-sectional observational study aims to identify the ideal site for performing Akin osteotomy and to identify the factors that influence its corrective power. Methods: To this end, an analysis was conducted on a random sample of 100 patients (186 feet) who underwent X-rays without surgical treatment. Variations in the width between the metaphysis and diaphysis were measured at five different points. For each cut level, corresponding to wedge bases of 2, 3 and 4 mm, three corrective angles were calculated. In addition, the distance between the cut line and the joint was recorded. Results: The base width ranged from 12.6 to 23.2 mm, showing greater variability in the metaphyseal region. The corrective power of the osteotomy showed wide variability, ranging from 5.9 to 18.4 degrees. Four determining factors emerged: the width of the base, the inclination of the medial cortex, the height at which the cut is made and the thickness of the wedge of bone removed. The data obtained suggest that osteotomy should not be performed less than 10 mm from the joint line to avoid the risk of joint invasion. Conclusions: In conclusion, there is no universally ideal site for performing an Akin osteotomy: the choice depends on the degree of correction desired, which in turn is influenced by the factors identified in the study. Full article

Background and clinical significance: Osteonecrosis of the femoral head (ONFH) is a disease of the epiphysis caused by the death of osteocytes and osteoblasts, resulting in debilitating pain. ONFH can be traumatic or nontraumatic, with prolonged glucocorticoid use being the leading cause of nontraumatic ONFH. Atopic dermatitis (AD) is a chronic inflammatory skin condition typically treated with topical corticosteroids. ONFH following topical corticosteroid treatment is exceedingly rare, with limited documentation in the literature. We present a case of an under-recognized complication of prolonged topical corticosteroid treatment. Case presentation: We report a case of a 29-year-old Caucasian male patient with sharp right hip pain. Plain radiographs, a CT scan, and an MRI indicated Ficat and Arlet stage 3 ONFH. The patient reported the prolonged uncontrolled use of topical mometasone furoate for five years due to AD. Following the diagnosis, topical corticosteroids were discontinued, and the treatment was shifted to tacrolimus and, subsequently, to oral methotrexate with folic acid. The patient underwent a total hip arthroplasty in June 2022. Given his young age and poor response to previous treatments, he was transitioned to upadacitinib, which led to significant improvement without skin flare-ups or postoperative hip pain. Conclusions: This case highlights the rare, but serious, risk of ONFH associated with long-term topical corticosteroid use. It underscores the importance of monitoring systemic side effects in dermatological therapies and educating patients on proper corticosteroid use. Alternative treatments, such as upadacitinib, should be considered in young male patients to prevent severe complications. Full article

Minimal facet and lateral mass fractures of the subaxial cervical spine (C3–C7) are a distinct subset of spinal injuries that present diagnostic and therapeutic challenges. These fractures often result from low-energy trauma or hyperextension mechanisms. They are frequently stable. However, subtle fracture instability and associated soft tissue injuries may lead to delayed instability, neurological compromise, and/or chronic severe pain if not properly identified. Accurate diagnosis relies on a combination of plain radiography, high-resolution computed tomography (CT), and magnetic resonance imaging (MRI) to assess bony and ligamentous integrity. Treatment strategy is determined based on fracture stability, neurological status, and radiographic findings. Most stable fractures can be effectively treated with conservative treatment, allowing for natural healing while minimizing complications. However, when instability is suspected—such as those with significant disc and ligamentous injuries, progressive deformity, or neurological deficits—surgical stabilization may be considered. The presence of vertebral artery injury (VAI) can further complicate management. To mitigate the risk of stroke, a multidisciplinary approach that includes neurosurgery, vascular surgery, and interventional radiology is needed. Surgical treatment aims to restore spinal alignment, maintain stability, and prevent further neurological deterioration with approaches tailored to individual fracture patterns and patient-specific factors. Advances in surgical techniques, perioperative management, and endovascular interventions for VAI continue refining treatment options to improve clinical outcomes while minimizing complications. Despite increasing knowledge of these fractures and associated vascular injuries, optimal treatment strategies remain unclear due to limited high-quality evidence. This review provides a comprehensive analysis of the anatomy, biomechanics, classification, imaging modalities, and treatment strategies for minimal facet and lateral mass fractures in the subaxial cervical spine, highlighting recent advancements in diagnostic tools, therapeutic approaches, and managing vertebral artery injuries. A more precise understanding of the natural history and optimal management of these injuries will help spine specialists refine clinical decision-making and improve patient outcomes. Full article

Background and Objectives: To investigate the natural metatasophalangeal (MTP) joint distance, we studied the appropriate degree of distraction for arthroscopy and the associated factors, including age, gender, and body mass index (BMI). Materials and Methods: Sixty-seven patients who underwent MTP joint arthroscopy or foot and ankle surgery from April 2013 to June 2020 were enrolled. Foot plain radiographs were taken using a mini-fluoroscan with no traction, manual traction, and traction of 5 pounds, 10 pounds, and 15 pounds to measure the MTP joint distance. Age, gender, and BMI were compared as associated factors. The minimum joint distance of MTP joint arthroscopy was defined as 2.8 mm, which was the sheath size of a 1.9 mm, 30° high-definition arthroscope. Results: Regarding natural MTP joint space sizes, the MTP-2 joint had the largest joint size (2.39 ± 0.37 mm). The MTP-5 joint had the smallest joint size (1.59 ± 0.34 mm). Traction of 10 lb was an appropriate distraction force for the MTP-1 joint (3.09 ± 0.03 mm) and MTP-4 joint (3.07± 0.47 mm) in arthroscopy. Traction of 5lb was an appropriate distraction force for the MTP-2 (3.32 ± 0.60 mm), MTP-3 (2.89 ± 0.50 mm), and MTP-5 (2.97 ± 0.49 mm) joints. For the MTP-1 and MTP-4 joints, males had significantly greater joint space sizes than females for no traction (p = 0.039), manual traction (p = 0.002), and traction of 5 pounds (p = 0.004), 10 pounds, (p = 0.013), and 15 pounds (p = 0.024). There was no statistically significant difference in joint space size according to age or BMI for any MTP joints (p > 0.05). Conclusions: Among natural joint spaces without traction, the MTP-2 joint had the largest joint size while the MTP-5 joint had the smallest joint size. In MTP joint arthroscopy, a traction power of 10 lb is sufficient for appropriate distraction of all MTP joints. Less distraction power is required for males than for females, especially for the MTP-1 and MTP-4 joints. Full article

Background: The accuracy of fracture diagnosis through radiographic imaging largely depends on image quality and the interpreter’s experience. In resource-limited settings (minimal-resource settings), imaging quality is often lower than in standard-resource facilities, potentially affecting diagnostic accuracy. Objective: This study aims to compare the diagnostic accuracy of plain radiograph interpretations between minimal-resource and standard-resource methods and assess the influence of interpreter experience on diagnostic precision. Methods: This cross-sectional study is based on secondary data from patients’ medical records at the Dr. Zainoel Abidin General Hospital (RSUDZA) Banda Aceh, Indonesia. Comparisons between minimal-resource and standard-resource interpretations were made and validated using a reference standard (gold standard). Statistical analyses included diagnostic testing, Chi-square tests, and ROC curve analysis to evaluate sensitivity, specificity, and accuracy. Results: The findings indicate that standard-resource radiographs have significantly higher accuracy than minimal-resource radiographs (p < 0.05). Radiologists demonstrated the highest diagnostic accuracy compared to general practitioners and radiology residents. Conclusions: The standard-resource method is superior in detecting fractures compared to the minimal-resource method. Enhancing imaging quality and providing additional training for medical personnel are essential to improve diagnostic accuracy in resource-limited settings. Full article