INTRODUCTION: Radiology plays an integral role in fracture detection in the emergency department (ED). After hours, when there are fewer reporting radiologists, most radiographs are interpreted by ED physicians. A minority of these interpretations may miss diagnoses, which later require the callback of patients for further management. Artificial intelligence (AI) has been viewed as a potential solution to augment the shortage of radiologists after hours. We explored the efficacy of an AI solution in the detection of appendicular and pelvic fractures for adult radiographs performed after hours at a general hospital ED in Singapore, and estimated the potential monetary and non-monetary benefits. METHODS: One hundred and fifty anonymised abnormal radiographs were retrospectively collected and fed through an AI fracture detection solution. The radiographs were re-read by two radiologist reviewers and their consensus was established as the reference standard. Cases were stratified based on the concordance between the AI solution and the reviewers' findings. Discordant cases were further analysed based on the nature of the discrepancy into overcall and undercall subgroups. Statistical analysis was performed to evaluate the accuracy, sensitivity and inter-rater reliability of the AI solution. RESULTS: Ninety-two examinations were included in the final study radiograph set. The AI solution had a sensitivity of 98.9%, an accuracy of 85.9% and an almost perfect agreement with the reference standard. CONCLUSION An AI fracture detection solution has similar sensitivity to human radiologists in the detection of fractures on ED appendicular and pelvic radiographs. Its implementation offers significant potential measurable cost, manpower and time savings.
Humans ; Singapore ; Emergency Service, Hospital ; Fractures, Bone/diagnostic imaging* ; Artificial Intelligence ; Retrospective Studies ; Adult ; Male ; Female ; Cost Savings ; Middle Aged ; Pelvic Bones/diagnostic imaging* ; Reproducibility of Results ; Aged ; Sensitivity and Specificity ; Radiography

Synthetic CT (sCT) generated from CBCT has proven effective in artifact reduction and CT number correction, facilitating precise radiation dose calculation. However, the quality of different regions in sCT images is severely imbalanced, with soft tissue region exhibiting notably inferior quality compared to others. To address this imbalance, we proposed a Multi-Task Attention Network (MuTA-Net) based on VGG-16, specifically focusing the enhancement of image quality in soft tissue region of sCT. First, we introduced a multi-task learning strategy that divides the sCT generation task into three sub-tasks: global image generation, soft tissue region generation and bone region segmentation. This approach ensured the quality of overall sCT image while enhancing the network's focus on feature extraction and generation for soft tissues region. The result of bone region segmentation task guided the fusion of sub-tasks results. Then, we designed an attention module to further optimize feature extraction capabilities of the network. Finally, by employing a results fusion module, the results of three sub-tasks were integrated, generating a high-quality sCT image. Experimental results on head and neck CBCT demonstrated that the sCT images generated by the proposed MuTA-Net exhibited a 12.52% reduction in mean absolute error in soft tissue region, compared to the best performance among the three comparative methods, including ResNet, U-Net, and U-Net++. It can be seen that MuTA-Net is suitable for high-quality sCT image generation and has potential application value in the field of CBCT guided adaptive radiation therapy.
Cone-Beam Computed Tomography/methods* ; Humans ; Image Processing, Computer-Assisted/methods* ; Artifacts ; Algorithms ; Bone and Bones/diagnostic imaging* ; Neural Networks, Computer

OBJECTIVE: To summarize the advances in MRI-based bone quality scoring systems and their clinical applications. METHODS: A comprehensive literature review was conducted on recent studies related to the MRI-based bone quality scoring system, focusing on measurement methods, influencing factors, and clinical significance. RESULTS: Osteoporosis has a high incidence in China, significantly impacting patients' quality of life and the postoperative outcomes of related orthopedic surgeries. Early identification of osteoporosis holds important clinical significance. In recent years, both domestic and international research has enriched the MRI-based bone quality scoring systems, which includes vertebral bone quality scoring, endplate bone quality scoring, and pedicle bone quality scoring. Compared to the "gold standard" of bone density measurement, dual-energy X-ray absorptiometry, the bone quality scoring systems demonstrate good efficacy in identifying abnormal bone mass and predicting postoperative complications, while being less influenced by degenerative changes in the lumbar spine, indicating its important clinical application value. CONCLUSION The MRI-based bone quality scoring systems have good value in clinical applications. However, current studies are mostly retrospective cohort and case-control studies, which carry a risk of bias. The clinical application value needs further clarification through meta-analysis and large-scale prospective studies.
Humans ; Magnetic Resonance Imaging/methods* ; Bone Density ; Osteoporosis/diagnosis* ; Absorptiometry, Photon ; Bone and Bones/diagnostic imaging* ; Lumbar Vertebrae/diagnostic imaging* ; Quality of Life ; Postoperative Complications

OBJECTIVE: To review the clinical characteristics of patients with traumatic spinopelvic dissociation (SPD) and explore the diagnostic and therapeutic methods. METHODS: A clinical data of 22 patients with SPD who underwent surgical treatment between March 2019 and August 2024 was retrospectively analyzed. There were 13 males and 9 females, with an average age of 35.5 years (range, 14-61 years). The causes of injury included falling from height in 16 cases, traffic accidents in 5 cases, and compression injury in 1 case. Sacral fractures were classified based on morphology into "U" type (9 cases), "H" type (7 cases), "T" type (4 cases), and "λ" type (2 cases). According to the Roy-Camille classification, there were 4 cases of type Ⅰ, 12 cases of type Ⅱ, 2 cases of type Ⅲ, and 4 cases of type Ⅳ. The Cobb angle was (35.7± 22.0)°. Sixteen patients were accompanied by lumbosacral trunk and cauda equina nerve injury, which was classified as grade Ⅱ in 5 cases, grade Ⅲ in 5 cases, and grade Ⅳ in 6 cases according to the Gibbons grading. The time from injury to operation was 2-17 days (mean, 5.7 days). Based on the type of sacral fracture and sacral nerve injury, 6 cases were treated with closed reduction and minimally invasive percutaneous sacroiliac screw fixation, 16 cases were treated with open reduction and lumbar iliac fixation (8 cases)/triangular fixation (8 cases). Among them, 11 patients with severe fracture displacement and kyphotic deformity leading to sacral canal stenosis or bony impingement within the sacral foramen underwent laminectomy and sacral nerve decompression. X-ray films and CT were reviewed during followed-up. The Matta score was used to evaluate the quality of fracture reduction. At last follow-up, the Majeed score was used to assess the functional recovery, and the Gibbons grading was used to evaluate the nerve function. RESULTS: All operations were successfully completed. All patients were followed up 8-64 months (mean, 20.4 months). Two patients developed deep vein thrombosis of the lower limbs, 2 had incision infections, and 1 developed a sacral pressure ulcer; no other complications occurred. Radiological examination showed that the Cobb angle was (12.0±6.8)°, which was significantly different from the preoperative one ( t=6.000, P<0.001). The Cobb angle in 16 patients who underwent open reduction was (14.9±5.5)°, which was significantly different from the preoperative one [(46.8±13.9)° ] ( t=8.684, P<0.001). According to the Matta scoring criteria, the quality of fracture reduction was rated as excellent in 8 cases, good in 7 cases, fair in 5 cases, and poor in 2 cases, with an excellent and good rate of 68.2%. Bone callus formation was observed at the fracture site in all patients at 12 weeks after operation, and bony union achieved in all cases at last follow-up, with a healing time ranging from 12 to 36 weeks (mean, 17.6 weeks). At last follow-up, the Majeed score was rated as excellent in 7 cases, good in 10 cases, fair in 4 cases, and poor in 1 case, with an excellent and good rate of 77.3%. One patient experienced a unilateral iliac screw breakage at 12 months after operation, but the fracture had already healed, and there was no loss of reduction. Among the 16 patients with preoperative sacral nerve injury, 11 cases showed improvement in nerve function (6 cases) or recovery (5 cases). CONCLUSION SPD with low incidence, multiple associated injuries, and high incidence of sacral nerve injury, requires timely decompression of the sacral canal for symptomatic sacral nerve compression, fractures reduction, deformities correction, and stable fixation.
Humans ; Adult ; Female ; Male ; Retrospective Studies ; Middle Aged ; Spinal Fractures/diagnostic imaging* ; Adolescent ; Sacrum/diagnostic imaging* ; Fracture Fixation, Internal/methods* ; Young Adult ; Pelvic Bones/surgery* ; Treatment Outcome ; Bone Screws

OBJECTIVE: To compare effectiveness of multiple metatarsal osteotomy versus first metatarsophalangeal arthrodesis in treating severe metatarsal adductus hallux valgus deformity. METHODS: A retrospective analysis was conducted on the clinical data of 25 patients with severe metatarsal adductus hallux valgus deformity admitted between June 2010 and May 2014 who met the selective criteria. Among them, 15 patients underwent multiple metatarsal osteotomy (osteotomy group), while 10 patients underwent first metatarsophalangeal arthrodesis (fusion group). There was no significant difference between groups ( P>0.05) in gender, age, disease duration, affected side, preoperative American Orthopaedic Foot and Ankle Society (AOFAS) score, visual analogue scale (VAS) score for pain, intermetatarsal angle (IMA), hallux valgus angle (HVA), or metatarsal adduction angle (MAA). The osteotomy group underwent fixation with screws and/or staples fixation, while the fusion group utilized anatomic fusion plates and trans-articular compression screws. The study compared the following outcome indicators between groups: operation time, pre- and post-operative differences (change values) in AOFAS scores, VAS scores, and radiographic parameters (HVA, MAA), osteotomy healing outcomes, and recurrence of hallux valgus deformity. RESULTS: Both surgical procedures were completed successfully. The operation time was significantly shorter in the fusion group than in the osteotomy group ( P<0.05). All patients were followed up 96-144 months (mean, 116 months). The follow-up time was (129.1±7.2) months in the osteotomy group and (104.4±8.0) months in the fusion group, with no significant difference between groups ( P>0.05). X-ray films revealed the radiographic union in two groups, and the fusion time was significantly shorter in the fusion group than in the osteotomy group ( P<0.05). At last follow-up, both groups demonstrated significant improvements in AOFAS and VAS scores compared to preoperative levels ( P<0.05). However, the differences in the change values of AOFAS and VAS scores between groups were not significant ( P>0.05). During follow-up, 3 cases (20%) of deformity recurrence occurred in the osteotomy group, while no recurrence was observed in the fusion group. There was no significant difference in the incidences of deformity recurrence between groups ( P>0.05). CONCLUSION For severe metatarsus adductus hallux valgus deformities, both multiple metatarsal osteotomy and first metatarsophalangeal arthrodesis can correct the deformity. The former preserves metatarsophalangeal joint mobility but demands high technical proficiency from the surgeon, involves relatively longer operation times, extended bone healing periods, and higher complication incidences. The latter procedure is relatively simpler, facilitates faster postoperative recovery, allows early weight-bearing, and yields more reliable outcomes, though it sacrifices first metatarsophalangeal joint mobility.
Humans ; Osteotomy/methods* ; Hallux Valgus/diagnostic imaging* ; Retrospective Studies ; Arthrodesis/instrumentation* ; Treatment Outcome ; Metatarsal Bones/diagnostic imaging* ; Metatarsophalangeal Joint/diagnostic imaging* ; Male ; Female ; Bone Screws ; Adult ; Middle Aged ; Bone Plates ; Pain Measurement

OBJECTIVE: To define a safe distance range from the LC-Ⅱ screw trajectory to the apex of the greater sciatic notch based on pelvic CT measurements, and to clinically assess the feasibility of using this range under iliac oblique view combined with iliac tangential view fluoroscopy to guide screw insertion. METHODS: CT scans of 104 normal pelvises collected between January 2022 and February 2025 were analyzed. There were 52 males and 52 females, with a median age of 45.8 years (range, 19-76 years). The RadiAnt DICOM Viewer software was used to reconstruct coronal, sagittal, and axial sections of the potential LC-Ⅱ screw trajectory. The maximum safety distance (Dmax) and the optimal safety distance (Dopt) from this trajectory to the greater sciatic notch were measured on the coronal and sagittal views. A retrospective analysis was conducted on 21 patients with LC-Ⅱ type pelvic fractures treated with the LC-Ⅱ screws fixation. And the screws were placed within the pre-defined safe distance under guidance from the iliac oblique view and iliac tangential view. Postoperative CT scans were obtained to evaluate the accuracy of screw placement. RESULTS: Radiographic measurements from the 104 cases showed that Dmax ranged from 1.87 to 3.87 cm (mean, 2.79 cm), and Dopt ranged from 1.01 to 2.92 cm (mean, 1.84 cm). Both Dmax and Dopt were significantly greater in the males than in the females ( P>0.05). No significant difference was found between the left and right sides within the same gender ( P>0.05). All 21 patients successfully underwent fracture reduction and fixation, with a total of 23 LC-Ⅱscrews implanted. According to the Lonstein grading system, the screw placement accuracy was rated as excellent in 16 screws, good in 3, fair in 3, and poor in 1, with an excellent and good rate of 82.6%. CONCLUSION Utilizing a CT-defined safe distance range from the screw trajectory to the greater sciatic notch, and adhering to this range under iliac oblique view combined with iliac tangential view fluoroscopy, enables the accurate and precise placement of LC-Ⅱ screws.
Humans ; Male ; Female ; Middle Aged ; Bone Screws ; Adult ; Tomography, X-Ray Computed/methods* ; Aged ; Ilium/surgery* ; Pelvic Bones/diagnostic imaging* ; Fracture Fixation, Internal/instrumentation* ; Retrospective Studies ; Fluoroscopy ; Fractures, Bone/diagnostic imaging* ; Young Adult

OBJECTIVE: To establish digital model of Ideberg typeⅡregional glenoid fracture anatomical plate with 3D metal printing technology. METHODS: The scapular imaging data of a 34-year-old healthy male volunteer were retrospectively selected. Mimics 15.01, NX 12.0 and other software were used to design Ideberg typeⅡ regional scapular fracture guide plate system. STL data were input into a metal 3D printer to print 1∶1 scapular model and anatomical plate of scapular pelvis with guide sleeve. The fit of the plate was tested in vitro and the accuracy of the screw position was evaluated by imaging. The printing time of scapular model, design of the nail path and making time of the anatomic guided plate were recorded. RESULTS: 3D metal-printed Ideberg typeⅡ guide plate for scapular fracture fitted well to 3D printed scapular model, the locking screw was oriented accurately, and X-ray and CT showed good screw position. The printing time of scapula model, time of nail path design and special-shaped anatomical guide plate production were 52.0, 15.0 and 320 min, respectively. CONCLUSION Anatomical plates based on 3D metal printing technology could achieve good adhesion of Ideberg typeⅡ regional fractures and precise screw placement, providing a new and accurate surgical method for the treatment of Ideberg typeⅡ glenoid fractures.
Humans ; Printing, Three-Dimensional ; Male ; Adult ; Bone Plates ; Fractures, Bone/diagnostic imaging* ; Fracture Fixation, Internal/methods* ; Pelvic Bones/surgery* ; Metals ; Scapula/surgery* ; Models, Anatomic

Humans ; Fractures, Bone/etiology* ; Bone and Bones/diagnostic imaging* ; Disability Evaluation

OBJECTIVE: To analyze radiological characteristics of Muller-Weiss disease, evaluate the clinical value of the imaging examination in diagnosis of Muller-Weiss disease. METHODS: The imaging data of 26 patients with Muller-Weiss disease were collected from September 2015 to August 2020, including 7 males and 19 females, aged 43 to 68 years old with an average of (52.7±4.6) years old. In the X-ray examination observed the shape and position of the navicular bone. The talar-first metatarsal angle(TFM) was measured on the weight-bearing anteroposterior radiograph. The arch angle and angle between mid-axis of talus and mid-axis of the first metatarsal(Meary angle) were measured on the weight-bearing lateral radiographs. The morphology, density, adjacent joint space and position of the navicular bone were evaluated by computed tomography(CT), and magnetic resonance imaging(MRI) was used to observe the shape, signal, cartilage and surrounding soft tissue changes of the navicular bone. RESULTS: Among 26 patients, 21 cases were unilateral and 5 cases were bilateral;X-ray examination showed that the lateral part of navicular bone of foot was compressed and flattened, showing"comma like"or"drop like", navicular moved to the medial side, partial fragmentation of bone, peripheral articular hyperplasia, uneven density and narrowing of relationship gap. According to Meary angle and deformity degree of the affected foot on the lateral X-ray of the load-bearing foot, Maceira staging was performed. There were 0 cases in stageⅠ, 2 cases in stage Ⅱ, 11 cases in stage Ⅲ, 9 cases in stage Ⅳand 4 cases in stage Ⅴ. CT examination showed bone fragmentation, medial displacement of navicular bone and formation of the talocalcaneal joint. MRI examination showed the irregular shape and uneven signal of navicular bone, narrowing of joint space, talocalcaneal joint surface hyperplasia and cartilage destruction, tarsal joint effusion and swelling of surrounding soft tissue. CONCLUSION Muller-Weiss disease has specific imaging manifestation, and an accurate diagnosis can be made based on the patient's age, gender, and clinincal history. Preoperative imaging examination can stage the disease, help clinicians to formulate better surgical plans, and postoperative imaging examination can better evaluate the surgical effect.
Adult ; Aged ; Bone Diseases/diagnostic imaging* ; Cartilage Diseases ; Female ; Foot Diseases/diagnostic imaging* ; Humans ; Hyperplasia/pathology* ; Male ; Middle Aged ; Talus/pathology* ; Tarsal Bones/surgery* ; Tarsal Joints

Bone and Bones/diagnostic imaging* ; Breast/diagnostic imaging* ; Breast Neoplasms/diagnostic imaging* ; Female ; Humans