BACKGROUND

Mobile clinics offer crucial healthcare services, including X-ray examinations, to underserved communities. Minimizing image repeats in this setting is vital due to radiation exposure, patient inconvenience, and cost implications.

This study investigated the prevalence and causes of image repeat in conventional radiography performed within mobile clinics in the Philippines.

A retrospective review analyzed data from five mobile clinics located in two highly urbanized cities in the Philippines from July to December 2023). Radiology staff assessed image quality, with suboptimal images requiring retakes. Reasons for rejection were categorized.

Out of 871 radiographs taken, 118 (13.55%) were repeated. Vertebrae and pelvic girdle images had the highest repeat rates (33.33%). Positioning errors were the most common cause (44.07%), followed by underexposure and overexposure.

This study identified a concerning repeat rate (13.55%) for mobile X-rays, primarily due to improper patient positioning, particularly for specific body parts. Targeted training programs and stricter protocols for mobile clinic staff are needed. Radiography education should also emphasize these skills, potentially through collaboration with mobile clinic operators to ensure graduates are prepared for the unique challenges of this environment.

BACKGROUND

Mobile clinics offer crucial healthcare services, including X-ray examinations, to underserved communities. Minimizing image repeats in this setting is vital due to radiation exposure, patient inconvenience, and cost implications.

This study investigated the prevalence and causes of image repeat in conventional radiography performed within mobile clinics in the Philippines.

A retrospective review analyzed data from five mobile clinics located in two highly urbanized cities in the Philippines from July to December 2023). Radiology staff assessed image quality, with suboptimal images requiring retakes. Reasons for rejection were categorized.

Out of 871 radiographs taken, 118 (13.55%) were repeated. Vertebrae and pelvic girdle images had the highest repeat rates (33.33%). Positioning errors were the most common cause (44.07%), followed by underexposure and overexposure.

This study identified a concerning repeat rate (13.55%) for mobile X-rays, primarily due to improper patient positioning, particularly for specific body parts. Targeted training programs and stricter protocols for mobile clinic staff are needed. Radiography education should also emphasize these skills, potentially through collaboration with mobile clinic operators to ensure graduates are prepared for the unique challenges of this environment.

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

INTRODUCTION: In this study, we aimed to compare the performance of a convolutional neural network (CNN)-based deep learning model that was trained on a dataset of normal and abnormal paediatric elbow radiographs with that of paediatric emergency department (ED) physicians on a binomial classification task. METHODS: A total of 1,314 paediatric elbow lateral radiographs (patient mean age 8.2 years) were retrospectively retrieved and classified based on annotation as normal or abnormal (with pathology). They were then randomly partitioned to a development set (993 images); first and second tuning (validation) sets (109 and 100 images, respectively); and a test set (112 images). An artificial intelligence (AI) model was trained on the development set using the EfficientNet B1 network architecture. Its performance on the test set was compared to that of five physicians (inter-rater agreement: fair). Performance of the AI model and the physician group was tested using McNemar test. RESULTS: The accuracy of the AI model on the test set was 80.4% (95% confidence interval [CI] 71.8%-87.3%), and the area under the receiver operating characteristic curve (AUROC) was 0.872 (95% CI 0.831-0.947). The performance of the AI model vs. the physician group on the test set was: sensitivity 79.0% (95% CI: 68.4%-89.5%) vs. 64.9% (95% CI: 52.5%-77.3%; P = 0.088); and specificity 81.8% (95% CI: 71.6%-92.0%) vs. 87.3% (95% CI: 78.5%-96.1%; P = 0.439). CONCLUSION The AI model showed good AUROC values and higher sensitivity, with the P-value at nominal significance when compared to the clinician group.
Humans ; Deep Learning ; Child ; Retrospective Studies ; Male ; Female ; Radiography/methods* ; ROC Curve ; Elbow/diagnostic imaging* ; Neural Networks, Computer ; Child, Preschool ; Elbow Joint/diagnostic imaging* ; Emergency Service, Hospital ; Adolescent ; Infant ; Artificial Intelligence

BACKGROUND: The correlation between the morphological structure of the patellofemoral joint (PFJ) and the severity of knee joint osteoarthritis (KOA) remains uncertain. This study aims to investigate the correlation between the severity of knee joint osteoarthritis and the alignment of patellofemoral and patellar height on radiographs. METHODS: This multi-center, retrospective study analyzed the magnetic resonance imaging (MRI) scans and anteroposterior radiographs of 534 adult outpatients with KOA. To evaluate the radiographic severity of KOA, anteroposterior radiographs of the knee and the Kellgren-Lawrence (K-L) grade were used. Knee MRI scans were used to measure the patellar length ratio (PLR), sulcus angle (SA), lateral patellar tilt angle (LPTA), and the distance between tibial tuberosity and trochlear groove (TT-TG). We examined the association between the configuration of the PFJ, arrangement, and harshness of the KOA. Information on participants' demographics, such as age, sex, side, height, and weight, was collected. A chi-squared test was used for the correlation of radiographic severity of KOA with sex and the affected side. Spearman correlation was used for patellofemoral alignment or morphology and the radiographic severity of lateral KOA. Multiple linear regression models were used for the association between LPTA, SA, TT-TG, and severity of KOA after accounting for demographic variables. RESULTS: The study comprised of 534 patients; of these, 339 (63%) were female. A total of 586 knees were evaluated in this study. Age showed a strong positive correlation with KOA severity ( r  = 0.516, P <0.01), whereas LPTA showed a strong negative correlation ( r  = -0.662, P <0.01). Additionally, SA ( r  = 0.616, P <0.05), and TT-TG showed a strong positive correlation ( r  = 0.770, P <0.01) with tibiofemoral osteoarthritis (TFOA) severity. Multiple linear regression analysis indicated that knee osteoarthritis severity (β = -2.946, P <0.001) and side (β = -0.839, P  = 0.001) was associated with LPTA; knee osteoarthritis severity (β = 5.032, P <0.001) and age (β = -0.095, P <0.001) was associated with SA; knee osteoarthritis severity (β = 2.445, P <0.001), sex (β = -0.326, P  = 0.041), body mass index (β = -0.061, P  = 0.017) and age (β = -0.025, P <0.001) was associated with TT-TG. CONCLUSION Radiographic severity of KOA was positively associated with age, SA, and TT-TG but negatively associated with LPTA.
Humans ; Female ; Male ; Osteoarthritis, Knee/pathology* ; Middle Aged ; Retrospective Studies ; Aged ; Patellofemoral Joint/pathology* ; Magnetic Resonance Imaging ; Adult ; Patella/pathology* ; Radiography

Objective: To investigate the application effectiveness of the artificial intelligence(AI) based Generative Pre-treatment tool of Skeletal Pathology (GPTSP) in measuring functional lumbar radiographic examinations. Methods: This is a retrospective case series study,reviewing the clinical and imaging data of 34 patients who underwent lumbar dynamic X-ray radiography at Department of Orthopedics, the Second Hospital of Shandong University from September 2021 to June 2023. Among the patients, 13 were male and 21 were female, with an age of (68.0±8.0) years (range:55 to 88 years). The AI model of the GPTSP system was built upon a multi-dimensional constrained loss function constructed based on the YOLOv8 model, incorporating Kullback-Leibler divergence to quantify the anatomical distribution deviation of lumbar intervertebral space detection boxes, along with the introduction of a global dynamic attention mechanism. It can identify lumbar vertebral body edge points and measure lumbar intervertebral space. Furthermore, spondylolisthesis index, lumbar index, and lumbar intervertebral angles were measured using three methods: manual measurement by doctors, predefined annotated measurement, and AI-assisted measurement. The consistency between the doctors and the AI model was analyzed through intra-class correlation coefficient (ICC) and Kappa coefficient. Results: AI-assisted physician measurement time was (1.5±0.1) seconds (range: 1.3 to 1.7 seconds), which was shorter than the manual measurement time ((2 064.4±108.2) seconds,range: 1 768.3 to 2 217.6 seconds) and the pre-defined annotation measurement time ((602.0±48.9) seconds,range: 503.9 to 694.4 seconds). Kappa values between physicians' diagnoses and AI model's diagnoses (based on GPTSP platform) for the lumbar slip index, lumbar index, and intervertebral angles measured by three methods were 0.95, 0.92, and 0.82 (all P<0.01), with ICC values consistently exceeding 0.90, indicating high consistency. Based on the doctor's manual measurement, compared with the predefined label measurement, altering AI assistance, doctors measurement with average annotation errors reduced from 2.52 mm (range: 0.01 to 6.78 mm) to 1.47 mm(range: 0 to 5.03 mm). Conclusions: The GPTSP system enhanced efficiency in functional lumbar analysis. AI model demonstrated high consistency in annotation and measurement results, showing strong potential to serve as a reliable clinical auxiliary tool.
Humans ; Female ; Retrospective Studies ; Male ; Lumbar Vertebrae/diagnostic imaging* ; Middle Aged ; Aged ; Aged, 80 and over ; Artificial Intelligence ; Radiography ; Spondylolisthesis/diagnostic imaging*

The orientation of the acetabular cup in hip joint anteroposterior radiograph is a key factor in evaluating the postoperative outcomes of total hip arthroplasty (THA). Currently, measurement of the acetabular cup anteversion angle primarily relies on manual drawing of auxiliary lines by orthopedic surgeons and calculations using scientific calculators. This study proposes an automated computer-aided measurement method for the acetabular cup anteversion angle based on hip joint anteroposterior radiograph. The proposed method segments hip prosthesis images using an improved Otsu algorithm, identifies feature points at the acetabular cup opening by combining circle-fitting theory and the cup's geometric characteristics, and fits an ellipse to the cup opening to calculate the anteversion angle. A total of 104 hip joint anteroposterior radiographs, including 71 right-sided and 81 left-sided prostheses, were analyzed. Two orthopedic surgeons independently measured the postoperative anteversion angles, and the results were compared with computer-generated measurements for correlation analysis. Spearman and Pearson correlation analyses demonstrated significant correlations between the proposed method and manual measurements for both the right group ( r = 0.795, P < 0.01) and the left group ( r = 0.859, P < 0.01). This method provides a reliable reference for orthopedic surgeons to assess postoperative prognosis.
Humans ; Acetabulum/anatomy & histology* ; Arthroplasty, Replacement, Hip/methods* ; Algorithms ; Hip Prosthesis ; Hip Joint/diagnostic imaging* ; Radiography ; Image Processing, Computer-Assisted/methods*

OBJECTIVE: To evaluate precise assessment methods for predicting the optimal acetabular cup size in total hip arthroplasty (THA). METHODS: A clinical data of 73 patients (80 hips) who underwent primary THA between December 2022 and July 2024 and met the inclusion criteria was analyzed. There were 39 males and 34 females with an average age of 66.3 years (range, 56-78 years). Among them, 66 cases were unilateral THA and 7 were bilateral THAs. There were 29 patients (34 hips) of osteoarthritis, 35 patients (35 hips) of femoral neck fractures, and 9 patients (11 hips) of osteonecrosis of the femoral head. Based on anteroposterior pelvic X-ray films, three methods were employed to predict acetabular cup size, including preoperative template planning, radiographic femoral head diameter (FHD) measurement, and intraoperative FHD measurement. The predicted acetabular cup sizes from these methods were compared with the actual implanted sizes. RESULTS: The predicted acetabular cup sizes using the preoperative template planning, radiographic FHD measurement, and intraoperative FHD measurement were (51.25±2.81), (49.72±3.11), and (49.90±2.74) mm, respectively, compared to the actual implanted cup size of (50.57±2.74) mm, with no significant difference ( P>0.05). Regarding agreement with the actual implanted cup size, the preoperative template planning achieved exact matches in 35 hips (43.75%), one-size deviation in 41 hips (51.25%), and two-size deviations in 4 hips (5%); the radiographic FHD measurement achieved exact matches in 12 hips (15%), one-size deviation in 57 hips (71.25%), and two-size deviations in 11 hips (13.75%); and the intraoperative FHD measurement achieved exact matches in 26 hips (32.5%), one-size deviation in 52 hips (65%), and two-size deviations in 2 hips (2.5%). There were significant differences in agreement distributions between the three methods and the actual implanted cup sizes ( H=18.579, P<0.001). CONCLUSION The intraoperative FHD measurement, as a simple, cost-effective, and accurate method, effectively guides acetabular cup selection, reduces the risk of prosthesis wear, enhances postoperative joint stability.
Humans ; Arthroplasty, Replacement, Hip/instrumentation* ; Male ; Female ; Middle Aged ; Acetabulum/diagnostic imaging* ; Aged ; Hip Prosthesis ; Prosthesis Design ; Femur Head/surgery* ; Osteoarthritis, Hip/surgery* ; Radiography ; Femoral Neck Fractures/surgery* ; Femur Head Necrosis/surgery*

OBJECTIVE: To explore the morphological characteristics of the postero-superior protuberance of the calcaneus and to explore its relationship with Haglund malformation. METHODS: Ankle lateral X-ray films of 391 hospitalized patients between May 2021 and June 2024 were retrospectively collected. The morphological parameters of the postero-superior protuberance of the calcaneus were measured, including the length of the base, the height of the base, and the tip angle of the postero-superior protuberance of the calcaneus, and the morphological types were classified according to the above parameters, including the peak type, the hill type, and the flat type. The related parameters of Haglund malformation were measured, including Fowler-Philipp angle (FPA), calcaneal pitch angle (CPA), parallel pitch line (PPL), Chauveaux-Liet angle (CLA), and X/Y ratio (total calcaneal length/length of greater tuberosity of calcaneus). The differences of the morphological parameters of the postero-superior protuberance of the calcaneus and the related indicators of Haglund deformity among the three types and between the males and the females were compared and analyzed, and the differences of the positive numbers of the related indicators of Haglund deformity among the three types were compared. RESULTS: According to the morphological parameters of the postero-superior protuberance of the calcaneus, there were 64 cases of peak type, 245 cases of hill type, and 82 cases of flat type. There was no significant difference in the length of the base of the postero-superior protuberance of the calcaneus, CPA, CLA, and X/Y ratio among the three types ( P>0.05). Among the three types, the peak type had the largest FPA and the flat type had the smallest ( P<0.05); the peak type had the smallest tip angle of the postero-superior protuberance of the calcaneus and the flat type had the largest ( P<0.05); the positive rate of PPL in the hill type was significantly higher than that in the peak type and flat type ( P<0.05); the height of the base of the postero-superior protuberance of the calcaneus in the flat type was the smallest ( P<0.05). FPA, CPA, CLA, PPL, and X/Y ratio were positive in 2, 42, 172, 142, and 77 patients, respectively. There was no significant difference in the number of positive Haglund deformity indicators among the three types ( P>0.05). There was no significant difference between male and female patients in the tip angle of the postero-superior protuberance of the calcaneus, FPA, the positive rate of PPL, and X/Y ratio ( P>0.05). The length and the height of the base of the postero-superior protuberance of the calcaneus, CPA, and CLA in male patients were significantly higher than those in female patients ( P<0.05). CONCLUSION The postero-superior protuberance of the calcaneus can be divided into three types: the peak type, the hill type, and the flat type. The peak type is more likely to suffer from Haglund deformity, and the males are more likely to suffer from Haglund deformity than the females.
Humans ; Calcaneus/anatomy & histology* ; Male ; Female ; Retrospective Studies ; Adult ; Middle Aged ; Adolescent ; Young Adult ; Radiography ; Child ; Aged

OBJECTIVE: To explore the effectiveness of triple osteotomy in correcting severe hallux valgus with the first metatarsal pronation deformity. METHODS: A retrospective analysis was conducted on the clinical data of 29 patients (40 feet) with severe hallux valgus accompanied by the first metatarsal pronation deformity, who were admitted between January 2022 and December 2023 and met the selection criteria. There were 8 males (10 feet) and 21 females (30 feet), with an average age of 50.0 years (range, 44-62 years). The disease duration ranged from 5 to 9 years (mean, 6.5 years). All patients underwent triple osteotomy to correct the deformity. The American Orthopaedic Foot and Ankle Society (AOFAS) score and visual analogue scale (VAS) score were used to evaluate joint function and pain before and after operation. Based on pre- and post-operative X-ray films, hallux valgus angle (HVA), intermetatarsal angle (IMA), and distal metatarsal articular angle (DMAA) were measured to evaluate the correction of hallux valgus; the shape classification of the lateral edge of the first metatarsal and the pronation of first metatarsal angle (PFMA) were observed to assess the correction of the first metatarsal pronation deformity. RESULTS: A superficial infection occurred in 1 foot and the incison healed after dressing change; the remaining incisions healed by first intention. All patients were followed up 12-18 months (mean, 12.6 months). Three cases (4 feet) experienced limited movement of the metatarsophalangeal joint after operation, and the joint function recovered after strengthening functional exercises. During follow-up, no recurrence of deformity or secondary metatarsal pain occurred. Compared with preoperative scores, the AOFAS score increased and the VAS score decreased at last follow-up, and the differences were significant ( P<0.05). Radiographic examination showed that the osteotomy achieved bony healing, with the healing time of 2.5-6.2 months (mean, 4.1 months). The hallux valgus deformity was corrected, and the IMA, HVA, and DMAA were significantly smaller at last follow-up when compared with those before operation ( P<0.05). The first metatarsal pronation deformity was also corrected; there was no R-type (R-type for pronation deformity) on the lateral edge of the first metatarsal at last follow-up, and the PFMA decreased compared with preoperative levels ( P<0.05) and was corrected to the normal range. CONCLUSION Triple osteotomy can achieve good effectiveness for correcting severe hallux valgus with the first metatarsal pronation deformity. The functional training of the first metatarsophalangeal joint needs to be strengthened.
Humans ; Hallux Valgus/diagnostic imaging* ; Osteotomy/methods* ; Female ; Male ; Middle Aged ; Adult ; Retrospective Studies ; Metatarsal Bones/diagnostic imaging* ; Treatment Outcome ; Pronation ; Radiography