Wrist Radiographs Research Articles

Cost-effectiveness and societal burden implications of opportunistic screening for low bone density using wrist radiographs in a UK general radiography setting

Cost-effectiveness and societal burden implications of opportunistic screening for low bone density using wrist radiographs in a UK general radiography setting

Retraction Note: Diagnostic power of ChatGPT 4 in distal radius fracture detection through wrist radiographs.

Retraction Note: Diagnostic power of ChatGPT 4 in distal radius fracture detection through wrist radiographs.

The Validation of the Greulich and Pyle Atlas for Radiological Bone Age Assessments in a Pediatric Population from the Canary Islands.

Bone age assessments measure the growth and development of children and adolescents by evaluating their skeletal maturity, which is influenced by various factors like heredity, ethnicity, culture, and nutrition. The clinical standards for this assessment should be up to date and appropriate for the specific population being studied. This study validates the GP-Canary Atlas for accurately predicting bone age by analyzing posteroanterior left hand and wrist radiographs of healthy children (80 females and 134 males) from the Canary Islands across various developmental stages and genders. We found strong intra-rater reliability among all three raters, with Raters 1 and 2 indicating very high consistency (intra-class coefficients = 0.990 to 0.996) and Rater 3 displaying slightly lower but still strong reliability (intra-class coefficients = 0.921 to 0.976). The inter-rater agreement was excellent between Raters 1 and 2 but significantly lower between Rater 3 and the other two raters, with intra-class coefficients of 0.408 and 0.463 for Rater 1 and 0.327 and 0.509 for Rater 2. The accuracy analysis revealed a substantial underestimation of bone age compared to chronological age for preschool- (mean difference = 17.036 months; p < 0.001) and school-age males (mean difference = 13.298 months; p < 0.001). However, this was not observed in females, where the mean difference was minimal (3.949 months; p < 0.239). In contrast, the Atlas showed greater accuracy for teenagers, showing only a slight overestimation (mean difference = 3.159 months; p = 0.823). In conclusion, the GP-Canary Atlas demonstrates overall precision but requires caution as it underestimates the BA in preschool children and overestimates it in school-age girls and adolescents.

Improved Automated Quality Control of Skeletal Wrist Radiographs Using Deep Multitask Learning.

Radiographic quality control is an integral component of the radiology workflow. In this study, we developed a convolutional neural network model tailored for automated quality control, specifically designed to detect and classify key attributes of wrist radiographs including projection, laterality (based on the right/left marker), and the presence of hardware and/or casts. The model's primary objective was to ensure the congruence of results with image requisition metadata to pass the quality assessment. Using a dataset of 6283 wrist radiographs from 2591 patients, our multitask-capable deep learning model based on DenseNet 121 architecture achieved high accuracy in classifying projections (F1 Score of 97.23%), detecting casts (F1 Score of 97.70%), and identifying surgical hardware (F1 Score of 92.27%). The model's performance in laterality marker detection was lower (F1 Score of 82.52%), particularly for partially visible or cut-off markers. This paper presents a comprehensive evaluation of our model's performance, highlighting its strengths, limitations, and the challenges encountered during its development and implementation. Furthermore, we outline planned future research directions aimed at refining and expanding the model's capabilities for improved clinical utility and patient care in radiographic quality control.

Decoding Radiology Reports: Artificial Intelligence-Large Language Models Can Improve the Readability of Hand and Wrist Orthopedic Radiology Reports.

The purpose of this study was to assess the effectiveness of an Artificial Intelligence-Large Language Model (AI-LLM) at improving the readability of hand and wrist radiology reports. The radiology reports of 100 hand and/or wrist radiographs, 100 hand and/or wrist computed tomography (CT) scans, and 100 hand and/or wrist magnetic resonance imaging (MRI) scans were extracted. The following prompt command was inserted into the AI-LLM: "Explain this radiology report to a patient in layman's terms in the second person: [Report Text]." The report length, Flesch reading ease score (FRES), and Flesch-Kincaid reading level (FKRL) were calculated for the original radiology report and the AI-LLM-generated report. The accuracy of the AI-LLM report was assessed via a 5-point Likert scale. Any "hallucination" produced by the AI-LLM-generated report was recorded. There was a statistically significant improvement in mean FRES scores and FKRL scores in the AI-LLM-generated radiograph report, CT report, and MRI report. For all AI-LLM-generated reports, the mean reading level improved to below an eighth-grade reading level. The mean Likert score for the AI-LLM-generated radiograph report, CT report, and MRI report was 4.1 ± 0.6, 3.9 ± 0.6, and 3.9 ± 0.7, respectively. The hallucination rate in the AI-LLM-generated radiograph report, CT report, and MRI report was 3%, 6%, and 6%, respectively. This study demonstrates that AI-LLM effectively improves the readability of hand and wrist radiology reports, underscoring the potential application of AI-LLM as a promising and innovative patient-centric strategy to improve patient comprehension of their imaging reports.Level of Evidence: IV.

Reliability of Wrist Arthroscopy in the Diagnosis and Treatment of Triangular Fibrocartilage Complex Tears

Wrist arthroscopy is considered the gold standard for diagnosis of intra-articular wrist conditions including triangular fibrocartilage complex (TFCC) tears; however, the ability to reliably diagnose TFCC pathology during wrist arthroscopy is unclear. The purpose of this study was to assess the reliability of the diagnosis of TFCC tears on wrist arthroscopy videos. Five hand surgeons reviewed 43 cases on a secure web-based platform at two time points separated by 4-6 weeks. Each case included a deidentified clinical vignette and wrist radiographs with ulnar variance measurements and an arthroscopy video of ulnar wrist pathology, averaging 42 seconds. Surgeons were queried on the presence of TFCC tear and Palmer and Atzei classifications. Interobserver/intraobserver reliabilities were determined using kappa coefficients. The interobserver reliability regarding the presence/absence of TFCC tear was fair-good, with kappa coefficients of 0.596 in the first round of case review and 0.708 in the second round. The overall intraobserver reliability for the presence/absence of TFCC tear was also fair-good, with a kappa coefficient of 0.567. For cases with central TFCC tears, the interobserver reliability regarding the presence of TFCC tear was perfect, with a kappa coefficient of 1.0. When central tears were excluded, the kappa coefficients decreased to 0.322 and 0.368 in each round. The interobserver reliability for the Palmer and Atzei classifications was low, with kappa coefficients of 0.220 and 0.121 in the first round and 0.222 and 0.123 in the second round. Experienced wrist arthroscopy surgeons demonstrated fair-good interobserver reliability for the diagnosis of TFCC tear on wrist arthroscopy. However, when central TFCC tears were excluded, interobserver reliability was poor. These findings demonstrate a need for a focus on education for wrist arthroscopy anatomy. This investigation demonstrated poor agreement in surgeon identification and classification of TFCC tears, aside from central TFCC tears. The low reliability has a direct bearing on treatment considerations for TFCC tears.

The impact of HIV infection on skeletal maturity in peripubertal children in Zimbabwe: a cross-sectional study

IntroductionHIV infection and its treatment compromises skeletal development (growth and maturation). Skeletal maturity is assessed as bone age (BA) on hand and wrist radiographs. BA younger than chronological age (CA) indicates delayed development. We conducted a cross-sectional study to determine differences between BA and CA (i.e., skeletal maturity deviation [SMD]), and risk factors associated with SMD in peripubertal children with and without HIV established on antiretroviral therapy (ART) including use of tenofovir disoproxil fumarate (TDF).MethodsChildren with HIV taking ART for at least two years and a comparison group of HIV-negative children, aged 8–16 years and frequency-matched by age and sex, were recruited from HIV clinics and local schools in the same catchment area, in Harare, Zimbabwe. BA was assessed from non-dominant hand-wrist radiographs using the Tanner Whitehouse 3 method. Negative SMD values correspond to delayed development, i.e., BA younger than CA. Multivariable linear regression models determined factors associated with SMD overall, and in children with HIV.ResultsIn total, 534 participants (54% males) were included; by design CA was similar in males and females, whether living with or without HIV. Mean (SD) SMD was more negative in CWH than in HIV-negative children in both males [-1.4(1.4) vs. -0.4(1.1) years] and females [-1.1(1.3) vs. -0.0(1.2) years]. HIV infection and weight-for-age Z-score<-2 were associated with more negative SMD in both males and females after adjusting for socio-economic status, orphanhood, pubertal stage, and calcium intake. Age at ART initiation was associated with SMD in both males and females with those starting ART later more delayed: starting ART aged 4–8 years 1.14 (-1.84, -0.43), or over 8 years 1.47 (-2.30, -0.65) (p-value for trend < 0.001). Similar non-significant trends were seen in males. TDF exposure TDF exposure whether < 4years or ≥ 4 years was not associated with delayed development.ConclusionPerinatally-acquired HIV infection and being underweight were independently associated with delayed skeletal maturation in both males and females. Starting ART later was independently associated with skeletal maturation delay in CWH. Given the known effects of delayed development on later health, it is important to find interventions to ensure healthy weight gain through early years and in CWH to initiate ART as early as possible.

Inter-Rater and Intrarater Reliability of Radiographs in the Diagnosis of Pediatric Scaphoid Fractures.

Pediatric scaphoid fractures can be challenging to diagnose on plain radiograph. Rates of missed scaphoid fractures can be as high as 30% to 37% on initial imaging and overall sensitivity ranging from 21% to 97%. Few studies, however, have examined the reliability of radiographs in the diagnosis of scaphoid fractures, and none are specific to the pediatric population. Reliability, both between different specialists and for individual raters, may elucidate some of the diagnostic challenges. We conducted a 2-iteration survey of pediatric orthopedic surgeons, plastic surgeons, radiologists, and emergency physicians at a tertiary children's hospital. Participants were asked to assess 10 series of pediatric wrist radiographs for evidence of scaphoid fracture. Inter-rater and intrarater reliability was calculated using the intraclass correlation coefficient of 2.1. Forty-two respondents were included in the first iteration analysis. Inter-rater reliability between surgeons (0.66; 95% confidence interval, 0.43-0.87), radiologists (0.76; 0.55-0.92), and emergency physicians (0.65; 0.46-0.86) was "good" to "excellent." Twenty-six respondents participated in the second iteration for intrarater reliability (0.73; 0.67-0.78). Sensitivity (0.75; 0.69-0.81) and specificity (0.78; 0.71-0.83) of wrist radiographs for diagnosing scaphoid fractures were consistent with results in other studies. Both inter-rater and intrarater reliability for diagnosing pediatric scaphoid fractures on radiographs was good to excellent. No significant difference was found between specialists. Plain radiographs, while useful for obvious scaphoid fractures, are unable to reliably rule out subtle fractures routinely. Our study demonstrates that poor sensitivity stems from the test itself, and not rater variability.

A comparison between IBEX bone health applied to digital radiographs and dual-energy X-ray absorptiometry at the distal-third and ultra-distal regions of the radius

BackgroundIn an ageing population, low impact fragility fractures are becoming increasingly common. However, fracture risk can be reduced where low bone density can be identified at an early stage. In this study we aim to demonstrate that IBEX Bone Health (IBEX BH) can provide a clinically useful prediction from wrist radiographs of aBMD and T-score at the ultra-distal (UD) and distal-third (DT) regions of the radius.MethodsA 261-participant single-centre, non-randomised, prospective, study was carried out to compare a) IBEX BH, a quantitative digital radiography software device, to b) Dual-energy X-ray Absorptiometry (DXA). A total of 257 participants with wrist digital radiograph (DR), forearm DXA pairs were included in the analysis after exclusions.ResultsThe adjusted R2 value for IBEX BH outputs to the radial areal bone mineral density (aBMD) produced by a GE Lunar DXA system for the UD region is 0.87 (99% Confidence Interval (CI) [0.84, 0.89]). The adjusted R2 value for IBEX BH outputs to aBMD for the DT region is 0.88 (99% CI [0.85, 0.90]). The Area Under the Receiver Operating Characteristic curve (AUC) for the forearm T-score ≤ − 2.5 risk prediction model at the UD region is 0.95 (99% CI [0.93, 0.98]). The AUC for the forearm T-score ≤ − 2.5 risk prediction model at the DT region is 0.98 (99% CI [0.97, 0.99]).ConclusionFrom a DR of the wrist, IBEX BH provides a clinically useful i) estimate of aBMD at the two regions of interest on the radius and ii) risk prediction model of forearm T-score ≤ − 2.5 at the UD and DT regions.

The Relationship between Structure of the Wrist and Function in a Japanese and Caucasian Population.

Background: Factors such as age and joint structure affect normal wrist motion. The midcarpal joint participates in flexion/extension, radial-ulnar/deviation (RUD), and since lunate/wrist type-2 is likely more stable than a lunate/wrist type-1, we suggest that midcarpal joint structure will affect wrist motion. Our purpose was to compare wrist motion in Caucasian and Japanese populations and to associate motion with midcarpal joint morphology. We hypothesised that radiographic structure would correlate with wrist motion. Methods: A total of 164 patients with normal wrist radiographs were included. Clinical measurements included wrist extension, flexion and RUD. Radiographic measurements included the radiocarpal joint: ulnar variance, radial height, radial inclination, volar inclination and carpal joint measurements: lunate type, capitate circumference and each of its joints contact measured and calculated as a proportion of capitate circumference. Results: The groups differed in wrist motion and in multiple radiographic measurements. When the two populations were analysed together, there were no significant associations between midcarpal joint type and wrist motion. The radiocarpal joint: ulnar variance was correlated with extension and radial deviation. Radial height was directly related to flexion, and both radial height and radial inclination were directly correlated with ulnar deviation. The intracarpal measurements: The main measurement affecting motion was the contact between the capitate and the scaphoid (as a proportion of capitate circumference) with lesser correlations of the contact of the capitate with the trapezoid and hamate. The most significant measurement associated with a lunate type-2 was scaphoid contact with the capitate p = 0.01. Logistic regression demonstrated that the measurements most associated with wrist motion were scaphoid contact with the capitate/capitate circumference and hamate contact with the capitate/capitate. Conclusions: This study supports discrepancies in wrist motion amongst different racial cohorts, and a relationship between bone/joint structure in the wrist and wrist motion. This can help treat wrist pathology. Level of Evidence: Level III (Diagnostic).

Progression of arthritis after four-corner fusion in patients with calcium pyrophosphate deposition disease: a case series of eleven patients

Aim: The purpose of this study is to evaluate outcomes and radiographic progression of wrist arthritis after four-corner fusion (4CF) in patients with evidence of calcium pyrophosphate deposition disease (CPPD). The insights derived from this study are expected to improve the understanding of 4CF outcomes in the presence of CPPD, guiding clinical decisions, and management strategies. Methods: 11 patients with prior 4CF and evidence of CPPD were available for prospective follow-up and imaging, with a mean follow-up time of 5 years. Range of motion measurements, radiographs, and outcome data were collected at the follow-up visit and prior data and imaging were reviewed retrospectively. The chronological progression of arthritis was evaluated on standard three-view wrist radiographs using the Larsen scale. Results: All participants (11/11) deemed their wrist fusion a success, with an average satisfaction score of 8.8 out of 10.73% (8/11) patients were able to return to their original occupation after the procedure. The mean flexion of the affected wrist preoperatively was 43 degrees (SD: ±12 degrees) and 41 degrees (SD: ±7 degrees) at the final follow-up. The mean extension of the affected wrist was 35 degrees (SD: ±8 degrees) preoperatively and 40 degrees (SD: ±12 degrees) at the final follow-up. Radiographic analysis showed that 82% (9/11) of patients displayed progression of arthritis as per the Larsen scale by the final follow-up. All patients that showed radiographic progression had involvement of the radiolunate (RL) articulation, which is classically persevered in non-inflammatory wrist arthritis. Conclusions: Scaphoid excision with 4CF is a promising surgical option for managing CPPD-related wrist arthritis, offering significant functional improvements, motion preservation, and high patient satisfaction. However, it does not halt radiographic progression of arthritis for the majority of patients at a mean prospective long-term follow-up of 5 years.

Association between carpal height ratio and ulnar variance in normal wrist radiography

IntroductionThe wrist joint is a complex anatomical structure, and various radiographic parameters are utilized to assess its normal alignment and orientation. Among these parameters are carpal height ratio (CHR) and ulnar variance (UV). Previous literature has indicated that factors such as age and gender may influence these parameters; However, there is a lack of studies investigating these differences specifically in the Middle East or Jordan. Additionally, no prior research has explored the relationship between UV and CHR. Therefore, the objective of this study is to investigate these critical radiological parameters and their associations.MethodologyA cross-sectional study design was employed, wherein a total of 385 normal wrist X-rays were reviewed, and CHR and UV were measured. Intra-observer and inter-observer reliability assessments were conducted to ensure the consistency and accuracy of measurements. Additionally, the association between UV and CHR was measured and plotted for further analysis.ResultsIn our study, the mean CHR was 0.5 (range: 0.4 to 1.5), and the mean UV was − 0.3 mm (range: -5.8 mm to 4.1 mm). We found a significant negative correlation between CHR and age (p < 0.05). No significant gender differences were observed in UV and CHR. Additionally, a weak positive correlation was found between UV and CHR (Pearson correlation coefficient = 0.13, p = 0.01; adjusted R2 = 0.014, p = 0.02).ConclusionAge correlated significantly with a decline in carpal height ratio. Additionally, ulnar variance had a week positive yet significant correlation with carpal height ratio.Level of evidenceCross-sectional study, Level III.

Cross-sectional and longitudinal analysis of bone age maturation during peri-pubertal growth in children with type I, III and IV osteogenesis imperfecta

Osteogenesis imperfecta (OI)is a rare genetically heterogeneous disorder caused by changes in the expression or processing of type I collagen. Clinical manifestations include bone fragility, decreased linear growth, and skeletal deformities that vary in severity. In typically growing children, skeletal maturation proceeds in a predictable pattern of changes in the size, shape, and mineralization on the hand and wrist bones that can be followed radiographically known at the bone age. Assessment of bone age can be clinically used to assess time remaining for linear growth, and the onset and duration of puberty, both of which can be useful in determining the timing of some surgeries or the interpretation of other imaging modalities such as bone densitometry. Additionally, deviations in the expected maturation process of the bone age may prompt or assist in the work up of a significant delay or advancement in a child's growth pattern. The primary aim of our study was to determine whether the bone age in children with a skeletal disorder such as OI follow the same pattern and rate of bone maturation compared to a control population. Using participants from the Natural History Study of the Brittle Bone Disorders Consortium, we analyzed 159 left hand and wrist radiographs (bone age) for a cross-sectional analysis and 55 bone ages repeated at approximately 24 months for a longitudinal analysis of skeletal maturation. Bone ages were read by a pediatric endocrinologist and by an automated analysis using a program called BoneXpert. Our results demonstrated that in children with mild-to-moderate OI (types I and IV), the skeletal maturation is comparable to chronological age-mated controls. For those with more severe forms of OI (type III), there is a delayed pattern of skeletal maturation of less than a year (10.5 months CI 5.1–16) P = 0.0012) at baseline and a delayed rate of maturation over the two-year follow up compared to type I (P = 0.06) and type III (P = 0.02). However, despite these parameters being statistically different, they may not be clinically significant. We conclude the bone age, with careful interpretation, can be used in the OI population in a way that is similar to the general pediatric population.

Evaluating inter- and intraobserver reliability in radiographic determination of wrist alignment following scaphoid excision and four-corner arthrodesis

BackgroundFour-corner arthrodesis is commonly performed for advanced collapse patterns of wrist arthritis. Reduction of the capitolunate (CL) angle during four-corner fusion is crucial to allow for the greatest radiocarpal joint arc of motion. Previous studies demonstrate variable inter- and intraobserver reliability of measuring the CL angle. However, in a four-corner fusion, hardware implementation and scaphoid excision can complicate carpal alignment measurements. The purpose of this study is to investigate inter- and intraobserver reliability of measuring carpal alignment parameters following scaphoid excision and four-corner arthrodesis. MethodsThree fellowship-trained orthopaedic hand surgeons evaluated 30 posteroanterior and lateral radiographs of wrists after scaphoid excision and four-corner fusion. Radiographic evaluation included analysis of the radiolunate angle (RL), CL angle, lunate posture, carpal height, carpal height ratio, hardware impingement, and arthrodesis technique. Intraclass correlation coefficients (ICCs) and kappa values were used to evaluate reliability of radiographic measurements. ResultsRL and CL angles demonstrated very good inter- (ICCs: 0.657 and 0.693, respectively) and intraobserver agreement (ICCs: 0.576 to 0.924 and 0.596 to 0.811, respectively). Hardware impingement metrics by dorsal prominence and radiocarpal prominence had excellent interobserver reliability of 0.821 and 0.803, respectively. ICC values for arthrodesis technique were equal to 1.00. The inter- and intraobserver ICC values for the number of screws/staples used were in excellent agreement ranging from 0.910 to 1.000. ConclusionsOur study demonstrated favorable intra- and interobserver reliability at assessing carpal alignment following scaphoid excision and four-corner arthrodesis and these metrics potentially could be used in future research to evaluate long-term surgical outcomes. Level of evidenceLevel III, retrospective cohort study.

Normative Data of Carpal Bone Measurements in the Sample Adult Indian Population.

Introduction Radiography is the most often accessible and affordable imaging modality. Accurate assessments of wrist X-rays can aid in the diagnosis and prognostic evaluation of various wrist problems. This study aims to identify normal radiographic anthropometry reference values and variations of carpal bones and joints by gender and age in sample Indian population, with the potential to be clinically applicable. Materials and Methods Two investigators conducted a prospective analysis of normal wrist radiographs in a single center. Radiology Information Systems and Picture Archiving and Communication Systems were used to collect standard digitized normal X-rays without significant osseous pathology over a year. We conducted measurements of length, angles, and indices in a standard posteroanterior and lateral wrist X-rays in order to establish the standard dimensions and variances based on age and gender. Results A total of 18 measurements which included eight linear measurements, eight angles, and two ratios were documented. A total of 500 X-rays of 250 males and 250 females with 125 of each in two age groups of 20 and 40 years and 41 and 60 years were evaluated. Conclusion This work is a comprehensive database of the Indian population measuring parameters in normal wrist radiographs of posteroanterior and lateral views. The results of our study indicate that men and younger individuals had a significantly higher carpal height ratio. The width of distal radial ulnar joint space was significantly lesser in older subjects. Additionally, males showed a significantly higher lunate uncovered ratio and radial height. When compared to the literature, the study revealed a significant positive ulnar variance in elderly people and women. However, we noted an overall increase in the percentage of positive ulnar variance individuals in our study. We also recorded a marginal increase in radial inclination with no variations across gender and age.

Radiologic Evaluation of the Distal End Radius Indices in Indian Paediatric Population.

The distal end radius's bony anatomy in relation to three variables-Radial Inclination, Volar tilt, and radial height-has been discussed commonly in the adult population and is not very well defined in the growing skeleton. In children aged 8-16years old, we measured the osseous distal end radius according to radiography standards. The research comprised 130 patients, 65 males and 65 females aged 8-16. In each child, the norms for radial inclination, volar tilt, and radial epiphyseal height were established. This research defines these radiographic parameters for the paediatric population in India for the first time. This research is an Unicentric Cross-sectional observational analytical study. We studied 130 normal wrist posteroanterior and lateral radiographs of the Indian paediatric population aged 8-16years who reported to our OPD and calculated the three parameters-(1) Radial height, (2) Volar Tilt, and (3) Radial Inclination. Mean measurement values were analysed statistically. The Mean distal end radius volar tilt is 10.92° ± 1.76° SD with a range from 4° to 15°. The Mean distal end radial inclination is 21.04° ± 2.10° SD with a range from 15° to 25°. The Mean distal end radial height is 11.93 ± 1.44mm SD with a range from 9.0 to 14.50mm. In true Postero-anterior and lateral wrist radiographs of the Indian paediatric population, we have established normal values that may be utilized as a guide for the evaluation and treatment of a variety of traumatic and non-traumatic problems in Indian children.

Deep Learning Model for Automatic Identification and Classification of Distal Radius Fracture.

Distal radius fracture (DRF) is one of the most common types of wrist fractures. We aimed to construct a model for the automatic segmentation of wrist radiographs using a deep learning approach and further perform automatic identification and classification of DRF. A total of 2240 participants with anteroposterior wrist radiographs from one hospital between January 2015 and October 2021 were included. The outcomes were automatic segmentation of wrist radiographs, identification of DRF, and classification of DRF (type A, type B, type C). The Unet model and Fast-RCNN model were used for automatic segmentation. The DenseNet121 model and ResNet50 model were applied to DRF identification of DRF. The DenseNet121 model, ResNet50 model, VGG-19 model, and InceptionV3 model were used for DRF classification. The area under the curve (AUC) with 95% confidence interval (CI), accuracy, precision, and F1-score was utilized to assess the effectiveness of the identification and classification models. Of these 2240 participants, 1440 (64.3%) had DRF, of which 701 (48.7%) were type A, 278 (19.3%) were type B, and 461 (32.0%) were type C. Both the Unet model and the Fast-RCNN model showed good segmentation of wrist radiographs. For DRF identification, the AUCs of the DenseNet121 model and the ResNet50 model in the testing set were 0.941 (95%CI: 0.926-0.965) and 0.936 (95%CI: 0.913-0.955), respectively. The AUCs of the DenseNet121 model (testing set) for classification type A, type B, and type C were 0.96, 0.96, and 0.96, respectively. The DenseNet121 model may provide clinicians with a tool for interpreting wrist radiographs.

A deep learning-based algorithm for automatic detection of perilunate dislocation in frontal wrist radiographs

This study proposes a Deep Learning algorithm to automatically detect perilunate dislocation in anteroposterior wrist radiographs. A total of 374 annotated radiographs, 345 normal and 29 pathological, of skeletally mature adolescents and adults aged ≥16 years were used to train, validate and test two YOLOv8 deep neural models. The training set included 245 normal and 15 pathological radiographs; the pathological training set was supplemented by 240 radiographs obtained by data augmentation. The test set comprised 30 normal and 10 pathological radiographs. The first model was used for detecting the carpal region, and the second for segmenting a region between Gilula’s 2nd and 3rd arcs. The output of the segmentation model, trained multiple times with varying random initial parameter values and augmentations, was then assigned a probability of being normal or pathological through ensemble averaging. In the study dataset, the algorithm achieved an overall F1-score of 0.880: 0.928 in the normal subgroup, with 1.0 precision, and 0.833 in the pathological subgroup, with 1.0 recall (or sensitivity), demonstrating that diagnosis of perilunate dislocation can be improved by automatic analysis of anteroposterior radiographs. Level of evidence: III.

A modified position for optimized skeletal maturity assessment of AIS patients and its impact on 3D spinal and pelvic parameters.

A hands-on-wall (HOW) position for low-dose stereoradiography of adolescent idiopathic scoliosis (AIS) patients would allow for skeletal maturity assessment of the hand and wrist. Our aims were twofold: confirm the reliability and validity of skeletal maturity assessment using the HOW radiographs and compare the spinal and pelvic 3D parameters to those of standard hands-on-cheeks (HOC) stereoradiographs. Seventy AIS patients underwent two successive stereoradiographs and a standard hand and wrist radiograph on the same day. Patients were randomly assigned to begin with HOW and follow with HOC, or vice versa. Raters assessed digital skeletal age (DSA), Sanders Simplified Skeletal Maturity (SSMS) and Thumb Ossification Composite Index (TOCI). 3D reconstructions of the spine and pelvis bones were performed for each stereoradiograph to measure nine clinically relevant spinal and pelvic 3D parameters. Inter-rater and intra-rater reliabilities were excellent for DSA, SSMS and TOCI with both standard radiographs and HOW (ICC > 0.95). Strong correlation was found between ratings of both imaging types (ICC > 0.95). In the 3D reconstructions, kyphosis and sacral slope were slightly decreased in the HOW position, but within the clinical margin of error. All other parameters did not differ significantly between positions (p < 0.05). The results suggest that HOW stereoradiographs allow clinicians to assess skeletal maturity of the hand and wrist with adequate reliability and validity. We recommend that scoliosis clinics adopt the HOW position to assess skeletal maturity because there is no significant clinical impact on the spinal and pelvic evaluation, and on radiation exposure, cost or time.

Distinct patterns of fracture propagation in distal radial fractures and the relationship to the ulnar head

BackgroundThe aim was to assess the direction of distal radius fractures and their relationship to the ulnar head. MethodsWe reviewed the 160 wrist radiographs. The fracture line was measured on the postero-anterior and lateral radiographs relative to the long axis of the forearm and the relationship to the ulnar head. FindingsPA radiographs: the fracture line ran distal ulnar to proximal radial (ulnar to radial) in 11%, transverse in 74% and distal radial to proximal ulnar (radial to ulnar) in 16%. Lateral radiographs: the fracture line ran distal volar to proximal dorsal in 88%, transverse in two 1% and dorsal to volar in 11%. Radial shift (7.5%) only occurred with ulnar to radial or transverse fractures.The ulnar to radial fracture line started at the proximal end of the ulnar head/distal radio-ulnar joint in 88%. The radial to ulnar fracture line started ended a mean of 2.5 mm proximal to the distal radio-ulnar joint (p < 0.01). The transverse fracture line started at the base of the distal radio-ulnar joint in 53% and proximally in 47%. InterpretationThere are two distinct coronal patterns: radial to ulnar ending c. 2 mm proximal to the distal radio-ulnar joint; ulnar to radial starting at the proximal distal radio-ulnar joint. There may be third pattern - transverse fractures; these may be variants of the above. Sagittally the main direction is volar to dorsal but 11% are obverse.This is the first description of distinct fracture patterns in extra-articular distal radius fractures. In addition the fracture patterns appear to correlate with different directions of force transmission which fit with our understanding of falling and the relatively uncontrolled impact of the wrist/hand with the ground.These patterns of fracture propagation help understand how the biomechanics of wrist fractures and may enable prediction of collapse.