Deep learning-based automated bone age estimation for Saudi patients on hand radiograph images: a retrospective study.

PURPOSE: In pediatric medicine, precise estimation of bone age is essential for skeletal maturity evaluation, growth disorder diagnosis, and therapeutic intervention planning. Conventional techniques for determining bone age depend on radiologists' subjective judgments, which may lead to non-negligible differences in the estimated bone age. This study proposes a deep learning-based model utilizing a fully connected convolutional neural network(CNN) to predict bone age from left-hand radiographs. METHODS: The data set used in this study, consisting of 473 patients, was retrospectively retrieved from the PACS (Picture Achieving and Communication System) of a single institution. We developed a fully connected CNN consisting of four convolutional blocks, three fully connected layers, and a single neuron as output. The model was trained and validated on 80% of the data using the mean-squared error as a cost function to minimize the difference between the predicted and reference bone age values through the Adam optimization algorithm. Data augmentation was applied to the training and validation sets yielded in doubling the data samples. The performance of the trained model was evaluated on a test data set (20%) using various metrics including, the mean absolute error (MAE), median absolute error (MedAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE). The code of the developed model for predicting the bone age in this study is available publicly on GitHub at https://github.com/afiosman/deep-learning-based-bone-age-estimation . RESULTS: Experimental results demonstrate the sound capabilities of our model in predicting the bone age on the left-hand radiographs as in the majority of the cases, the predicted bone ages and reference bone ages are nearly close to each other with a calculated MAE of 2.3 [1.9, 2.7; 0.95 confidence level] years, MedAE of 2.1 years, RMAE of 3.0 [1.5, 4.5; 0.95 confidence level] years, and MAPE of 0.29 (29%) on the test data set. CONCLUSION: These findings highlight the usability of estimating the bone age from left-hand radiographs, helping radiologists to verify their own results considering the margin of error on the model. The performance of our proposed model could be improved with additional refining and validation.

The optimal measurement method considering reliability and validity in the anterior knee laxity of anterior cruciate ligament tears.

INTRODUCTION: To seek an optimal measurement method with high reliability and high validity for evaluation of the anterior knee laxity on stress radiographs and comparing the translation values to those of KT-2000 arthrometer. METHODS: Anterior knee laxity in 77 patients was measured preoperatively using the TelosTM and the KT-2000 arthrometer. Side-to-side difference measurements were taken using three conventional measuring methods and one proposed method (Modified Lateral). The knee position on the stress radiograph was evaluated and scored based on the stress radiograph qualifying criteria depending on stress film correctiveness. Intraclass correlation coefficients were analyzed to evaluate the reliability of the measurement methods and were compared between high (Group H) and low (Group L) radiograph quality score groups for each method. Validity was assessed by comparing the KT-2000 and the TelosTM using Pearson correlation (r value). RESULTS: The Modified Lateral method showed the best Intraclass Correlation Coefficients (ICCs), followed by Center to Center, and Medial to Medial and Lateral to Lateral methods without considering the quality of Telos. In the comparison between groups based on Telos quality for intra-rater reliability, the Medial to Medial (MM) method demonstrated the best reliability in both groups (MM: ICCs, Group H = 0.942, Group L = 0.917, P = 0.693). As for inter-rater reliability, the Modified Lateral (ML) method exhibited the best reliability in both groups (ML: ICCs, Group H = 0.923, Group L = 0.882, P = 0.547). The value measured using the ML method in Telos showed the highest correlation coefficient with the KT-2000 measured value in both groups H and L. There were no statistically significant differences among the correlation coefficient values. CONCLUSION: The Modified Lateral method is recommended for its high reliability, taking into account the differences in bilateral knee positions and anatomical discriminability on stress radiographs when evaluating anterior knee translation with Telos. It also best reflected the KT-2000 arthrometer. LEVEL OF EVIDENCE: Case Series, Level IV.

Deep learning-based automated angle measurement for flatfoot diagnosis in weight-bearing lateral radiographs.

This study aimed to develop and evaluate a deep learning-based system for the automatic measurement of angles (specifically, Meary's angle and calcaneal pitch) in weight-bearing lateral radiographs of the foot for flatfoot diagnosis. We utilized 3960 lateral radiographs, either from the left or right foot, sourced from a pool of 4000 patients to construct and evaluate a deep learning-based model. These radiographs were captured between June and November 2021, and patients who had undergone total ankle replacement surgery or ankle arthrodesis surgery were excluded. Various methods, including correlation analysis, Bland-Altman plots, and paired T-tests, were employed to assess the concordance between the angles automatically measured using the system and those assessed by clinical experts. The evaluation dataset comprised 150 weight-bearing radiographs from 150 patients. In all test cases, the angles automatically computed using the deep learning-based system were in good agreement with the reference standards (Meary's angle: Pearson correlation coefficient (PCC) = 0.964, intraclass correlation coefficient (ICC) = 0.963, concordance correlation coefficient (CCC) = 0.963, p-value = 0.632, mean absolute error (MAE) = 1.59°; calcaneal pitch: PCC = 0.988, ICC = 0.987, CCC = 0.987, p-value = 0.055, MAE = 0.63°). The average time required for angle measurement using only the CPU to execute the deep learning-based system was 11 ± 1 s. The deep learning-based automatic angle measurement system, a tool for diagnosing flatfoot, demonstrated comparable accuracy and reliability with the results obtained by medical professionals for patients without internal fixation devices.

Outcomes of Medial Closing-Wedge Distal Femoral Osteotomy for Femoral- and Tibial-Based Valgus Deformity.

BACKGROUND: In carefully selected patients with an arthritic valgus knee, distal femoral osteotomy (DFO) can improve symptoms at medium- to long-term follow-up, reducing osteoarthritis progression. To date, there is no clear evidence in the current literature regarding the role of postoperative joint line obliquity (JLO) in valgus deformity correction. PURPOSE: To assess the clinical and radiological outcomes of medial closing-wedge DFO (MCW-DFO) for the treatment of valgus knees, considering both tibial- and femoral-based deformities, as well as to verify the efficacy and safety of MCW-DFO according to JLO boundaries (≤4°). STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: A retrospective analysis was conducted on a cohort of patients with valgus knees. Patients were divided into 2 groups: femoral-based valgus (FB-V) and tibial-based valgus (TB-V). Knee radiographs were collected before surgery and at the last follow-up. The clinical outcome was evaluated through several validated scores (International Knee Documentation Committee, Knee Society Score, Knee injury and Osteoarthritis Outcome Score, Tegner, Numeric Rating Scale, Crosby-Insall). RESULTS: A total of 30 patients (34 knees) with a mean age of 49.3 ± 9.1 years were included in the study. The overall mean follow-up was 9.4 ± 5.9 years. The mean preoperative hip-knee-ankle angle was 187.6°± 3.3° (range, 181.5°-191°) and the postoperative angle was 180°± 3.1° (range, 176°-185°). Most postoperative JLOs were within the safe zone of ≤4° in both groups (the postoperative JLO was >4° in 4 patients in the TB-V group and 1 patient in the FB-V group), although FB-V knees exhibited significant superior JLO correction (postoperative JLO in the TB-V group: mean, 4.0°± 2.5° [P = .1]; postoperative JLO in the FB-V group: mean, 2.4°± 1.4° [P = .5]). Significant improvements in all clinical scores were observed in both groups (P < .01). Additionally, the severity of the osteoarthritis did not worsen at the last follow-up. CONCLUSION: MCW-DFO is an effective procedure for treating pathological valgus knees, regardless of the site of the deformity. Both FB-V and TB-V groups showed comparable improvements in the clinical scores, development of osteoarthritis, and the restoration of a neutral mechanical axis. Notably, FB-V knees achieved more JLO correction compared with the TB-V ones.

Pediatric chest radiograph interpretation in a real-life setting.

Chest radiography is a frequently used imaging modality in children. However, only fair to moderate inter-observer agreement has been reported between chest radiograph interpreters. Most studies were not performed in real-world clinical settings. Our aims were to examine the agreement between emergency department pediatricians and board-certified radiologists in a pediatric real-life setting and to identify clinical risk factors for the discrepancies. Included were children aged 3 months to 18 years who underwent chest radiography in the emergency department not during the regular hours of radiologist interpretation. Every case was reviewed by an expert panel. Inter-observer agreement between emergency department pediatricians and board-certified radiologists was assessed by Cohen's kappa; risk factors for disagreement were analyzed. Among 1373 cases, the level of agreement between emergency department pediatricians and board-certified radiologists was "moderate" (k = 0.505). For radiographs performed after midnight, agreement was only "fair" (k = 0.391). The expert panel identified clinically relevant disagreements in 260 (18.9%) of the radiographs. Over-treatment of antibiotics was identified in 121 (8.9%) of the cases and under-treatment in 79 (5.8%). In a multivariable logistic regression, the following parameters were found to be significantly associated with disagreements: neurological background (p = 0.046), fever (p = 0.001), dyspnea (p = 0.014), and radiographs performed after midnight (p = 0.007). CONCLUSIONS: Moderate agreement was found between emergency department pediatricians and board-certified radiologists in interpreting chest radiographs. Neurological background, fever, dyspnea, and radiographs performed after midnight were identified as risk factors for disagreement. Implementing these findings could facilitate the use of radiologist expertise, save time and resources, and potentially improve patient care. WHAT IS KNOWN: • Only fair to moderate inter-observer agreement has been reported between chest radiograph interpreters. • Most studies were not performed in real-world clinical settings. Clinical risk factors for disagreements have not been reported. WHAT IS NEW: • In this study, which included 1373 cases at the emergency department, the level of agreement between interpreters was only "moderate." • The major clinical parameters associated with interpretation discrepancies were neurological background, fever, dyspnea, and interpretations conducted during the night shift.

DC-YOLOv5-based target detection algorithm for cervical vertebral maturation.

The cervical vertebral maturation (CVM) method is essential to determine the timing of orthodontic and orthopedic treatment. In this paper, a target detection model called DC-YOLOv5 is proposed to achieve fully automated detection and staging of CVM. A total of 1800 cephalometric radiographs were labeled and categorized based on the CVM stages. We introduced a model named DC-YOLOv5, optimized for the specific characteristics of CVM based on YOLOv5. This optimization includes replacing the original bounding box regression loss calculation method with Wise-IOU to address the issue of mutual interference between vertical and horizontal losses in Complete-IOU (CIOU), which made model convergence challenging. We incorporated the Res-dcn-head module structure to enhance the focus on small target features, improving the model's sensitivity to subtle sample differences. Additionally, we introduced the Convolutional Block Attention Module (CBAM) dual-channel attention mechanism to enhance focus and understanding of critical features, thereby enhancing the accuracy and efficiency of target detection. Loss functions, precision, recall, mean average precision (mAP), and F1 scores were used as the main algorithm evaluation metrics to assess the performance of these models. Furthermore, we attempted to analyze regions important for model predictions using gradient Class Activation Mapping (CAM) techniques. The final F1 scores of the DC-YOLOv5 model for CVM identification were 0.993, 0.994 for mAp0.5 and 0.943 for mAp0.5:0.95, with faster convergence, more accurate and more robust detection than the other four models. The DC-YOLOv5 algorithm shows high accuracy and robustness in CVM identification, which provides strong support for fast and accurate CVM identification and has a positive effect on the development of medical field and clinical diagnosis.

False-Profile Radiograph Sourcil-Edge and Bone-Edge Measurements Correlate to Different Weightbearing Regions of the Acetabulum: A 3-Dimensional Analysis.

BACKGROUND: The acetabular sourcil is commonly interpreted as a reliable radiographic representation of the weightbearing dome of the acetabulum, despite limited modern data. Assessment of weightbearing acetabular coverage has been described using both the sourcil edge and bone edge as anatomic landmarks, leading to confusion and potential misguidance in surgical decision-making and thus compromised patient outcomes. PURPOSE/HYPOTHESIS: The purpose of this study was to characterize the 3-dimensional (3D) anatomic correlates of the sourcil-edge and bone-edge radiographic measurements on false-profile radiographs. It was hypothesized that the sourcil edge would represent anterolateral coverage and the bone edge would represent anterior coverage. STUDY DESIGN: Descriptive laboratory study. METHODS: A total of 80 hips were grouped by large or small differences between bone-edge and sourcil-edge anterior center-edge angles, based on upper and lower quartiles of discrepancy. Three-dimensional surface mesh models and digitally reconstructed radiographs were generated from hip computed tomography scans. Sourcil-edge and bone-edge anterior center-edge angles were identified on digitally reconstructed radiographs and registered to the 3D models with fiducial markers. Intersections of bone-edge and sourcil-edge projection lines with the acetabular rim were obtained from the 3D models. RESULTS: The bone-edge and sourcil-edge projections intersected the acetabular rim at clockface means of 2:05 ± 0:22 and 1:12 ± 0:25, respectively. The 3D models consistently demonstrated that, in both large- and small-discrepancy groups, the sourcil edge corresponded to the acetabular area just posterior to the anterior inferior iliac spine (AIIS) projection, and the bone edge corresponded to the weightbearing region inferior to the AIIS. Additionally, in large-discrepancy hips, the bone edge corresponded to more prominent acetabular coverage in the region inferomedial to the AIIS when compared with the small-discrepancy hips. CONCLUSION: On false-profile radiographs, the sourcil edge corresponds to superior femoral head coverage, and the bone edge corresponds to anterosuperior coverage. Radiographs with a large discrepancy between sourcil-edge and bone-edge measurements demonstrate acetabular rim prominence in the region of the AIIS. CLINICAL RELEVANCE: Characterizing the anatomic weightbearing regions of the acetabulum represented on false-profile radiographs facilitates improved clinical and intraoperative decision-making in hip preservation surgery, including acetabuloplasty and periacetabular osteotomy.

Weight-bearing pain and implant migration, progressive radiolucencies, radiolucency more than 2 mm and subsidence on radiographs and CT are generally accepted criteria for knee arthroplasty loosening: An international Delphi consensus study.

PURPOSE: Establishing the diagnosis of loosening in total or unicondylar knee arthroplasty remains a challenge with different clinical and radiological signs evaluated in study designs with high risk of bias, where few or incomplete criteria are formulated for establishing the diagnosis of implant loosening. This study aimed at evaluating the variability between different clinical and radiological criteria and establish a consensus regarding clinical and radiological criteria for the diagnosis of knee arthroplasty loosening. METHODS: Highly specialized knee surgeons focusing on revision arthroplasty were invited to take part in an international panel for a Delphi consensus study. In the first round, the participants were asked to state their most important clinical and radiological criteria for implant loosening. In a second round, the panel's agreement with the collected criteria was rated on a 5-point Likert scale (1-5). High variability was defined by receiving at least one score each indicating complete disagreement and complete agreement. Consensus was established when over 70% of participants rated a criterion as 'fully agree' (5) or 'mostly agree' (4). RESULTS: High variability was observed in 56% of clinical criteria and 38% of radiological criteria. A consensus was reached on one clinical (weight-bearing pain [82%]) and four radiological criteria, that is, implant migration, progressive radiolucencies, subsidence and radiolucencies >2 mm on X-ray or computed tomography (CT) (84%-100%). CONCLUSION: Amongst specialized knee revision surgeons, there is high variability in clinical and radiological criteria that are seen as important contributing factors to diagnosis of knee implant loosening. A consensus was reached on weight-bearing pain as clinical criterion and on implant migration, progressive radiolucencies, subsidence and radiolucencies of more than 2 mm on X-ray or CT as radiological criteria. The variability rates observed, along with the criteria that reached consensus, offer important insights for the standardization of diagnostic protocols. LEVEL OF EVIDENCE: Level V.

The influence of tibial length on radiographic posterior tibial slope measurement: How much tibia do we need?

PURPOSE: The purpose of this study was to determine whether significant differences exist when comparing posterior tibial slope (PTS) measured using increasing lengths of the tibia to determine the anatomical axis. METHODS: Patients with full-length weight-bearing tibial radiographs were retrospectively identified from 2014 to 2022 at a single institution. Patients were excluded if there was any previous history of lower extremity fracture or osteotomy. The anatomical axis of the tibia was determined using the full length of tibial radiographs, and the "reference PTS" was measured using this axis. Using the same radiograph, the PTS was measured using four different anatomical axes at standardized tibial lengths. While the center of the proximal circle remained constant at 5-cm below the tibial plateau, the center of the distal circle was drawn at four points: a) overlapping circles; b) 10-cm distal to the tibial plateau; c) 15-cm distal to the tibial plateau; d) half the length of the tibia, measured from the tibial plateau to the tibial plafond. Bivariate correlation and frequency distribution analysis (measurements >2-degrees from reference PTS) were performed between the reference PTS and PTS measured at each of the four other lengths. RESULTS: A total of 154 patients (39.8 ± 17.4 years old, 44.2% male) were included in the final analysis. Measurements at each of the four tibial lengths were all significantly different from the reference PTS (p < 0.001). The correlation strength improved with increasing tibial length (overlapping: R = 0.681, 10-cm: R = 0.821, 15-cm: R = 0.937, and half-tibia: R = 0.963). The number of PTS measurements >2-degree absolute difference from the reference PTS decreased with increasing tibial length (overlapping: 40.3%, 10-cm: 24.0%, 15-cm: 26.0%, and half-tibia: 18.8%). CONCLUSION: Assessment of PTS is dependent on the length of the tibia utilized to obtain the anatomical axis. Accuracy and precision of PTS measurements improved with increasing length of tibia used to determine the anatomical axis. STUDY DESIGN: Case series.

YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition.

OBJECTIVES: In the interpretation of panoramic radiographs (PRs), the identification and numbering of teeth is an important part of the correct diagnosis. This study evaluates the effectiveness of YOLO-v5 in the automatic detection, segmentation, and numbering of deciduous and permanent teeth in mixed dentition pediatric patients based on PRs. METHODS: A total of 3854 mixed pediatric patients PRs were labelled for deciduous and permanent teeth using the CranioCatch labeling program. The dataset was divided into three subsets: training (n = 3093, 80% of the total), validation (n = 387, 10% of the total) and test (n = 385, 10% of the total). An artificial intelligence (AI) algorithm using YOLO-v5 models were developed. RESULTS: The sensitivity, precision, F-1 score, and mean average precision-0.5 (mAP-0.5) values were 0.99, 0.99, 0.99, and 0.98 respectively, to teeth detection. The sensitivity, precision, F-1 score, and mAP-0.5 values were 0.98, 0.98, 0.98, and 0.98, respectively, to teeth segmentation. CONCLUSIONS: YOLO-v5 based models can have the potential to detect and enable the accurate segmentation of deciduous and permanent teeth using PRs of pediatric patients with mixed dentition.

Radiographic Edema Is a Predictor of de Quervain's Tenosynovitis.

Background de Quervain's tenosynovitis (DeQ) is a clinical diagnosis; however, due to the symptom overlap with other pathologies, it can occasionally be challenging to make an accurate diagnosis, especially for nonorthopaedic trained physicians. Questions/Purposes We hypothesized that the ratio of radial-sided to ulnar-sided soft tissue swelling could serve as a universally accessible diagnostic tool to assist in differentiating DeQ from other upper extremity conditions. Patients and Methods We retrospectively identified patients with isolated DeQ (M65.4), thumb carpometacarpal arthritis (M18.X), or carpal tunnel syndrome (G56.0x) between 2018 and 2019. Five blinded, independent reviewers evaluated anterior-posterior radiographs of the affected wrist. A digital caliper was used to measure the shortest distance from the lateral cortex of the distal radius and the medial cortex of the distal ulna to the outer edge of the radial and ulnar soft tissue shadows, respectively. Results The mean radial:ulnar ratio in the DeQ group was significantly larger than in the control groups. The interclass correlation coefficient showed strong agreement between all measurements. Patients with a radial:ulnar ratio of 1.7 or higher had a 61% chance of having DeQ with a 56.5% sensitivity, 66.3% specificity, 59.3% positive predictive value (PPV), and 63.8% negative predictive value. A ratio of more than 2.5 correlates to a 55% chance of having DeQ with a sensitivity of 12.9%, specificity of 96.9%, and PPV of 78.6%. Conclusion The ratio of radial- to ulnar-sided wrist edema can be used as a novel diagnostic aid in DeQ, especially for those not trained in orthopaedics or hand surgery. Level of Evidence Level IV, diagnostic study.

Reliability assessment of leg length and angular alignment on manual reads versus artificial intelligence-generated lower extremity radiographic measurements.

PURPOSE: Leg length discrepancy (LLD) and lower extremity malalignment can lead to pain and osteoarthritis. A variety of radiographic parameters are used to assess LLD and alignment. A 510(k) FDA approved artificial intelligence (AI) software locates landmarks on full leg standing radiographs and performs several measurements. The objective of this study was to assess the reliability of this AI tool compared to three manual readers. METHODS: A sample of 320 legs was used. Three readers' measurements were compared to AI output for hip-knee-angle (HKA), anatomical-tibiofemoral angle (aTFA), anatomical-mechanical-axis angle (AMA), joint-line-convergence angle (JLCA), mechanical-lateral-proximal-femur-angle (mLPFA), mechanical-lateral-distal-femur-angle (mLDFA), mechanical-medial-proximal-tibia-angle (mMPTA), mechanical-lateral-distal-tibia- angle (mLDTA), femur length, tibia length, full leg length, leg-length-discrepancy (LLD), and mechanical-axis-deviation (MAD). Intraclass correlation coefficients (ICCs) and Bland-Altman analysis were used to track performance. RESULTS: AI output was successfully produced for 272/320 legs in the study. The reader versus AI pairwise ICCs were mostly in the excellent range: 12/13, 12/13, and 9/13 variables were in the excellent range (ICC > 0.75) for readers 1, 2, and 3, respectively. There was better agreement for leg length, femur length, tibia length, LLD, and HKA than for other variables. The median reading times for the three readers and AI were 250, 282, 236, and 38 s, respectively. CONCLUSION: This study showed that AI-based software provides reliable assessment of LLD and lower extremity alignment with substantial time savings.

Changes in femoral anteversion after intramedullary nailing for pediatric femoral shaft fracture: a multicenter study.

BACKGROUND: The rotational change after using a flexible intramedullary (IM) nail for femoral shaft fractures has been a concern for many surgeons. Recently, a statistical shape model (SSM) was developed for the three-dimensional reconstruction of the femur from two-dimensional plain radiographs. In this study, we measured postoperative femoral anteversion (FAV) in patients diagnosed with femoral shaft fractures who were treated with flexible IM nails and investigated age-related changes in FAV using the SSM. METHODS: This study used radiographic data collected from six regional tertiary centers specializing in pediatric trauma in South Korea. Patients diagnosed with femoral shaft fractures between September 2002 and June 2020 and patients aged < 18 years with at least two anteroposterior (AP) and lateral (LAT) femur plain radiographs obtained at least three months apart were included. A linear mixed model (LMM) was used for statistical analysis. RESULTS: Overall, 72 patients were included in the study. The average patient age was 7.6 years and the average follow-up duration was 6.8 years. The average FAV of immediate postoperative images was 27.5 ± 11.5°. Out of 72 patients, 52 patients (72.2%) showed immediate postoperative FAV greater than 20°. The average FAV in patients with initial FAV > 20° was 32.74°, and the LMM showed that FAV decreased by 2.5° (p = 0.0001) with each 1-year increase from the time of initial trauma. CONCLUSIONS: This study explored changes in FAV after femoral shaft fracture using a newly developed technology that allows 3D reconstruction from uncalibrated 2D images. There was a pattern of change on the rotation of the femur after initial fixation, with a 2.5° decrease of FAV per year.

Update on Rheumatic Diseases in Clinical Practice: Recent Concepts and Developments.

Diagnostic imaging is essential in the diagnostic process of rheumatic diseases. Given the heterogeneity of this group of diseases and the tremendous impact of novel therapeutic options, guidelines and recommendations regarding the optimal choice of the most appropriate technique/s are continuously revised and radiologists should always be up-to-date. Last, because of the continuous technological innovations, we will assist to the progressive application of advanced techniques and tools in rheumatology.

Traditional radiography versus computed tomography to assess reduced distal radius fractures.

INTRODUCTION: This study compares computed tomography (CT) with plain radiography in its ability to assess distal radius fracture (DRF) malalignment after closed reduction and cast immobilization. METHODS: Malalignment is defined as radiographic fracture alignment beyond threshold values according to the Dutch guideline encompassing angulation, inclination, positive ulnar variance and intra-articular step-off or gap. After identifying 96 patients with correct alignment on initial post-reduction radiographs, we re-assessed alignment on post-reduction CT scans. RESULTS: Significant discrepancies were found between radiographs and CT scans in all measurement parameters. Notably, intra-articular step-off and gap variations on CT scans led to the reclassification of the majority of cases from correct alignment to malalignment. CT scans showed malalignment in 53% of cases, of which 73% underwent surgery. CONCLUSION: When there is doubt about post-reduction alignment based on radiograph imaging, additional CT scanning often reveals malalignment, primarily due to intra-articular incongruency.

Automatic classification and grading of canine tracheal collapse on thoracic radiographs by using deep learning.

Tracheal collapse is a chronic and progressively worsening disease; the severity of clinical symptoms experienced by affected individuals depends on the degree of airway collapse. Cutting-edge automated tools are necessary to modernize disease screening using radiographs across various veterinary settings, such as animal clinics and hospitals. This is primarily due to the inherent challenges associated with interpreting uncertainties among veterinarians. In this study, an artificial intelligence model was developed to screen canine tracheal collapse using archived lateral cervicothoracic radiographs. This model can differentiate between a normal and collapsed trachea, ranging from early to severe degrees. The you-only-look-once (YOLO) models, including YOLO v3, YOLO v4, and YOLO v4 tiny, were used to train and test data sets under the in-house XXX platform. The results showed that the YOLO v4 tiny-416 model had satisfactory performance in screening among the normal trachea, grade 1-2 tracheal collapse, and grade 3-4 tracheal collapse with 98.30% sensitivity, 99.20% specificity, and 98.90% accuracy. The area under the curve of the precision-recall curve was >0.8, which demonstrated high diagnostic accuracy. The intraobserver agreement between deep learning and radiologists was κ = 0.975 (P < .001), with all observers having excellent agreement (κ = 1.00, P < .001). The intraclass correlation coefficient between observers was >0.90, which represented excellent consistency. Therefore, the deep learning model can be a useful and reliable method for effective screening and classification of the degree of tracheal collapse based on routine lateral cervicothoracic radiographs.

Two-stage corrective operation for the treatment of pes cavovarus in patients with spina bifida.

BACKGROUND: Pes cavovarus has an estimated incidence of 8%-17% in patients with spina bifida (SB). The majority of the current literature on surgical treatment of cavovarus feet in children and adolescents includes a variety of diagnoses. There are currently no case series describing a treatment algorithm for deformity correction in this specific patient population. The authors of this study present the results of a retrospective case series performed to assess the radiographic outcomes of two-stage corrective surgery in patients with SB. AIM: To assess the radiographic outcomes of a staged operation consisting of radical plantar release followed by osteotomy for pes cavovarus in patients with SB. METHODS: Retrospective chart review was performed on patients with SB with a diagnosis of pes cavovarus at a freestanding children's hospital who underwent surgical correction of the deformity. Patients were excluded for lack of two-stage corrective operation, nonambulatory status, lack of at least six months follow-up, and age > 18 years at the time of surgery. This resulted in a cohort of 19 patients. Radiographic analysis was performed on 11 feet that had a complete series of preoperative and postoperative weightbearing X-rays. Preoperative and postoperative radiographic outcome measurements were compared using a two-sample t-test. RESULTS: Significant changes between the preoperative and postoperative measurements were seen in Meary's angle, the anteroposterior talo-first metatarsal (AP TMT1) angle, and the talonavicular coverage. Mean values of Meary's angle were 17.9 ± 13.1 preoperatively and 4.7 ± 10.3 postoperatively (P = 0.016). Mean AP TMT1 angle was 20.6 ± 15.1 preoperatively and 9.3 ± 5.5 postoperatively (P = 0.011). Mean talonavicular coverage values were -10.3 ± 9.6 preoperatively and -3.8 ± 10.1 postoperatively (P = 0.025). CONCLUSION: The two-stage corrective procedure demonstrated efficacy in correcting cavovarus deformity in patients with SB. Providers should strongly consider employing the staged surgical algorithm presented in this manuscript for management of these patients.

Utility of Recovery Room vs Post-Operative Day 1 Radiographs Following Shoulder Arthroplasty.

Background: Postoperative radiographs may be performed on different timelines after shoulder arthroplasty. Radiographs obtained in the post-operative recovery unit (PACU) are often of poorer quality. The purpose of the current study was to explore and compare the quality of PACU radiographs and radiographs performed in the radiology suite on post-operative Day 1 (POD1), as well as determine their impact on changes in post-operative management. Methods: Our series included 50 consecutive anatomic total shoulder arthroplasties (TSA) for which post-operative radiographs were obtained in the PACU and 50 consecutive TSA for which post-operative radiographs were obtained in the radiology suite on POD 1. TSA radiographs were blinded and reviewed by 3 authors and graded on their quality using criteria described using previously published methods. The weighted kappa was used to describe the intra-rater agreement and inter-rater agreement between two raters. Results: There was no difference in age, sex, BMI, and comorbidities between cohorts. Intra-observer reliability was moderate to substantial with weighted kappa values of 0.65±0.07 (p<0.001), 0.58±0.09 (p<0.001), and 0.67±0.07 (p<0.001). Inter-observer reliability was moderate to substantial with weighted kappa values of 0.605±0.07 (p<0.001), 0.66±0.07 (p<0.001), and 0.65±0.08 (p<0.001). When assessing quality of radiographs, 30% of radiographs obtained in PACU were deemed quality while 57% of radiographs obtained in the radiology suite were deemed quality (p<0.001). Conclusion: Post-operative radiographs in the PACU do not alter patient management and are often inadequate to serve as baseline radiographs. Conversely, radiographs obtained in the radiology suite are of higher quality and can serve as a superior baseline radiograph. Level of Evidence: IV.

Comparison of two CBCT analysis techniques with conventional periapical radiographs in assessment of tertiary dentin after indirect pulp capping in young permanent teeth.

BACKGROUND AND AIM: To compare two cone beam computed tomography (CBCT) analysis techniques for measuring tertiary dentin (TD) volume, density, and root length increase, after indirect pulp therapy (IPT) in young permanent teeth with conventional periapical radiographs. DESIGN: Comparative study design: Sixty-nine CBCT scans were taken initially (T1) and after 1 year (T2) of IPT. New CBCT analysis technique A, standardization, segmentation, and registration of T1 and T2 scans were performed using ITK-SNAP and 3D Slicer CMF to measure TD volume (mm3), density (gray-level intensity), and root length increase (mm). In the traditional CBCT analysis technique B, analyses were conducted using the In-Vivo software to calculate TD thickness (mm), radiodensity (HU%), and root length increase (mm). Paired t-test and the intraclass correlation coefficient were calculated to compare and assess the reliability of all techniques. RESULTS: No significant difference between the two techniques existed in the measurement of TD mineral density (Mean [SD]:A = 22.4 [15.4]; B = 24.4 [15.4]; p = .47). Technique A resulted in significantly higher root length increase values (Mean [SD]: A = 1.3 [0.6]; B = 1.1 [0.5]; p = .03). The two techniques showed acceptable reliability levels (0.76-0.99). CONCLUSION: CBCT analysis techniques yielded similar findings for mineral density. The new CBCT volumetric analysis technique, although more laborious, produced higher values for root length increase, and allowed for measurement of dentin volume.