RESUMO
PURPOSE: This study aimed to evaluate patient-reported outcome measures (PROMs) and the effects of gender and age on achieving clinically significant outcomes in patients undergoing arthroscopic superior capsular reconstruction (ASCR) with a minimum 2-year follow-up. METHODS: Patients undergoing ASCR for irreparable rotator cuff tear between 2013 and 2020 were reviewed. Preoperative and minimum 2-year postoperative PROMs were collected, including American Shoulder and Elbow Surgeons (ASES), Constant, single assessment numeric evaluation (SANE), and visual analog scale (VAS) scores. Minimal clinically important difference (MCID) and patient-acceptable symptomatic state (PASS) were calculated for each functional score and analyzed according to age and gender. The percentages of patients achieving MCID and PASS were recorded. RESULTS: The study included 83 patients, with a mean follow-up of 3.5 ± 1.4 years. Significant improvements were found in ASES, Constant, SANE, and VAS for all groups based on gender and age. Based on receiver-operating characteristic curves, all scores had acceptable areas under the curve for PASS. Values for PASS and MCID were 81.5 and 10.3 for ASES; 61.5 and 6.2 for Constant; 82.5 and 11.5 for SANE and 1.5 and 1.1 for VAS, respectively. Analysis of achieving MCID and PASS showed no difference between the groups in the majority of outcome measures. However, female patients achieved the SANE thresholds for PASS at significantly higher rates than male patients. Patients ≥65 years old achieved ASES and Constant thresholds for MCID at significantly higher rates than patients Ë65 years old. CONCLUSION: Most patients achieved MCID and PASS at a 2-year follow-up. Patients showed comparable rates of MCID and PASS achievement on most outcome tools based on age and gender. Female patients achieved PASS on SANE at significantly higher rates than male patients and older patients achieved MCID on ASES and Constant at higher rates than young patients. Thus, age is a stronger factor for achieving MCID than gender. LEVEL OF EVIDENCE: Level II.
Assuntos
Diferença Mínima Clinicamente Importante , Lesões do Manguito Rotador , Humanos , Masculino , Feminino , Idoso , Resultado do Tratamento , Ombro , Lesões do Manguito Rotador/cirurgia , Avaliação de Resultados em Cuidados de Saúde , Estudos Retrospectivos , ArtroscopiaRESUMO
HYPOTHESIS: This study aimed to investigate the correlation between rotator cuff stump classification and postoperative outcomes after superior capsular reconstruction (SCR). METHODS: A total of 75 patients who underwent SCR between June 2013 and May 2021 were included in this study. Based on stump classification using the signal intensity ratio of the tendon rupture site to the deltoid muscle in the coronal view of preoperative T2-weighted, fat-suppressed magnetic resonance imaging scans, the patients were classified into types 1, 2, and 3 with ratios of <0.8, 0.8-1.3, and >1.3 (44, 17, and 14 patients, respectively). The American Shoulder and Elbow Surgeons (ASES), Constant, and visual analog scale (VAS) scores for pain and range of motion were evaluated at a minimum of 1 year of follow-up postoperatively. The acromiohumeral distance and rotator cuff arthropathy according to the Hamada classification were assessed on plain radiography. The graft integrity was evaluated by magnetic resonance imaging at 3 and 12 months postoperatively and annually thereafter. RESULTS: Clinical and radiological outcomes were significantly improved after SCR. In comparison with type 2 and 3 patients, type 1 patients had significantly higher ASES scores (type 1, 2, and 3 = 84 ± 10, 75 ± 15, and 76 ± 14; all P = .014), Constant scores (type 1, 2, and 3 = 65 ± 5, 61 ± 9, and 56 ± 13; all P = .005), and forward flexion (type 1, 2, and 3 = 155 ± 10, 154 ± 15, and 145 ± 13; all P = .013). However, these statistical differences between groups were below the established minimum clinically important difference values for the ASES and Constant scores after rotator cuff repair. The graft failure rate after surgery was lower in the type 1 group than that in the other 2 groups; however, the difference was not statistically significant (P = .749). CONCLUSION: Patients with stump classification type 1 showed significantly better functional scores (ASES and VAS scores) and forward flexion; however, the clinical importance of these differences may be limited. Stump classification may be useful for predicting postoperative clinical outcomes.
Assuntos
Imageamento por Ressonância Magnética , Lesões do Manguito Rotador , Manguito Rotador , Humanos , Masculino , Feminino , Pessoa de Meia-Idade , Imageamento por Ressonância Magnética/métodos , Lesões do Manguito Rotador/cirurgia , Lesões do Manguito Rotador/diagnóstico por imagem , Idoso , Manguito Rotador/cirurgia , Manguito Rotador/diagnóstico por imagem , Estudos Retrospectivos , Amplitude de Movimento Articular , Resultado do Tratamento , Adulto , Procedimentos de Cirurgia Plástica/métodos , Cápsula Articular/cirurgia , Cápsula Articular/diagnóstico por imagem , Articulação do Ombro/cirurgia , Articulação do Ombro/diagnóstico por imagemRESUMO
OBJECTIVES: Diagnosis of flatfoot using a radiograph is subject to intra- and inter-observer variabilities. Here, we developed a cascade convolutional neural network (CNN)-based deep learning model (DLM) for an automated angle measurement for flatfoot diagnosis using landmark detection. METHODS: We used 1200 weight-bearing lateral foot radiographs from young adult Korean males for the model development. An experienced orthopedic surgeon identified 22 radiographic landmarks and measured three angles for flatfoot diagnosis that served as the ground truth (GT). Another orthopedic surgeon (OS) and a general physician (GP) independently identified the landmarks of the test dataset and measured the angles using the same method. External validation was performed using 100 and 17 radiographs acquired from a tertiary referral center and a public database, respectively. RESULTS: The DLM showed smaller absolute average errors from the GT for the three angle measurements for flatfoot diagnosis compared with both human observers. Under the guidance of the DLM, the average errors of observers OS and GP decreased from 2.35° ± 3.01° to 1.55° ± 2.09° and from 1.99° ± 2.76° to 1.56° ± 2.19°, respectively (both p < 0.001). The total measurement time decreased from 195 to 135 min in observer OS and from 205 to 155 min in observer GP. The absolute average errors of the DLM in the external validation sets were similar or superior to those of human observers in the original test dataset. CONCLUSIONS: Our CNN model had significantly better accuracy and reliability than human observers in diagnosing flatfoot, and notably improved the accuracy and reliability of human observers. KEY POINTS: ⢠Development of deep learning model (DLM) that allows automated angle measurements for landmark detection based on 1200 weight-bearing lateral radiographs for diagnosing flatfoot. ⢠Our DLM showed smaller absolute average errors for flatfoot diagnosis compared with two human observers. ⢠Under the guidance of the model, the average errors of two human observers decreased and total measurement time also decreased from 195 to 135 min and from 205 to 155 min.
Assuntos
Pé Chato , Masculino , Adulto Jovem , Humanos , Pé Chato/diagnóstico por imagem , Pé Chato/cirurgia , Reprodutibilidade dos Testes , Radiografia , Redes Neurais de Computação , Suporte de CargaRESUMO
PURPOSE: To investigate the time-dependent nature of clinically significant outcomes, including the minimal clinically important difference (MCID), substantial clinical benefit, and Patient Acceptable Symptomatic State (PASS) after arthroscopic superior capsular reconstruction, and the factors contributing to the achievement of early clinically significant outcomes. METHODS: Patients who underwent ASCR between March 2015 and September 2020 with complete preoperative and postoperative 6-month, 1-year, and 2-year patient-reported outcome measures (PROMs) were retrospectively analysed. Threshold values for MCID, substantial clinical benefit, and PASS were obtained from the previous literature for the PROMs. The time required to achieve clinically significant outcomes was calculated using Kaplan-Meier analysis. Multivariate Cox regression was performed to evaluate the variables predictive of an earlier or delayed achievement of MCID. RESULTS: Fifty-nine patients with a mean age of 64.5 ± 8.7 years old were included. The time of mean achievement of MCID, substantial clinical benefit, and PASS for VAS was 11.2 ± 0.9, 16.3 ± 1.1, and 16.6 ± 0.9 months, respectively. The time of mean achievement of MCID, substantial clinical benefit, and PASS for ASES was 13.2 ± 1.0, 16.8 ± 1.0, and 18.3 ± 0.9 months, respectively. The time of mean achievement of MCID, substantial clinical benefit, and PASS for the Constant score was 11.6 ± 0.9, 15.1 ± 1.0, and 14.7 ± 0.9 months, respectively. The time of mean achievement of MCID, substantial clinical benefit, and PASS for SANE was 14.4 ± 1.0, 16.1 ± 1.0, and 15.5 ± 0.8 months, respectively. Patients with a higher preoperative VAS score achieved an earlier MCID for VAS (P = 0.014). However, patients with a higher preoperative ASES and SANE scores achieved delayed MCID for ASES and SANE (P = 0.026, and P < 0.001, respectively). CONCLUSION: Most patients achieved MCIDs around 1 year after arthroscopic superior capsular reconstruction. A higher preoperative VAS score favours faster MCID achievement, while higher preoperative ASES and SANE scores contribute to delayed MCID achievement. STUDY DESIGN: Cohort study LEVEL OF EVIDENCE: Level IV.
Assuntos
Artroscopia , Diferença Mínima Clinicamente Importante , Humanos , Pessoa de Meia-Idade , Idoso , Estudos de Coortes , Resultado do Tratamento , Estudos Retrospectivos , Medidas de Resultados Relatados pelo PacienteRESUMO
PURPOSE: Treatment of a tibial plateau fracture (TPF) remains controversial and is generally challenging. Many authors report good results after conventional open reduction and internal fixation in TPF, but complications still occur. This study analyzed causes and outcomes of revision surgery for TPF. The usefulness of a flow chart for revision surgery in TPF was also evaluated. METHODS: We reviewed all patients who underwent more than two operations for a TPF between 2008 and 2015. Finally, 24 cases were selected and retrospectively investigated. The medial tibial plateau angle and proximal posterior tibial angle were radiologically evaluated. The American Knee Society Score (AKSS), Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), range of motion (ROM), and bone union time were investigated after surgery. RESULTS: Revision surgery for infection was performed in eight cases, for nonunion in six cases, for posttraumatic arthritis (with total knee arthroplasty) in six cases, and for other reasons in four cases. The mean clinical AKSS at final follow-up was 87.3 ± 5.3 (range, 75-95), the functional AKSS was 81.9 ± 5.5 (range, 70-90), the WOMAC score was 9.9 ± 3.1 (range, 5-16), the flexion ROM was 119.8 ± 16.5° (range, 100-150°), and the extension ROM was 2.5 ± 3.3° (range, 0-10°). CONCLUSIONS: Although complications cannot be avoided in some cases, good clinical outcomes are possible when patients are divided according to the presence or absence of infection, with selection of appropriate revision surgery as shown in the flow chart. If an infection is present, treatment should be based on the presence or absence of bone union. If there is no infection, treatment should be based on the presence or absence of nonunion, post-traumatic arthritis, malunion, or immediate post-operative malreduction.
Assuntos
Fixação Interna de Fraturas/efeitos adversos , Traumatismos do Joelho/cirurgia , Redução Aberta/efeitos adversos , Tíbia/cirurgia , Fraturas da Tíbia/cirurgia , Adulto , Idoso , Feminino , Humanos , Traumatismos do Joelho/complicações , Articulação do Joelho/cirurgia , Masculino , Pessoa de Meia-Idade , Reoperação , Estudos Retrospectivos , Tíbia/lesões , Fraturas da Tíbia/complicações , Adulto JovemRESUMO
BACKGROUND: The goal of this study was to compare the inter- and intra-observer reliabilities of computed tomography (CT) scans of bicondylar tibial plateau fractures (Bi-TPFs) with or without distraction with a bridging external fixation (EF) as interpreted by inexperienced surgeons. METHODS: Patients that underwent CT after distraction with a bridging EF were allocated to group 1 (n = 18), and patients that underwent CT before distraction with a bridging EF were allocated to group 2 (n = 18). Five observers were given plain radiographs and CT images to assess (survey 1) and this assessment was repeated six weeks later (survey 2). Agreements regarding fracture classification and pre-operative planning were evaluated using kappa coefficients. In addition, to evaluate fracture severity, we designed a severity score. RESULTS: Inter-observer reliabilities for fracture classification and pre-operative planning were higher in group 1 than in group 2. Surveys 1 and 2 revealed similar kappa coefficients in the two study groups. The mean absolute difference (MAD) in severity scores allocated at the two surveys was significantly different between the two groups (P = 0.045). Intra-observer reliabilities of fracture classification and pre-operative planning were also higher in group 1 than in group 2. In addition, level of training was found to have a significant impact on the MAD in severity scores (P = 0.007). CONCLUSIONS: Inter- and intra-observer reliabilities for fracture classification and pre-operative planning were better for inexperienced surgeons when CT was performed after distraction with a bridging EF for Bi-TPFs. Thus, when staged treatment using EF is selected in Bi-TPF patients, the authors suggest that CT scans be performed after distraction with a bridging EF especially for inexperienced surgeons.
Assuntos
Fixação de Fratura/métodos , Osteogênese por Distração/métodos , Fraturas da Tíbia/cirurgia , Tomografia Computadorizada por Raios X/métodos , Adulto , Idoso , Fixadores Externos/efeitos adversos , Feminino , Fixação de Fratura/efeitos adversos , Humanos , Escala de Gravidade do Ferimento , Masculino , Pessoa de Meia-Idade , Variações Dependentes do Observador , Osteogênese por Distração/efeitos adversos , Estudos Retrospectivos , Cirurgiões , Inquéritos e Questionários , Tíbia/diagnóstico por imagem , Tíbia/cirurgia , Fraturas da Tíbia/diagnóstico por imagemRESUMO
BACKGROUND/PURPOSE: Distal radius fractures (DRFs) account for approximately 18% of fractures in patients 65 years and older. While plain radiographs are standard, the value of high-resolution computed tomography (CT) for detailed imaging crucial for diagnosis, prognosis, and intervention planning, and increasingly recognized. High-definition 3D reconstructions from CT scans are vital for applications like 3D printing in orthopedics and for the utility of mobile C-arm CT in orthopedic diagnostics. However, concerns over radiation exposure and suboptimal image resolution from some devices necessitate the exploration of advanced computational techniques for refining CT imaging without compromising safety. Therefore, this study aims to utilize conditional Generative Adversarial Networks (cGAN) to improve the resolution of 3 mm CT images (CT enhancement). METHODS: Following institutional review board approval, 3 mm-1 mm paired CT data from 11 patients with DRFs were collected. cGAN was used to improve the resolution of 3 mm CT images to match that of 1 mm images (CT enhancement). Two distinct methods were employed for training and generating CT images. In Method 1, a 3 mm CT raw image was used as input with the aim of generating a 1 mm CT raw image. Method 2 was designed to emphasize the difference value between the 3 mm and 1 mm images; using a 3 mm CT raw image as input, it produced the difference in image values between the 3 mm and 1 mm CT scans. Both quantitative metrics, such as peak signal-to-noise ratio (PSNR), mean squared error (MSE), and structural similarity index (SSIM), and qualitative assessments by two orthopedic surgeons were used to evaluate image quality by assessing the grade (1~4, which low number means high quality of resolution). RESULTS: Quantitative evaluations showed that our proposed techniques, particularly emphasizing the difference value in Method 2, consistently outperformed traditional approaches in achieving higher image resolution. In qualitative evaluation by two clinicians, images from method 2 showed better quality of images (grade: method 1, 2.7; method 2, 2.2). And more choice was found in method 2 for similar image with 1 mm slice image (15 vs 7, p = 201). CONCLUSION: In our study utilizing cGAN for enhancing CT imaging resolution, the authors found that the method, which focuses on the difference value between 3 mm and 1 mm images (Method 2), consistently outperformed.
Assuntos
Fraturas do Rádio , Tomografia Computadorizada por Raios X , Fraturas do Punho , Humanos , Redes Neurais de Computação , Fraturas do Rádio/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Fraturas do Punho/diagnóstico por imagemRESUMO
We report here a case of oral myiasis in the Republic of Korea. The patient was a 37-year-old man with a 30-year history of Becker's muscular dystrophy. He was intubated due to dyspnea 8 days prior to admission to an intensive care unit (ICU). A few hours after the ICU admission, 43 fly larvae were found during suction of the oral cavity. All maggots were identified as the third instars of Lucilia sericata (Diptera: Calliphoridae) by morphology. We discussed on the characteristics of myiasis acquired in Korea, including the infection risk and predisposing factors.
Assuntos
Dípteros/classificação , Boca/parasitologia , Miíase/diagnóstico , Miíase/parasitologia , Adulto , Animais , Dípteros/anatomia & histologia , Humanos , Larva/anatomia & histologia , Larva/classificação , Masculino , República da CoreiaRESUMO
Recent studies of automatic diagnosis of vertebral compression fractures (VCFs) using deep learning mainly focus on segmentation and vertebral level detection in lumbar spine lateral radiographs (LSLRs). Herein, we developed a model for simultaneous VCF diagnosis and vertebral level detection without using adjacent vertebral bodies. In total, 1102 patients with VCF, 1171 controls were enrolled. The 1865, 208, and 198 LSLRS were divided into training, validation, and test dataset. A ground truth label with a 4-point trapezoidal shape was made based on radiological reports showing normal or VCF at some vertebral level. We applied a modified U-Net architecture, in which decoders were trained to detect VCF and vertebral levels, sharing the same encoder. The multi-task model was significantly better than the single-task model in sensitivity and area under the receiver operating characteristic curve. In the internal dataset, the accuracy, sensitivity, and specificity of fracture detection per patient or vertebral body were 0.929, 0.944, and 0.917 or 0.947, 0.628, and 0.977, respectively. In external validation, those of fracture detection per patient or vertebral body were 0.713, 0.979, and 0.447 or 0.828, 0.936, and 0.820, respectively. The success rates were 96 % and 94 % for vertebral level detection in internal and external validation, respectively. The multi-task-shared encoder was significantly better than the single-task encoder. Furthermore, both fracture and vertebral level detection was good in internal and external validation. Our deep learning model may help radiologists perform real-life medical examinations.
RESUMO
OBJECTIVE: Conventional computer-aided diagnosis using convolutional neural networks (CNN) has limitations in detecting sensitive changes and determining accurate decision boundaries in spectral and structural diseases such as scoliosis. We devised a new method to detect and diagnose adolescent idiopathic scoliosis in chest X-rays (CXRs) employing the latent space's discriminative ability in the generative adversarial network (GAN) and a simple multi-layer perceptron (MLP) to screen adolescent idiopathic scoliosis CXRs. MATERIALS AND METHODS: Our model was trained and validated in a two-step manner. First, we trained a GAN using CXRs with various scoliosis severities and utilized the trained network as a feature extractor using the GAN inversion method. Second, we classified each vector from the latent space using a simple MLP. RESULTS: The 2-layer MLP exhibited the best classification in the ablation study. With this model, the area under the receiver operating characteristic (AUROC) curves were 0.850 in the internal and 0.847 in the external datasets. Furthermore, when the sensitivity was fixed at 0.9, the model's specificity was 0.697 in the internal and 0.646 in the external datasets. CONCLUSION: We developed a classifier for Adolescent idiopathic scoliosis (AIS) through generative representation learning. Our model shows good AUROC under screening chest radiographs in both the internal and external datasets. Our model has learned the spectral severity of AIS, enabling it to generate normal images even when trained solely on scoliosis radiographs.
Assuntos
Cifose , Escoliose , Humanos , Adolescente , Escoliose/diagnóstico por imagem , Radiografia , Redes Neurais de Computação , Diagnóstico por Computador/métodosRESUMO
Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.
Assuntos
Inteligência Artificial , Radiologia , Humanos , Estudos Prospectivos , Radiologia/métodos , Aprendizado de Máquina SupervisionadoRESUMO
Flatfoot causes significant fatigue and pain while walking, and even asymptomatic flatfoot may increase the risk of metatarsal stress fracture during long-distance walking. While most studies have used physical examination or plantar footprints to diagnose flatfoot, a weight-bearing radiograph of the foot provides more objective data. However, data on the prevalence of flatfoot in Asian populations gathered in a nationwide cohort of a specific age group is lacking. We examined the prevalence of flatfoot among 19-year-old male Korean army recruits using a weight-bearing lateral radiograph and evaluated the correlation among flatfoot angles. A total of 560,141 19-year-old Korean males were examined at the regional Military Manpower Administration offices between April 2018 and April 2020. Weight-bearing lateral radiographs of the foot were obtained using an X-ray system while the subjects were standing on a table with their feet in a neutral position. Based on these radiographs, military orthopedic surgeons and radiologists measured the talo-first metatarsal angle (TMA) and calcaneal pitch angle (CPA) for flatfoot diagnosis. Mild flatfoot was diagnosed when the TMA ranged from 6 to 15° or the CPA was <17°, and moderate-to-severe flatfoot was diagnosed when the TMA was 15° or greater or the CPA was <10°. Pearson correlation coefficients and scatter plot matrix were used to evaluate the correlation among the flatfoot angles. Finally, we evaluated the relationship between body mass index (BMI) and flatfoot angles and compared the BMI in subjects with or without self-checked foot deformities including flatfoot and pes cavus. Of the 560,141 subjects, 16,102 (2.9%) were diagnosed as flatfoot, and 5265 (0.9%) were diagnosed with moderate-to-severe flatfoot. The coefficients between TMA and CPA ranged from 0.342 to 0.449 (all P valuesâ <â 0.001), and those between the 2 sides of TMA and CPA were 0.709 and 0.746 (all P valuesâ <â 0.001), respectively. BMI had a significant correlation with both TMA and CPA in subjects with flatfoot, and those with self-checked foot deformities had a significantly higher BMI than the group without foot deformities. The prevalence of total flatfoot and moderate-to-severe flatfoot in 19-year-old Korean males based on a weight-bearing lateral radiograph was 2.9% and 0.9%, respectively. The correlation coefficients between TMAs and CPAs showed a low degree of positive correlation. Higher BMI was associated with the likelihood of the presence of flatfoot.
Assuntos
Pé Chato , Deformidades do Pé , Adulto , Pé Chato/diagnóstico por imagem , Pé Chato/epidemiologia , Humanos , Masculino , Prevalência , República da Coreia/epidemiologia , Suporte de Carga , Adulto JovemRESUMO
Robust labeling for semantic segmentation in radiographs is labor-intensive. No study has evaluated flatfoot-related deformities using semantic segmentation with U-Net on weight-bearing lateral radiographs. Here, we evaluated the robustness, accuracy enhancement, and efficiency of automated measurements for flatfoot-related angles using semantic segmentation in an active learning manner. A total of 300 consecutive weight-bearing lateral radiographs of the foot were acquired. The first 100 radiographs were used as the test set, and the following 200 radiographs were used as the training and validation sets, respectively. An expert orthopedic surgeon manually labeled ground truths. U-Net was used for model training. The Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to evaluate the segmentation results. In addition, angle measurement errors with a minimum moment of inertia (MMI) and ellipsoidal fitting (EF) based on the segmentation results were compared between active learning and learning with a pooled dataset. The mean values of DSC, HD, MMI, and EF of the average of all bones were 0.967, 1.274 mm, 0.792°, and 1.147° in active learning, and 0.964, 1.292 mm, 0.828°, and 1.186° in learning with a pooled dataset, respectively. The mean DSC and HD were significantly better in active learning than in learning with a pooled dataset. Labeling of all bones required 0.82 min in active learning and 0.88 min in learning with a pooled dataset. The accuracy and angle errors generally converged in both learning. However, the accuracies based on DSC and HD were significantly better in active learning. Moreover, active learning took less time for labeling, suggesting that active learning could be an accurate and efficient learning strategy for developing flatfoot classifiers based on semantic segmentation.
Assuntos
Pé Chato , Ossos do Metatarso , Pé Chato/diagnóstico por imagem , Humanos , Processamento de Imagem Assistida por Computador , Ossos do Metatarso/diagnóstico por imagem , Semântica , Suporte de CargaRESUMO
Landmark detection in flatfoot radiographs is crucial in analyzing foot deformity. Here, we evaluated the accuracy and efficiency of the automated identification of flatfoot landmarks using a newly developed cascade convolutional neural network (CNN) algorithm, Flatfoot Landmarks AnnoTating Network (FlatNet). A total of 1200 consecutive weight-bearing lateral radiographs of the foot were acquired. The first 1050 radiographs were used as the training and tuning, and the following 150 radiographs were used as the test sets, respectively. An expert orthopedic surgeon (A) manually labeled ground truths for twenty-five anatomical landmarks. Two orthopedic surgeons (A and B, each with eight years of clinical experience) and a general physician (GP) independently identified the landmarks of the test sets using the same method. After two weeks, observers B and GP independently identified the landmarks once again using the developed deep learning CNN model (DLm). The X- and Y-coordinates and the mean absolute distance were evaluated. The average differences (mm) from the ground truth were 0.60 ± 0.57, 1.37 ± 1.28, and 1.05 ± 1.23 for the X-coordinate, and 0.46 ± 0.59, 0.97 ± 0.98, and 0.73 ± 0.90 for the Y-coordinate in DLm, B, and GP, respectively. The average differences (mm) from the ground truth were 0.84 ± 0.73, 1.90 ± 1.34, and 1.42 ± 1.40 for the absolute distance in DLm, B, and GP, respectively. Under the guidance of the DLm, the overall differences (mm) from the ground truth were enhanced to 0.87 ± 1.21, 0.69 ± 0.74, and 1.24 ± 1.31 for the X-coordinate, Y-coordinate, and absolute distance, respectively, for observer B. The differences were also enhanced to 0.74 ± 0.73, 0.57 ± 0.63, and 1.04 ± 0.85 for observer GP. The newly developed FlatNet exhibited better accuracy and reliability than the observers. Furthermore, under the FlatNet guidance, the accuracy and reliability of the human observers generally improved.
Assuntos
Pé Chato , Pé , Humanos , Redes Neurais de Computação , Reprodutibilidade dos Testes , Suporte de CargaRESUMO
INTRODUCTION: Be it as a nicotine replacement or a fashionable seduction for young people or casual smokers with or without nicotine additives - the popularity of e-cigarettes in Europe has increased during the past decade. In addition to the potential of long-term pulmonary damage, which is still largely unknown to date, there is a risk of battery explosion with specific injury patterns. Most users are unaware of the danger in their pockets. MATERIAL AND METHODS: Between February and July 2019, four patients were treated with burns from exploded e-cigarettes in the burn centre at Sana Hospital in Offenbach am Main (Germany). This article describes the cause and extent of the injury and its treatment. RESULTS: In all patients, the cause of the explosion was what is called "thermal runaway" (very rapid discharge of the battery). The average age of the patients, who were exclusively male, was 37 (25-50) years. The combustion depth ranged from grade I to deep grade IIb. The burnt body surface averaged 3â % (0.5-4.5â %) TBSA and affected the body regions that are typically in direct contact with the e-cigarette: thighs, genitals and hands. Conservative treatment was successful in one case and surgical treatment in two cases (two alloplastic covers, one meshed split-skin transplant). One patient discharged himself from hospital against medical advice after initial treatment. The average time in hospital for the three remaining patients was 15.6â days (6-17). CONCLUSION: Burns from an exploding e-cigarette represent a rare new entity. The force of the explosion of the battery body leads to injury patterns that require treatment in specialised centres with the entire spectrum of burn care. Mixed injuries with deep burns occur at the predilection sites due to thermal action, colliquative necrosis due to leaking electrolyte fluid and contamination by foreign bodies (metallic lithium, splinters of the destroyed housing) and require special initial measures. The extinction of fire caused by e-cigarettes also requires special measures. Proper handling of CE-certified devices is essential. Manipulation of the device in the event of defective functions or defective batteries is highly dangerous and should be strictly prohibited. General security requirements must be observed.
Assuntos
Queimaduras , Sistemas Eletrônicos de Liberação de Nicotina , Substâncias Explosivas , Abandono do Hábito de Fumar , Adolescente , Adulto , Queimaduras/etiologia , Queimaduras/cirurgia , Europa (Continente) , Alemanha , Humanos , Masculino , Pessoa de Meia-Idade , Dispositivos para o Abandono do Uso de TabacoRESUMO
BACKGROUND: The treatment of pediatric radial head fracture (RHF) is controversial, and the outcome is unpredictable. We aimed to evaluate the long term clinical and radiographic outcomes of patients with pediatric RHF. MATERIALS AND METHODS: 24 patients with pediatric RHFs operated between January 2004 and 2012 were included in this retrospective study. 17 patients had extra articular radial head (EARH) fractures and 7 had intraarticular radial head (IARH) fractures. The Mayo Elbow Performance Score (MEPS), Tibone and Stoltz classification, range of motion (ROM), and carrying angle (CA) were evaluated. The radial head diameter (RHD) and radial head height (RHH), neck shaft angle (NSA), and distance from the radial head to the radial tuberosity (RHRT) were measured and compared with the other side in simple anteroposterior views of elbow radiographs. RESULTS: At the last followup, the mean MEPS was 100 and 97.9 in groups EARH and IARH, respectively. There were no clinically and radiographically significant differences between the groups. The injured elbows showed smaller ROMs than the uninjured elbows in flexion, supination, and pronation with statistically significant differences. However, the injured elbows showed larger extension ranges than the uninjured elbows with a statistical significance (all P = 0.000). CA, RHD, and RHH were higher in the injured elbows than in the uninjured elbows with statistically significant differences (P = 0.006, 0.000, and 0.011) However, NSA and RHRT of both elbows were similar, with no statistically significant difference (P = 0.810 and 0.752). CONCLUSION: All patients with pediatric RHF were satisfied with the long term clinical results. The injured elbows showed restricted ROMs compared with the uninjured elbows; however, the extension range increased.
RESUMO
PURPOSE: This study is to investigate clinical and radiological results of staged treatment using a temporary external fixator in bicondylar tibial plateau fractures (TPFs) and to evaluate correlation between prognostic factors and postoperative clinical outcomes. MATERIALS AND METHODS: Twenty-four bicondylar TPF patients were selected. All patients were operated by a temporary external fixator first and then open reduction and internal fixation with dual plating. Clinical and radiological outcomes were evaluated. RESULTS: The mean American Knee Society score (AKSS) was 85.3. The mean Western Ontario and McMaster Universities Osteoarthritis index was 11.2. The mean range of motion (ROM) was 123.4°. The mean medial tibial plateau angle (mTPA) was 88.3°, and the mean proximal posterior tibial angle (PPTA) was 8.4°. Compared with the uninjured limb, the mean difference of mTPA was 1.5° and that of PPTA was 4.0°. The difference of PPTA and the AKSS demonstrated negative correlation (p=0.007). Patients with normal mTPA showed better ROM than those with abnormal mTPA (p=0.041). CONCLUSIONS: Staged treatment using a temporary external fixator in bicondylar TPFs showed good clinical and radiological outcomes. Surgeons should evaluate the reduction status intraoperatively by fluoroscopy and also refer to the uninjured limb radiologically.
RESUMO
PURPOSE: The purpose of this study is to compare the accuracy of the GNRB arthrometer (Genourob), Lachman test, and Telos device (GmbH) in acute anterior cruciate ligament (ACL) injuries and to evaluate the accuracy of each diagnostic tool according to the length of time from injury to examination. MATERIALS AND METHODS: From September 2015 to September 2016, 40 cases of complete ACL rupture were reviewed. We divided the time from injury to examination into three periods of 10 days each and analyzed the diagnostic tools according to the time frame. RESULTS: An analysis of the area under the curve (AUC) of a receiver operating characteristic curve showed that all diagnostic tools were fairly informative. The GNRB showed a higher AUC than other diagnostic tools. In 10 cases assessed within 10 days after injury, the GNRB showed statistically significant side-to-side difference in laxity (pï¼0.001), whereas the Telos test and Lachman test did not show significantly different laxity (p=0.541 and p=0.413, respectively). CONCLUSIONS: All diagnostic values of the GNRB were better than other diagnostic tools in acute ACL injuries. The GNRB was more effective in acute ACL injuries examined within 10 days of injury. The GNRB arthrometer can be a useful diagnostic tool for acute ACL injuries.
RESUMO
We compared the outcomes of nonoperative and operative treatments of triplane fractures. Thirty-three patients with triplane fractures were treated conservatively (n=19) or surgically (n=14). Bone union and postoperative complications were radiographically examined. The mean American Orthopedic Foot and Ankle Society scores were 100 (nonoperative group) and 98.1 (operative group) (P=0.304). The modified Weber protocol scores were excellent in both groups. One patient in each group showed a leg-length discrepancy of more than 10 mm at the last follow-up. According to our preliminary data, it appears that nonoperative treatment of triplane fracture may have comparable clinical and radiographic results to operative treatment. However, further studies are needed to corroborate our findings.
Assuntos
Fraturas do Tornozelo/cirurgia , Osso e Ossos/patologia , Desigualdade de Membros Inferiores/etiologia , Criança , Pré-Escolar , Estudos de Coortes , Feminino , Fixação de Fratura , Humanos , Masculino , Procedimentos Ortopédicos , Ortopedia , Período Pós-Operatório , Reprodutibilidade dos Testes , Resultado do TratamentoRESUMO
STUDY DESIGN: Retrospective review of prospectively collected data. OBJECTIVE: To determine the impact of L5 sacralization on fusion rates and clinical outcomes after single-level posterior lumbar interbody fusion (PLIF) surgery at the L4-L5 level. SUMMARY OF BACKGROUND DATA: L5 sacralization can produce greater stress concentration at the adjacent segment (L4-L5); therefore, L4-L5 PLIF surgery in patients with L5 sacralization may negatively affect fusion rate and be associated with poor clinical outcomes. However, no study has examined the impact of L5 sacralization on fusion rates and clinical outcomes of patients who undergo L4-L5 PLIF surgery. MATERIALS AND METHODS: Of 153 patients who underwent L4-L5 PLIF, data of 145 who met the study criteria were retrospectively reviewed. Among them, 31 patients had L5 sacralization (group A), whereas the remaining 114 patients did not (group B). The primary study endpoint was fusion rate evaluated using dynamic radiographs and computed tomographic scans. Secondary endpoints included (1) pain intensity in the lower back and radiating to the lower extremities on the visual analog scale; (2) clinical outcomes assessed using the Oswestry Disability Index and 12-item Short Form Health Survey; (3) surgical outcomes; and (4) complications. RESULTS: Fusion rate evaluated using dynamic radiographs and computed tomographic scans at 6 months after surgery did not differ significantly between patients with and without sacralization (P=0.70 and 0.81, respectively), whereas fusion rate at 1 year after surgery did (P=0.04 and 0.04, respectively). In particular, patients with type II or III L5 sacralization had significantly lower fusion rates than those with other types of or no L5 sacralization. Pain intensity, clinical and surgical outcomes, and complications did not differ significantly between groups. CONCLUSIONS: Patients with type II or III L5 sacralization may have worse fusion rates after L4-L5 PLIF surgery than those with type I or no sacralization.