The June 2012 Children’s orthopaedics Roundup. 360. looks at; open reduction for DDH; growing rod instrumentation for scoliosis; acute patellar dislocation; management of the relapsed clubfoot; clubfoot in Iran; laughing gas and fracture manipulation; vascularised periosteal fibular grafting for nonunion; slipped upper femoral epiphysis; intramedullary leg lengthening and
Introduction: The Ionising Radiations Medical Exposure Regulations Act 2000 has established diagnostic reference levels for radiological examinations, however at present there are no national guidelines available for orthopaedic trauma surgery. There may be a role for the introduction of diagnostic reference levels at a local level therefore we studied patient area dose and screening time for orthopaedic trauma operations performed in the Regional Trauma Centre in Northern Ireland. Methods: Retrospectively data was retrieved from written radiography records in the Royal Victoria Hospital, during the period of 1st January 2007 to 31st December 2007 for all orthopaedic trauma cases in which an image intensifier was used. The screening time, patient area dose (PAD), details of the operation, patient age, sex, month of the operation and grade of the operating surgeon (trainee or consultant), were recorded. Results: 1709 cases using image intensifier were reviewed. 137 cases were excluded due to incomplete data. 319 hips were screened for insertion of sliding hip screw, mean screening time was 0.51min with a mean PAD of 145cGycm2. 127 femoral nails were inserted with an average screening time of 1.84min and mean PAD of 310cGycm2. 166 tibias were screened for application of Ilizarov frame or insertion of tibial nail, average screening time was 3.00min with a mean PAD of 48cGycm2. 129 spinal cases were screened with an average screening time of 0.80mins and mean PAD of 37.9cGycm2. Consultants had lower screening times and mean PADs than trainees with 0.63min versus 1.01min and 65.8cGycm2 versus 70.9cGycm2. Conclusions: The average screening times and mean PADs compared favourably with local reference guides for image intensifier cases and with other published series. Every trauma unit should have local reference ranges for
Introduction: The Ionising Radiations Medical Exposure Regulations Act 2000 has established diagnostic reference levels for radiological examinations, however at present there are no national guidelines available for orthopaedic trauma surgery. There may be a role for the introduction of diagnostic reference levels at a local level therefore we studied patient area dose and screening time for orthopaedic trauma operations performed in the Regional Trauma Centre in Northern Ireland. Methods: Retrospectively data was retrieved from written radiography records in the Royal Victoria Hospital, during the period of 1st January 2007 to 31st December 2007 for all orthopaedic trauma cases in which an image intensifier was used. The screening time, patient area dose (PAD), details of the operation, patient age, sex, month of the operation and grade of the operating surgeon (trainee or consultant), were recorded. Results: 1709 cases using image intensifier were reviewed. 137 cases were excluded due to incomplete data. 319 hips were screened for insertion of sliding hip screw, mean screening time was 0.51min with a mean PAD of 145cGycm2. 127 femoral nails were inserted with an average screening time of 1.84min and mean PAD of 310 cGycm2. 166 tibias were screened for application of Ilizarov frame or insertion of tibial nail, average screening time was 3.00min with a mean PAD of 48cGycm2. 129 spinal cases were screened with an average screening time of 0.80mins and mean PAD of 37.9cGycm2. Consultants had lower screening times and mean PADs than trainees with 0.63min versus 1.01min and 65.8cGycm2 versus 70.9cGycm2. Conclusions: The average screening times and mean PADs compared favourably with local reference guides for image intensifier cases and with other published series. Every trauma unit should have local reference ranges for
Artificial intelligence (AI) is, in essence, the concept of ‘computer thinking’, encompassing methods that train computers to perform and learn from executing certain tasks, called machine learning, and methods to build intricate computer models that both learn and adapt, called complex neural networks. Computer vision is a function of AI by which machine learning and complex neural networks can be applied to enable computers to capture, analyze, and interpret information from clinical images and visual inputs. This annotation summarizes key considerations and future perspectives concerning computer vision, questioning the need for this technology (the ‘why’), the current applications (the ‘what’), and the approach to unlocking its full potential (the ‘how’). Cite this article:
The aim of this study was to evaluate the ability of a machine-learning algorithm to diagnose prosthetic loosening from preoperative radiographs and to investigate the inputs that might improve its performance. A group of 697 patients underwent a first-time revision of a total hip (THA) or total knee arthroplasty (TKA) at our institution between 2012 and 2018. Preoperative anteroposterior (AP) and lateral radiographs, and historical and comorbidity information were collected from their electronic records. Each patient was defined as having loose or fixed components based on the operation notes. We trained a series of convolutional neural network (CNN) models to predict a diagnosis of loosening at the time of surgery from the preoperative radiographs. We then added historical data about the patients to the best performing model to create a final model and tested it on an independent dataset.Aims
Methods
The diagnosis of developmental dysplasia of the hip (DDH) is challenging owing to extensive variation in paediatric pelvic anatomy. Artificial intelligence (AI) may represent an effective diagnostic tool for DDH. Here, we aimed to develop an anteroposterior pelvic radiograph deep learning system for diagnosing DDH in children and analyze the feasibility of its application. In total, 10,219 anteroposterior pelvic radiographs were retrospectively collected from April 2014 to December 2018. Clinicians labelled each radiograph using a uniform standard method. Radiographs were grouped according to age and into ‘dislocation’ (dislocation and subluxation) and ‘non-dislocation’ (normal cases and those with dysplasia of the acetabulum) groups based on clinical diagnosis. The deep learning system was trained and optimized using 9,081 radiographs; 1,138 test radiographs were then used to compare the diagnoses made by deep learning system and clinicians. The accuracy of the deep learning system was determined using a receiver operating characteristic curve, and the consistency of acetabular index measurements was evaluated using Bland-Altman plots.Aims
Methods
