Triplane ankle fracture patterns in paediatric patients.

Aims: Triplane ankle fractures are complex injuries typically occurring in children aged between 12 and 15 years. Classic teaching that closure of the physis dictates the overall fracture pattern, based on studies in the 1960s, has not been challenged. The aim of this paper is to analyze whether these injuries correlate with the advancing closure of the physis with age. Methods: A fracture mapping study was performed in 83 paediatric patients with a triplane ankle fracture treated in three trauma centres between January 2010 and June 2020. Patients aged younger than 18 years who had CT scans available were included. An independent Paediatric Orthopaedic Trauma Surgeon assessed all CT scans and classified the injuries as n-part triplane fractures. Qualitative analysis of the fracture pattern was performed using the modified Cole fracture mapping technique. The maps were assessed for both patterns and correlation with the closing of the physis until consensus was reached by a panel of six surgeons. Results: Fracture map grouped by age demonstrates that, regardless of age (even at the extremes of the spectrum), the fracture lines consolidate in a characteristic Y-pattern, and no shift with closure of the physis was observed. A second fracture map with two years added to female age also did not show a shift. The fracture map, grouped by both age and sex, shows a Y-pattern in all different groups. The fracture lines appear to occur between the anterior and posterior inferior tibiofibular ligaments, and the medially fused physis or deltoid ligament. Conclusion: This fracture mapping study reveals that triplane ankle fractures have a characteristic Y-pattern, and acknowledges the weakness created by the physis, however it also challenges classic teaching that the specific fracture pattern at the level of the joint of these injuries relies on advancing closure of the physis with age. Instead, this study observes the importance of ligament attachment in the fracture patterns of these injuries.

Artificial intelligence fracture recognition on computed tomography: review of literature and recommendations.

PURPOSE: The use of computed tomography (CT) in fractures is time consuming, challenging and suffers from poor inter-surgeon reliability. Convolutional neural networks (CNNs), a subset of artificial intelligence (AI), may overcome shortcomings and reduce clinical burdens to detect and classify fractures. The aim of this review was to summarize literature on CNNs for the detection and classification of fractures on CT scans, focusing on its accuracy and to evaluate the beneficial role in daily practice. METHODS: Literature search was performed according to the PRISMA statement, and Embase, Medline ALL, Web of Science Core Collection, Cochrane Central Register of Controlled Trials and Google Scholar databases were searched. Studies were eligible when the use of AI for the detection of fractures on CT scans was described. Quality assessment was done with a modified version of the methodologic index for nonrandomized studies (MINORS), with a seven-item checklist. Performance of AI was defined as accuracy, F1-score and area under the curve (AUC). RESULTS: Of the 1140 identified studies, 17 were included. Accuracy ranged from 69 to 99%, the F1-score ranged from 0.35 to 0.94 and the AUC, ranging from 0.77 to 0.95. Based on ten studies, CNN showed a similar or improved diagnostic accuracy in addition to clinical evaluation only. CONCLUSIONS: CNNs are applicable for the detection and classification fractures on CT scans. This can improve automated and clinician-aided diagnostics. Further research should focus on the additional value of CNN used for CT scans in daily clinics.

Development and external validation of automated detection, classification, and localization of ankle fractures: inside the black box of a convolutional neural network (CNN).

PURPOSE: Convolutional neural networks (CNNs) are increasingly being developed for automated fracture detection in orthopaedic trauma surgery. Studies to date, however, are limited to providing classification based on the entire image-and only produce heatmaps for approximate fracture localization instead of delineating exact fracture morphology. Therefore, we aimed to answer (1) what is the performance of a CNN that detects, classifies, localizes, and segments an ankle fracture, and (2) would this be externally valid? METHODS: The training set included 326 isolated fibula fractures and 423 non-fracture radiographs. The Detectron2 implementation of the Mask R-CNN was trained with labelled and annotated radiographs. The internal validation (or 'test set') and external validation sets consisted of 300 and 334 radiographs, respectively. Consensus agreement between three experienced fellowship-trained trauma surgeons was defined as the ground truth label. Diagnostic accuracy and area under the receiver operator characteristic curve (AUC) were used to assess classification performance. The Intersection over Union (IoU) was used to quantify accuracy of the segmentation predictions by the CNN, where a value of 0.5 is generally considered an adequate segmentation. RESULTS: The final CNN was able to classify fibula fractures according to four classes (Danis-Weber A, B, C and No Fracture) with AUC values ranging from 0.93 to 0.99. Diagnostic accuracy was 89% on the test set with average sensitivity of 89% and specificity of 96%. External validity was 89-90% accurate on a set of radiographs from a different hospital. Accuracies/AUCs observed were 100/0.99 for the 'No Fracture' class, 92/0.99 for 'Weber B', 88/0.93 for 'Weber C', and 76/0.97 for 'Weber A'. For the fracture bounding box prediction by the CNN, a mean IoU of 0.65 (SD ± 0.16) was observed. The fracture segmentation predictions by the CNN resulted in a mean IoU of 0.47 (SD ± 0.17). CONCLUSIONS: This study presents a look into the 'black box' of CNNs and represents the first automated delineation (segmentation) of fracture lines on (ankle) radiographs. The AUC values presented in this paper indicate good discriminatory capability of the CNN and substantiate further study of CNNs in detecting and classifying ankle fractures. LEVEL OF EVIDENCE: II, Diagnostic imaging study.

Artificial intelligence and computer vision in orthopaedic trauma : the why, what, and how.

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: Bone Joint J 2022;104-B(8):911-914.

CNN Attention Guidance for Improved Orthopedics Radiographic Fracture Classification.

Convolutional neural networks (CNNs) have gained significant popularity in orthopedic imaging in recent years due to their ability to solve fracture classification problems. A common criticism of CNNs is their opaque learning and reasoning process, making it difficult to trust machine diagnosis and the subsequent adoption of such algorithms in clinical setting. This is especially true when the CNN is trained with limited amount of medical data, which is a common issue as curating sufficiently large amount of annotated medical imaging data is a long and costly process. While interest has been devoted to explaining CNN learnt knowledge by visualizing network attention, the utilization of the visualized attention to improve network learning has been rarely investigated. This paper explores the effectiveness of regularizing CNN network with human-provided attention guidance on where in the image the network should look for answering clues. On two orthopedics radiographic fracture classification datasets, through extensive experiments we demonstrate that explicit human-guided attention indeed can direct correct network attention and consequently significantly improve classification performance. The development code for the proposed attention guidance is publicly available on https://github.com/zhibinliao89/fracture_attention_guidance.

3D virtual pre-operative planning may reduce the incidence of dorsal screw penetration in volar plating of intra-articular distal radius fractures.

PURPOSE: To evaluate the effect of three-dimensional virtual pre-operative planning (3DVP) on the incidence of dorsal screw penetration after volar plating of distal radius fractures. METHODS: A cross-sectional diagnostic imaging study was performed. Twenty out of 50 patients were randomly selected from our index prospective cohort (IPC): a prior study evaluating dorsal tangential views (DTVs) in reducing dorsal screw penetration in internal fixation of intra-articular distal radius fractures using post-operative CT scans to quantify screw protrusion. Pre-operative CTs from this cohort were now used for 3DVP by three experienced orthopaedic trauma surgeons (supplementary video). 3DVP was compared with the corresponding post-operative CT for assessing screw lengths and incidence of dorsal penetration. The Wilcoxon Signed Ranks test was used to compare screw lengths and the Fishers' exact for incidence of penetration. RESULTS: Three surgeons performed 3DVP for 20 distal radius fractures and virtually applied 60 volar plates and 273 screws. Median screw length was shorter in the 3DVP when compared to IPC: 18 mm (range, 12-22) versus 20 mm (range, 14-26) (p < 0.001). The number of penetrating screws was 5% (13/273 screws) in the 3DVP group compared to 11% (10/91 screws) in the IPC (p = 0.047). Corresponding to a reduction in incidence of at least one dorsally penetrating screw in 40% of patients in the IPC group, to 18% in the 3DVP group (p = 0.069). CONCLUSION: Three-Dimensional Virtual Pre-Operative Planning (3DVP) may reduce the incidence of dorsally penetrating screws in patients treated with volar plating for intra-articular distal radius fractures. LEVEL OF EVIDENCE: II, diagnostic imaging study.

An increasing number of convolutional neural networks for fracture recognition and classification in orthopaedics : are these externally validated and ready for clinical application?

AIMS: The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs? METHODS: The PubMed and Embase databases were systematically searched from January 2010 to October 2020 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. The type of EV, characteristics of the external dataset, and diagnostic performance characteristics on the IV and EV datasets were collected and compared. Quality assessment was conducted using a seven-item checklist based on a modified Methodologic Index for NOn-Randomized Studies instrument (MINORS). RESULTS: Out of 1,349 studies, 36 reported development of a CNN for fracture detection and/or classification. Of these, only four (11%) reported a form of EV. One study used temporal EV, one conducted both temporal and geographical EV, and two used geographical EV. When comparing the CNN's performance on the IV set versus the EV set, the following were found: AUCs of 0.967 (IV) versus 0.975 (EV), 0.976 (IV) versus 0.985 to 0.992 (EV), 0.93 to 0.96 (IV) versus 0.80 to 0.89 (EV), and F1-scores of 0.856 to 0.863 (IV) versus 0.757 to 0.840 (EV). CONCLUSION: The number of externally validated CNNs in orthopaedic trauma for fracture recognition is still scarce. This greatly limits the potential for transfer of these CNNs from the developing institute to another hospital to achieve similar diagnostic performance. We recommend the use of geographical EV and statements such as the Consolidated Standards of Reporting Trials-Artificial Intelligence (CONSORT-AI), the Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence (SPIRIT-AI) and the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis-Machine Learning (TRIPOD-ML) to critically appraise performance of CNNs and improve methodological rigor, quality of future models, and facilitate eventual implementation in clinical practice. Cite this article: Bone Jt Open 2021;2(10):879-885.

Presenting artificial intelligence, deep learning, and machine learning studies to clinicians and healthcare stakeholders: an introductory reference with a guideline and a Clinical AI Research (CAIR) checklist proposal.

Background and purpose - Artificial intelligence (AI), deep learning (DL), and machine learning (ML) have become common research fields in orthopedics and medicine in general. Engineers perform much of the work. While they gear the results towards healthcare professionals, the difference in competencies and goals creates challenges for collaboration and knowledge exchange. We aim to provide clinicians with a context and understanding of AI research by facilitating communication between creators, researchers, clinicians, and readers of medical AI and ML research.Methods and results - We present the common tasks, considerations, and pitfalls (both methodological and ethical) that clinicians will encounter in AI research. We discuss the following topics: labeling, missing data, training, testing, and overfitting. Common performance and outcome measures for various AI and ML tasks are presented, including accuracy, precision, recall, F1 score, Dice score, the area under the curve, and ROC curves. We also discuss ethical considerations in terms of privacy, fairness, autonomy, safety, responsibility, and liability regarding data collecting or sharing.Interpretation - We have developed guidelines for reporting medical AI research to clinicians in the run-up to a broader consensus process. The proposed guidelines consist of a Clinical Artificial Intelligence Research (CAIR) checklist and specific performance metrics guidelines to present and evaluate research using AI components. Researchers, engineers, clinicians, and other stakeholders can use these proposal guidelines and the CAIR checklist to read, present, and evaluate AI research geared towards a healthcare setting.