Adult distal radius fractures classification systems: essential clinical knowledge or abstract memory testing?

Shehovych, A; Salar, O; Meyer, Cer; Ford, David

doi:10.1308/rcsann.2016.0237

Cited by 36 publications

(35 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These findings shed light on the possibility of the clinical use of DCNN in orthopedics. However, the actual outcome of detecting a fracture still remains unknown, because most of the available fracture classifications lack prognostic value 31 .…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence for the detection of vertebral fractures on plain spinal radiography

Murata

Endo

Aihara

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Vertebral fractures (VFs) cause serious problems, such as substantial functional loss and a high mortality rate, and a delayed diagnosis may further worsen the prognosis. Plain thoracolumbar radiography (PTLR) is an essential method for the evaluation of VFs. Therefore, minimizing the diagnostic errors of VFs on PTLR is crucial. Image identification based on a deep convolutional neural network (DCNN) has been recognized to be potentially effective as a diagnostic strategy; however, the accuracy for detecting VFs has not been fully investigated. A DCNN was trained with PTLR images of 300 patients (150 patients with and 150 without VFs). The accuracy, sensitivity, and specificity of diagnosis of the model were calculated and compared with those of orthopedic residents, orthopedic surgeons, and spine surgeons. The DCNN achieved accuracy, sensitivity, and specificity rates of 86.0% [95% confidence interval (CI) 82.0–90.0%], 84.7% (95% CI 78.8–90.5%), and 87.3% (95% CI 81.9–92.7%), respectively. Both the accuracy and sensitivity of the model were suggested to be noninferior to those of orthopedic surgeons. The DCNN can assist clinicians in the early identification of VFs and in managing patients, to prevent further invasive interventions and a decreased quality of life.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial intelligence for the detection of vertebral fractures on plain spinal radiography

Murata

Endo

Aihara

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…As many of our fracture classifications lack prognostic value (Shehovych et al. 2016 ), often with questionable inter-observer reliability (Audigé et al. 2005 ), the option of aiding the classification using a computer algorithm is of great interest.…”

Section: Methodsmentioning

confidence: 99%

“… 2011 , Shehovych et al. 2016 ). Aiding image interpretation using computers is therefore highly interesting from a clinical perspective.…”

mentioning

confidence: 99%

Artificial intelligence for analyzing orthopedic trauma radiographs

et al. 2017

View full text Add to dashboard Cite

Background and purpose — Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this study we sought to determine the feasibility of using deep learning for skeletal radiographs.Methods — We extracted 256,000 wrist, hand, and ankle radiographs from Danderyd’s Hospital and identified 4 classes: fracture, laterality, body part, and exam view. We then selected 5 openly available deep learning networks that were adapted for these images. The most accurate network was benchmarked against a gold standard for fractures. We furthermore compared the network’s performance with 2 senior orthopedic surgeons who reviewed images at the same resolution as the network.Results — All networks exhibited an accuracy of at least 90% when identifying laterality, body part, and exam view. The final accuracy for fractures was estimated at 83% for the best performing network. The network performed similarly to senior orthopedic surgeons when presented with images at the same resolution as the network. The 2 reviewer Cohen’s kappa under these conditions was 0.76.Interpretation — This study supports the use for orthopedic radiographs of artificial intelligence, which can perform at a human level. While current implementation lacks important features that surgeons require, e.g. risk of dislocation, classifications, measurements, and combining multiple exam views, these problems have technical solutions that are waiting to be implemented for orthopedics.

show abstract

“…Many studies [5][6][7][8] have compared the various classification systems used to assess distal radius fractures and assessed the validity and reliability among them. Our study focused on the accuracy of diagnosis of each type of Fernandez classification fracture, which is based on mechanism of injury 9 , according to the type of imaging study used.…”

Section: Discussionmentioning

confidence: 99%

A Comparison of Intra-Observer and Inter-Observer Reliability of Plain Radiographs, Standard Computed Tomography Scans and Mobile Computed Tomography Scans in the Assessment of Distal Radius Fractures: A Cadaveric Study

Suwannaphisit

Yoykaew

Suwanraksa

et al. 2019

J Health Sci Med Res

View full text Add to dashboard Cite

Objective: Diagnosis of a distal end radius fracture relies on various imaging studies. However, the relative usefulness of these studies is still a matter of some controversy. The aim of this study was to compare the intra-observer and inter-observer reliability of plain radiographs, standard computed tomography (CT) scans and mobile CT scans in the assessment of distal radius fractures as categorized by the Fernandez classification method. The secondary objective was to compare the dosages of radiation between the different imaging modalities. Material and Methods: Sixteen fresh cadaveric wrist bones were used in this experimental study. The desired fractures were created in the bones to mimic Fernandez types I-V fractures and plain radiographs were taken in 4 views. Standard CT and mobile CT scans were also taken with the fractured bones in the same four positions. Interobserver reliability was assessed using Kappa statistics to determine the diagnostic consistency among the nine observers. Inter-observer agreement was assessed based on the Fernandez classification system diagnoses. Results: Overall, the inter-observer agreement was substantial for the Fernandez classifications (Kappa range 0.636 0.727) in all types of imaging. For intra-observer agreement, the analysis found higher agreement for both standard CT scans and mobile CT scans. The standard CT images imparted a higher average dose of radiation than both the mobile CT scans and the plain radiographs.Conclusion: The mobile CT scan can provide an alternative imaging method for precise diagnosis of distal end radius fractures, with the additional benefits of mobility and lower radiation exposure.

show abstract

Adult distal radius fractures classification systems: essential clinical knowledge or abstract memory testing?

Cited by 36 publications

References 32 publications

Artificial intelligence for the detection of vertebral fractures on plain spinal radiography

Artificial intelligence for the detection of vertebral fractures on plain spinal radiography

Artificial intelligence for analyzing orthopedic trauma radiographs

A Comparison of Intra-Observer and Inter-Observer Reliability of Plain Radiographs, Standard Computed Tomography Scans and Mobile Computed Tomography Scans in the Assessment of Distal Radius Fractures: A Cadaveric Study

Contact Info

Product

Resources

About