Artificial Intelligence in Fracture Detection: A Systematic Review                     and Meta-Analysis

Kuo, Rachel; Harrison, Conrad; Curran, Terry-Ann; Jones, Benjamin E.; Freethy, Alexander; Cussons, David; Stewart, Max; Collins, Gary S.; Furniss, Dominic

doi:10.1148/radiol.211785

Cited by 101 publications

(44 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a recent meta-analysis by Kuo et al 37 studies with AI tools for fracture detection in radiographs were analyzed, reaching a pooled sensitivity of up to 92% and a sensitivity of 91%. However, many of these algorithms were only for one specific anatomic region [ 13 ]. For distal radial fractures, sensitivities of 86% and 94% were reached [ 14 , 15 ] while AI was able to detect hip fractures with up to 100% sensitivity and 99% specificity [ 16 ].…”

Section: Discussionmentioning

confidence: 99%

A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow

Oppenheimer

Lüken

Hamm

et al. 2023

Life

View full text Add to dashboard Cite

Gleamer BoneView© is a commercially available AI algorithm for fracture detection in radiographs. We aim to test if the algorithm can assist in better sensitivity and specificity for fracture detection by residents with prospective integration into clinical workflow. Radiographs with inquiry for fracture initially reviewed by two residents were randomly assigned and included. A preliminary diagnosis of a possible fracture was made. Thereafter, the AI decision on presence and location of possible fractures was shown and changes to diagnosis could be made. Final diagnosis of fracture was made by a board-certified radiologist with over eight years of experience, or if available, cross-sectional imaging. Sensitivity and specificity of the human report, AI diagnosis, and assisted report were calculated in comparison to the final expert diagnosis. 1163 exams in 735 patients were included, with a total of 367 fractures (31.56%). Pure human sensitivity was 84.74%, and AI sensitivity was 86.92%. Thirty-five changes were made after showing AI results, 33 of which resulted in the correct diagnosis, resulting in 25 additionally found fractures. This resulted in a sensitivity of 91.28% for the assisted report. Specificity was 97.11, 84.67, and 97.36%, respectively. AI assistance showed an increase in sensitivity for both residents, without a loss of specificity.

show abstract

Section: Discussionmentioning

confidence: 99%

A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow

Oppenheimer

Lüken

Hamm

et al. 2023

Life

View full text Add to dashboard Cite

show abstract

“…A recent meta-analysis of artificial intelligence algorithms for detecting fractures on imaging reported a sensitivity of 89% and a specificity of 80% in studies with adequate external validation cohorts and low risk of bias. 11 Another meta-analysis of artificial intelligence algorithms for classifying abnormal versus normal chest radiographs found a sensitivity and specificity of 87% and 89%, respectively 12 ; however, this also included studies without external validation, which will likely boost the accuracy reported in the meta-analysis. These studies also did not require a diagnosis to be provided, just a binary distinction of normality versus abnormality, unlike our study.…”

Section: Discussionmentioning

confidence: 99%

“…The artificial intelligence candidate’s performance is representative of similar artificial intelligence models reported in the wider literature. A recent meta-analysis of artificial intelligence algorithms for detecting fractures on imaging reported a sensitivity of 89% and a specificity of 80% in studies with adequate external validation cohorts and low risk of bias 11. Another meta-analysis of artificial intelligence algorithms for classifying abnormal versus normal chest radiographs found a sensitivity and specificity of 87% and 89%, respectively12; however, this also included studies without external validation, which will likely boost the accuracy reported in the meta-analysis.…”

Section: Discussionmentioning

confidence: 99%

Can artificial intelligence pass the Fellowship of the Royal College of Radiologists examination? Multi-reader diagnostic accuracy study

Shelmerdine

Martı́n

Shirodkar

et al. 2022

BMJ

View full text Add to dashboard Cite

Objective To determine whether an artificial intelligence candidate could pass the rapid (radiographic) reporting component of the Fellowship of the Royal College of Radiologists (FRCR) examination. Design Prospective multi-reader diagnostic accuracy study. Setting United Kingdom. Participants One artificial intelligence candidate (Smarturgences, Milvue) and 26 radiologists who had passed the FRCR examination in the preceding 12 months. Main outcome measures Accuracy and pass rate of the artificial intelligence compared with radiologists across 10 mock FRCR rapid reporting examinations (each examination containing 30 radiographs, requiring 90% accuracy rate to pass). Results When non-interpretable images were excluded from the analysis, the artificial intelligence candidate achieved an average overall accuracy of 79.5% (95% confidence interval 74.1% to 84.3%) and passed two of 10 mock FRCR examinations. The average radiologist achieved an average accuracy of 84.8% (76.1-91.9%) and passed four of 10 mock examinations. The sensitivity for the artificial intelligence was 83.6% (95% confidence interval 76.2% to 89.4%) and the specificity was 75.2% (66.7% to 82.5%), compared with summary estimates across all radiologists of 84.1% (81.0% to 87.0%) and 87.3% (85.0% to 89.3%). Across 148/300 radiographs that were correctly interpreted by >90% of radiologists, the artificial intelligence candidate was incorrect in 14/148 (9%). In 20/300 radiographs that most (>50%) radiologists interpreted incorrectly, the artificial intelligence candidate was correct in 10/20 (50%). Most imaging pitfalls related to interpretation of musculoskeletal rather than chest radiographs. Conclusions When special dispensation for the artificial intelligence candidate was provided (that is, exclusion of non-interpretable images), the artificial intelligence candidate was able to pass two of 10 mock examinations. Potential exists for the artificial intelligence candidate to improve its radiographic interpretation skills by focusing on musculoskeletal cases and learning to interpret radiographs of the axial skeleton and abdomen that are currently considered “non-interpretable.”

show abstract

“…Furthermore, even if radiologists generally interpret patient radiographs, orthopaedic surgeons make the final decision about performing CT based on the radiologists’ interpretations. Also, Kuo et al reported that orthopaedic surgeons and radiologists had very similar ability to diagnose fractures on radiographs 26 ; thus, the demonstrated accuracy of AI that far surpasses that of orthopaedic surgeons appears valuable.…”

Section: Discussionmentioning

confidence: 99%

Detection of Sacral Fractures on Radiographs Using Artificial Intelligence

et al. 2022

View full text Add to dashboard Cite

Background: Sacral fractures are often difficult to diagnose on radiographs. Computed tomography (CT) and magnetic resonance imaging (MRI) can improve the detection rate but cannot always be performed. The accuracy of artificial intelligence (AI) in detecting orthopaedic fractures is now comparable with that of orthopaedic specialists. However, the ability of AI to detect sacral fractures has not been investigated, to our knowledge. We hypothesized that the ability to detect sacral fractures on radiographs could be improved by using AI, and aimed to develop an AI model to detect sacral fractures accurately on radiographs with better accuracy than that of orthopaedic surgeons. Methods: Subjects were patients with suspected pelvic fractures for whom radiographs and CT scans had been obtained. The radiographs were labeled according to sacral fracture status based on CT results. The data set was divided into a training set (2,038 images) and a test set (200 images). Eight convolutional neural network (CNN) models were trained using the training set. Post-trained models were used to evaluate their discrimination ability. The detection ability of 4 experienced orthopaedic surgeons was also measured using the same test set. The results of fracture assessment by the orthopaedic surgeons were compared with those of the 3 CNNs with the greatest area under the receiver operating characteristic curve. Results: Among the 8 trained models, the highest areas under the curve were for InceptionV3 (0.989), Xception (0.987), and Inception ResNetV2 (0.984). The detection rate was significantly higher for these 3 CNNs than for the orthopaedic surgeons. Conclusions: By enhancing the processing of probabilistic tasks and the communication of their results, AI may be better able to detect sacral fractures than orthopaedic surgeons. Level of Evidence: Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.

show abstract

Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis

Cited by 101 publications

References 63 publications

A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow

A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow

Can artificial intelligence pass the Fellowship of the Royal College of Radiologists examination? Multi-reader diagnostic accuracy study

Detection of Sacral Fractures on Radiographs Using Artificial Intelligence

Contact Info

Product

Resources

About