Zobrazit v EDS

An overview of the performance of AI in fracture detection in lumbar and thoracic spine radiographs on a per vertebra basis

Uloženo v:
Podrobná bibliografie
Název: An overview of the performance of AI in fracture detection in lumbar and thoracic spine radiographs on a per vertebra basis
Autoři: J., Oppenheimer, S., Lüken, S., Geveshausen, B., Hamm, S. M., Niehues
Zdroj: Skeletal Radiol
Informace o vydavateli: Springer Science and Business Media LLC, 2024.
Rok vydání: 2024
Témata: Male, Adult, Aged, 80 and over, Lumbar Vertebrae, Middle Aged, Sensitivity and Specificity, Thoracic Vertebrae, 03 medical and health sciences, 0302 clinical medicine, Artificial Intelligence, Fractures, Compression, Humans, Spinal Fractures, Radiographic Image Interpretation, Computer-Assisted, Scientific Article, Female, Algorithms, Fractures, Compression/diagnostic imaging [MeSH], Algorithms [MeSH], Female [MeSH], Thoracic Vertebrae/injuries [MeSH], Computer-aided diagnosis, Aged, 80 and over [MeSH], Aged [MeSH], Adult [MeSH], Humans [MeSH], Lumbar Vertebrae/injuries [MeSH], Artificial intelligence, Retrospective Studies [MeSH], Middle Aged [MeSH], Radiographic Image Interpretation, Computer-Assisted/methods [MeSH], Trauma, Radiography, Artificial Intelligence [MeSH], Sensitivity and Specificity [MeSH], Thoracic Vertebrae/diagnostic imaging [MeSH], Male [MeSH], Lumbar Vertebrae/diagnostic imaging [MeSH], Spinal Fractures/diagnostic imaging [MeSH], Retrospective Studies, Aged
Popis: Purpose Subtle spinal compression fractures can easily be missed. AI may help in interpreting these images. We propose to test the performance of an FDA-approved algorithm for fracture detection in radiographs on a per vertebra basis, assessing performance based on grade of compression, presence of foreign material, severity of degenerative changes, and acuity of the fracture. Methods Thoracic and lumbar spine radiographs with inquiries for fracture were retrospectively collected and analyzed by the AI. The presence or absence of fracture was defined by the written report or cross-sectional imaging where available. Fractures were classified semi-quantitatively by the Genant classification, by acuity, by the presence of foreign material, and overall degree of degenerative change of the spine. The results of the AI were compared to the gold standard. Results A total of 512 exams were included, depicting 4114 vertebra with 495 fractures. Overall sensitivity was 63.2% for the lumbar spine, significantly higher than the thoracic spine with 50.6%. Specificity was 96.7 and 98.3% respectively. Sensitivity increased with fracture grade, without a significant difference between grade 2 and 3 compression fractures (lumbar spine: grade 1, 52.5%; grade 2, 72.3%; grade 3, 75.8%; thoracic spine: grade 1, 42.4%; grade 2, 60.0%; grade 3, 60.0%). The presence of foreign material and a high degree of degenerative changes reduced sensitivity. Conclusion Overall performance of the AI on a per vertebra basis was degraded in clinically relevant scenarios such as for low-grade compression fractures.
Druh dokumentu: Article
Other literature type
Jazyk: English
ISSN: 1432-2161
0364-2348
DOI: 10.1007/s00256-024-04626-2
Přístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/38413400
https://repository.publisso.de/resource/frl:6519511
Rights: CC BY
Přístupové číslo: edsair.doi.dedup.....0d9fa5c8e4247b30cf321ee2c0c828af
Databáze: OpenAIRE
Popis
Abstrakt:Purpose Subtle spinal compression fractures can easily be missed. AI may help in interpreting these images. We propose to test the performance of an FDA-approved algorithm for fracture detection in radiographs on a per vertebra basis, assessing performance based on grade of compression, presence of foreign material, severity of degenerative changes, and acuity of the fracture. Methods Thoracic and lumbar spine radiographs with inquiries for fracture were retrospectively collected and analyzed by the AI. The presence or absence of fracture was defined by the written report or cross-sectional imaging where available. Fractures were classified semi-quantitatively by the Genant classification, by acuity, by the presence of foreign material, and overall degree of degenerative change of the spine. The results of the AI were compared to the gold standard. Results A total of 512 exams were included, depicting 4114 vertebra with 495 fractures. Overall sensitivity was 63.2% for the lumbar spine, significantly higher than the thoracic spine with 50.6%. Specificity was 96.7 and 98.3% respectively. Sensitivity increased with fracture grade, without a significant difference between grade 2 and 3 compression fractures (lumbar spine: grade 1, 52.5%; grade 2, 72.3%; grade 3, 75.8%; thoracic spine: grade 1, 42.4%; grade 2, 60.0%; grade 3, 60.0%). The presence of foreign material and a high degree of degenerative changes reduced sensitivity. Conclusion Overall performance of the AI on a per vertebra basis was degraded in clinically relevant scenarios such as for low-grade compression fractures.
ISSN:14322161
03642348
DOI:10.1007/s00256-024-04626-2