دورية أكاديمية
Artificial intelligence-based detection of paediatric appendicular skeletal fractures: performance and limitations for common fracture types and locations.
العنوان: | Artificial intelligence-based detection of paediatric appendicular skeletal fractures: performance and limitations for common fracture types and locations. |
---|---|
المؤلفون: | Altmann-Schneider I; Department of Diagnostic Imaging, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland. i.altmann-schneider@hotmail.com.; Paediatric Emergency Department, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland. i.altmann-schneider@hotmail.com., Kellenberger CJ; Department of Diagnostic Imaging, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland.; Paediatric Emergency Department, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland., Pistorius SM; Department of Diagnostic Imaging, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland.; Paediatric Emergency Department, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland., Saladin C; Department of Diagnostic Imaging, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland.; Paediatric Emergency Department, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland., Schäfer D; Children's Research Centre, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland., Arslan N; Children's Research Centre, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland., Fischer HL; Children's Research Centre, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland., Seiler M; Paediatric Emergency Department, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland.; Children's Research Centre, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland. |
المصدر: | Pediatric radiology [Pediatr Radiol] 2024 Jan; Vol. 54 (1), pp. 136-145. Date of Electronic Publication: 2023 Dec 15. |
نوع المنشور: | Journal Article; Research Support, Non-U.S. Gov't |
اللغة: | English |
بيانات الدورية: | Publisher: Springer-Verlag Country of Publication: Germany NLM ID: 0365332 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1432-1998 (Electronic) Linking ISSN: 03010449 NLM ISO Abbreviation: Pediatr Radiol Subsets: MEDLINE |
أسماء مطبوعة: | Original Publication: Berlin, New York, Springer-Verlag. |
مواضيع طبية MeSH: | Radius Fractures*/diagnostic imaging , Ulna Fractures*/diagnostic imaging , Joint Dislocations* , Salter-Harris Fractures*, Humans ; Child ; Infant, Newborn ; Infant ; Child, Preschool ; Adolescent ; Artificial Intelligence ; Retrospective Studies ; Radiography |
مستخلص: | Background: Research into artificial intelligence (AI)-based fracture detection in children is scarce and has disregarded the detection of indirect fracture signs and dislocations. Objective: To assess the diagnostic accuracy of an existing AI-tool for the detection of fractures, indirect fracture signs, and dislocations. Materials and Methods: An AI software, BoneView (Gleamer, Paris, France), was assessed for diagnostic accuracy of fracture detection using paediatric radiology consensus diagnoses as reference. Radiographs from a single emergency department were enrolled retrospectively going back from December 2021, limited to 1,000 radiographs per body part. Enrolment criteria were as follows: suspected fractures of the forearm, lower leg, or elbow; age 0-18 years; and radiographs in at least two projections. Results: Lower leg radiographs showed 607 fractures. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were high (87.5%, 87.5%, 98.3%, 98.3%, respectively). Detection rate was low for toddler's fractures, trampoline fractures, and proximal tibial Salter-Harris-II fractures. Forearm radiographs showed 1,137 fractures. Sensitivity, specificity, PPV, and NPV were high (92.9%, 98.1%, 98.4%, 91.7%, respectively). Radial and ulnar bowing fractures were not reliably detected (one out of 11 radial bowing fractures and zero out of seven ulnar bowing fractures were correctly detected). Detection rate was low for styloid process avulsions, proximal radial buckle, and complete olecranon fractures. Elbow radiographs showed 517 fractures. Sensitivity and NPV were moderate (80.5%, 84.7%, respectively). Specificity and PPV were high (94.9%, 93.3%, respectively). For joint effusion, sensitivity, specificity, PPV, and NPV were moderate (85.1%, 85.7%, 89.5%, 80%, respectively). For elbow dislocations, sensitivity and PPV were low (65.8%, 50%, respectively). Specificity and NPV were high (97.7%, 98.8%, respectively). Conclusions: The diagnostic performance of BoneView is promising for forearm and lower leg fractures. However, improvement is mandatory before clinicians can rely solely on AI-based paediatric fracture detection using this software. (© 2023. The Author(s).) |
References: | Emerg Radiol. 2008 Nov;15(6):391-8. (PMID: 18506493) Skeletal Radiol. 2022 Nov;51(11):2129-2139. (PMID: 35522332) Pediatr Radiol. 2022 Oct;52(11):2215-2226. (PMID: 36169667) Pediatr Radiol. 2023 Jul;53(8):1675-1684. (PMID: 36877239) Acta Orthop. 2017 Apr;88(2):123-128. (PMID: 27882802) Pediatr Radiol. 2022 Oct;52(11):2149-2158. (PMID: 34272573) J Pediatr Orthop. 2020 Nov/Dec;40(10):e916-e921. (PMID: 33045157) Insights Imaging. 2022 Jun 3;13(1):94. (PMID: 35657439) Acta radiol. 1954 Sep;42(3):205-10. (PMID: 13206822) JBJS Rev. 2022 Oct 24;10(10):. (PMID: 36326720) AJR Am J Roentgenol. 1998 Jul;171(1):243-5. (PMID: 9648797) Diagn Interv Imaging. 2022 Mar;103(3):151-159. (PMID: 34810137) AJR Am J Roentgenol. 2018 Dec;211(6):1361-1368. (PMID: 30300006) AJR Am J Roentgenol. 1986 Jan;146(1):83-5. (PMID: 3484416) Comput Biol Med. 2016 Nov 1;78:120-125. (PMID: 27684324) Invest Radiol. 2020 Feb;55(2):101-110. (PMID: 31725064) AJR Am J Roentgenol. 1977 Jun;128(6):981-4. (PMID: 414566) |
فهرسة مساهمة: | Keywords: Appendicular skeleton; Artificial intelligence; Fracture; Paediatric; Radiograph |
تواريخ الأحداث: | Date Created: 20231215 Date Completed: 20240110 Latest Revision: 20240321 |
رمز التحديث: | 20240322 |
مُعرف محوري في PubMed: | PMC10776701 |
DOI: | 10.1007/s00247-023-05822-3 |
PMID: | 38099929 |
قاعدة البيانات: | MEDLINE |
تدمد: | 1432-1998 |
---|---|
DOI: | 10.1007/s00247-023-05822-3 |