Beurteilung der Sakroiliitis mittels künstlicher Intelligenz – Fortschritte und Limitationen

Zusammenfassung

Die Sakroiliitis ist eine entzündliche Erkrankung des Sakroiliakalgelenks, die durch Faktoren wie Infektionen, Traumata und Autoimmunerkrankungen ausgelöst werden kann. Sie verursacht Schmerzen und Steifheit im unteren Rücken, weshalb eine frühzeitige Diagnose für eine optimale Behandlung entscheidend ist. Die Diagnose ist anspruchsvoll und erfordert klinische Beurteilung, Labortests und bildgebende Verfahren wie Röntgen, MRT oder CT. In den letzten Jahren hat sich die künstliche Intelligenz (KI) als vielversprechendes Instrument für die Beurteilung von Veränderungen im Rahmen der Sakroiliitis herausgestellt. KI-Algorithmen analysieren verschiedene bildgebende Verfahren, um strukturelle Veränderungen und Entzündungen im Sakroiliakalgelenk zu erkennen, zu quantifizieren und einzuordnen. Die Anwendung von KI kann die Diagnosegenauigkeit und Effizienz des Radiologen bzw. des Rheumatologen bei der Beurteilung von Sakroiliitis durch bildgebende Verfahren verbessern. KI-Algorithmen können strukturelle Veränderungen und Entzündungen im Sakroiliakalgelenk quantifizieren und Vorhersagemodelle für den Krankheitsverlauf erstellen. Herausforderungen wie der Bedarf an qualitativ hochwertigen Daten und die Minimierung von Verzerrungen und Fehlern in den Daten und Algorithmen müssen jedoch bewältigt werden. Weitere Studien sind erforderlich, um das volle Potenzial der KI bei der Beurteilung von Sakroiliitis auszuschöpfen. Der Einsatz von KI kann jedoch die Ergebnisse für Patienten verbessern, indem er eine frühzeitige Diagnose und Behandlung ermöglicht.

Abstract

Sacroiliitis is an inflammatory disease of the sacroiliac joint that can be triggered by factors such as infections, traumata, and autoimmune diseases. It causes pain and stiffness in the lower back, making early diagnosis crucial for optimal treatment. The diagnosis is challenging and requires clinical evaluation, laboratory tests, and imaging techniques such as X-ray, MRI, or CT. In recent years, artificial intelligence (AI) has emerged as a promising tool for assessing changes in sacroiliitis. AI algorithms analyse various imaging techniques to detect, quantify, and classify structural changes and inflammation in the sacroiliac joint. The application of AI can improve the accuracy and efficiency of radiologists or rheumatologists in assessing sacroiliitis through imaging techniques. AI algorithms can quantify structural changes and inflammation in the sacroiliac joint and create predictive models for the disease course. However, challenges such as the need for high-quality data and minimising biases and errors in the data and algorithms must be overcome. Further studies are required to fully exploit the potential of AI in assessing sacroiliitis through imaging techniques. Nevertheless, the use of AI can improve patient outcomes by enabling early diagnosis and treatment.

Schlüsselwörter

Sakroiliitis - Radiologie - Künstliche Intelligenz - Deep Learning

Key words

Sacroiliitis - Radiology - Artificial Intelligence - Deep Learning

Publication History

Article published online:
15 June 2023

• Literatur

• 1 Tsoi C, Griffith JF, Lee RKL. et al. Imaging of sacroiliitis: current status, limitations and pitfalls. Quantitative Imaging in Medicine and Surgery 2019; 9: 318
• 2 Bressem KK, Adams LC, Proft F. et al. Deep learning detects changes indicative of axial spondyloarthritis at MRI of sacroiliac joints. Radiology 2022; 305: 655-665
• 3 Robinson PC, Sengupta R, Siebert S. Non-radiographic axial spondyloarthritis (nr-axSpA): advances in classification, imaging and therapy. Rheumatology and therapy 2019; 6: 165-177
• 4 Barnett R, Ingram T, Sengupta R. Axial spondyloarthritis 10 years on: still looking for the lost tribe. Rheumatology 2020; 59: iv25-iv37
• 5 Seo MR, Baek HL, Yoon HH. et al. Delayed diagnosis is linked to worse outcomes and unfavourable treatment responses in patients with axial spondyloarthritis. Clinical rheumatology 2015; 34: 1397-1405
• 6 Poddubnyy D, Sieper J. Diagnostic delay in axial spondyloarthritis–a past or current problem?. Current Opinion in Rheumatology 2021; 33: 307-312
• 7 Spoorenberg A, De Vlam K, van der Linden S. et al. Radiological scoring methods in ankylosing spondylitis. Reliability and change over 1 and 2 years. The Journal of rheumatology 2004; 31: 125-132
• 8 Christiansen AA, Hendricks O, Kuettel D. et al. Limited reliability of radiographic assessment of sacroiliac joints in patients with suspected early spondyloarthritis. The Journal of rheumatology 2017; 44: 70-77
• 9 Barnes C, ozdogan HA, yurdakul S. et al. Observer variation in grading sacroiliac radiographs might be a cause of sacroiliitis reported in certain disease states. 1987
• 10 Van Den Berg R, Lenczner G, Feydy A. et al. Agreement between clinical practice and trained central reading in reading of sacroiliac joints on plain pelvic radiographs: results from the DESIR cohort. Arthritis & rheumatology 2014; 66: 2403-2411
• 11 Üreten K, Maraş Y, Duran S. et al. Deep learning methods in the diagnosis of sacroiliitis from plain pelvic radiographs. Modern Rheumatology 2023; 33: 202-206
• 12 Thrall JH, Li X, Li Q. et al. Artificial intelligence and machine learning in radiology: opportunities, challenges, pitfalls, and criteria for success. Journal of the American College of Radiology 2018; 15: 504-508
• 13 Fritz B, Yi PH, Kijowski R. et al. Radiomics and deep learning for disease detection in musculoskeletal radiology: an overview of novel MRI-and CT-based approaches. Investigative Radiology 2023; 58: 3-13
• 14 Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology 2016; 278: 563-577 DOI: 10.1148/radiol.2015151169.
• 15 Wang S, Summers RM. Machine learning and radiology. Medical image analysis 2012; 16: 933-951
• 16 McBee MP, Awan OA, Colucci AT. et al. Deep learning in radiology. Academic radiology; 2018. 25. 1472-1480
• 17 Khalid H, Hussain M, Al Ghamdi MA. et al. A comparative systematic literature review on knee bone reports from mri, x-rays and ct scans using deep learning and machine learning methodologies. Diagnostics 2020; 10: 518
• 18 McMaster C, Liew DF, Liu B. et al. Comment on: Deep learning algorithms for magnetic resonance imaging of inflammatory sacroiliitis in axial spondyloarthritis. Rheumatology 2022; 61: e316-e317
• 19 Bressem KK, Vahldiek JL, Adams L. et al. Deep learning for detection of radiographic sacroiliitis: achieving expert-level performance. Arthritis Research & Therapy 2021; 23: 1-10
• 20 Noh SH, An C, Kim D. et al. Automated detection of sacroiliitis on plain radiograph using EfficientDet algorithm in young patients with back pain: a pilot study. 2021
• 21 Liu L, Zhang H, Zhang W. et al. Grading Diagnosis of Sacroiliitis in CT Scans Based on Radiomics and Deep Learning. In: Biometric Recognition: 16th Chinese Conference, CCBR 2022, Beijing, China, November 11–13, 2022, Proceedings. Springer; 2022: 655-663
• 22 Shenkman Y, Qutteineh B, Joskowicz L. et al. Automatic detection and diagnosis of sacroiliitis in CT scans as incidental findings. Medical image analysis 2019; 57: 165-175
• 23 Castro-Zunti R, Park EH, Choi Y. et al. Early detection of ankylosing spondylitis using texture features and statistical machine learning, and deep learning, with some patient age analysis. Computerized Medical Imaging and Graphics 2020; 82: 101718
• 24 Turk S, Demirkaya A, Turali MY. et al. JointNET: A Deep Model for Predicting Active Sacroiliitis from Sacroiliac Joint Radiography. arXiv preprint arXiv:230110769. 2023
• 25 Jans LB, Chen M, Elewaut D. et al. MRI-based synthetic CT in the detection of structural lesions in patients with suspected sacroiliitis: comparison with MRI. Radiology 2021; 298: 343-349
• 26 Morbée L, Vereecke E, Laloo F. et al. Common incidental findings on sacroiliac joint MRI: Added value of MRI-based synthetic CT. European Journal of Radiology 2023; 158: 110651
• 27 Tenório APM, Ferreira-Junior JR, Dalto VF. et al. Radiomic quantification for MRI assessment of sacroiliac joints of patients with spondyloarthritis. Journal of Digital Imaging 2022; 35: 29-38
• 28 Faleiros MC, Nogueira-Barbosa MH, Dalto VF. et al. Machine learning techniques for computer-aided classification of active inflammatory sacroiliitis in magnetic resonance imaging. Advances in Rheumatology. 2020 60.
• 29 Lee KH, Choi ST, Lee GY. et al. Method for diagnosing the bone marrow edema of sacroiliac joint in patients with axial spondyloarthritis using magnetic resonance image analysis based on deep learning. Diagnostics 2021; 11: 1156
• 30 Lin KYY, Peng C, Lee KH. et al. Deep learning algorithms for magnetic resonance imaging of inflammatory sacroiliitis in axial spondyloarthritis. Rheumatology 2022; 61: 4198-4206
• 31 Sun X, Zhou C, Zhu J. et al. Identification of clinical heterogeneity and construction of a novel subtype predictive model in patients with ankylosing spondylitis: An unsupervised machine learning study. International Immunopharmacology 2023; 117: 109879
• 32 Recht MP, Dewey M, Dreyer K. et al. Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations. European radiology 2020; 30: 3576-3584
• 33 Acosta JN, Falcone GJ, Rajpurkar P. et al. Multimodal biomedical AI. Nature Medicine 2022; 28: 1773-1784