Exploring the limit of image resolution for human expert classification of vascular ultrasound images in giant cell arteritis and healthy subjects: the GCA-US-AI project.
Authors
Affiliations (36)
Affiliations (36)
- Clinic of Internal Medicine III - Rheumatology, University Hospital Bonn, Bonn, Germany. Electronic address: [email protected].
- Department of Rheumatology, University Hospital of Southern Denmark, Esbjerg, Denmark.
- Department of Rheumatology and Immunology, Medical University Graz, Graz, Austria; Department of Rheumatology, Hospital of Bruneck (ASAA-SABES), Teaching Hospital of the Paracelsius Medical University, Bruneck, Italy.
- Division of Rheumatology, Mayo Clinic, Rochester, MN, USA.
- Division of Rheumatology, Allergy and Immunology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
- IRCCS Istituto Auxologico Italiano, Immunorheumatology Research Laboratory, Milan, Italy.
- Rheumatology, Immanuel Krankenhaus Berlin, Medical Centre for Rheumatology Berlin-Buch, Berlin, Germany.
- Vasculitis Service, Rheumatology Department, Norfolk and Norwich University Hospital, Norwich, UK.
- Clinic of Internal Medicine III - Rheumatology, University Hospital Bonn, Bonn, Germany.
- Department of Rheumatology, Internal Medicine, Geriatrics and Clinical Immunology, Pomeranian Medical University in Szczecin, Szczecin, Poland.
- Department of Rheumatology, ULS de Santa Maria, Centro Académico de Medicina de Lisboa, Lisbon, Portugal; Faculdade de Medicina, Universidade de Lisboa, Centro Académico de Medicina de Lisboa, Lisbon, Portugal.
- Department of Internal Medicine, Clinical Division of Internal Medicine II, Medical University Innsbruck, Innsbruck, Austria.
- Department of Rheumatology, Hospital Universitario La Paz, Madrid, Spain.
- Department of Rheumatology, University Medical Centre Ljubljana, Ljubljana, Slovenia.
- Università degli Studi di Torino, Turin, Italy.
- Department of Clinical Medicine, Copenhagen University, Copenhagen, Denmark; Copenhagen Center for Arthritis Research (COPECARE), Center for Rheumatology and Spine Diseases, Rigshospitalet, Glostrup, Denmark.
- Copenhagen Center for Arthritis Research (COPECARE), Center for Rheumatology and Spine Diseases, Rigshospitalet, Glostrup, Denmark.
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Department of Rheumatology, Aarhus University Hospital, Aarhus, Denmark; Department of Medicine, The Regional Hospital in Horsens, Horsens, Denmark.
- Department of Rheumatology, Immanuel Hospital, Berlin, Germany.
- Department of Rheumatology and Immunology, Inselspital, Bern University Hospital, University of Bern, Switzerland.
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Department of Rheumatology, Aarhus University Hospital, Aarhus, Denmark.
- Medical University of Plovdiv, Clinic of Rheumatology, University Hospital "Kaspela", Plovdiv, Bulgaria.
- Clinic for Rheumatology, University Hospital Basel, Basel, Switzerland.
- Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds, UK; Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds, UK.
- Division of Rheumatology, Department of Medicine, Loma Linda University School of Medicine, Loma Linda, CA, USA.
- Rheumatology and Clinical Immunology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands.
- Department of Rheumatology and Clinical Immunology, Hospital Group Twente, Almelo, The Netherlands.
- Department of Rheumatology and Immunology, Medical University Graz, Graz, Austria.
- Unit of Immunology, Rheumatology, Allergy and Rare Diseases, San Raffaele Scientific Institute, Milan, Italy.
- Department of Angiology, University Hospital Basel, Basel, Switzerland.
- Rheumatology, David Geffen School of Medicine, University of California, Los Angeles, CA, USA.
- Department of Infectious Diseases, Akershus University Hospital, Lørenskog, Norway.
- Regional Hospital Northern Jutland, Hjorring, Denmark; Department of Rheumatology, Odense University Hospital, Odense, Denmark.
- Division of Rheumatology, Marmara University School of Medicine, Istanbul, Turkey.
- Department of Diagnostic and Interventional Radiology, University Hospital Bonn, Bonn, Germany; Helmholtz Munich, Helmholtz AI, Neuherberg, Germany.
- Institute of Medical Biometry, Informatics and Epidemiology, University Hospital of Bonn, Bonn, Germany.
Abstract
Prompt diagnosis of giant cell arteritis (GCA) with ultrasound is crucial for preventing severe ocular and other complications, yet expertise in ultrasound performance is scarce. The development of an artificial intelligence (AI)-based assistant that facilitates ultrasound image classification and helps to diagnose GCA early promises to close the existing gap. In the projection of the planned AI, this study investigates the minimum image resolution required for human experts to reliably classify ultrasound images of arteries commonly affected by GCA for the presence or absence of GCA. Thirty-one international experts in GCA ultrasonography participated in a web-based exercise. They were asked to classify 10 ultrasound images for each of 5 vascular segments as GCA, normal, or not able to classify. The following segments were assessed: (1) superficial common temporal artery, (2) its frontal and (3) parietal branches (all in transverse view), (4) axillary artery in transverse view, and 5) axillary artery in longitudinal view. Identical images were shown at different resolutions, namely 32 × 32, 64 × 64, 128 × 128, 224 × 224, and 512 × 512 pixels, thereby resulting in a total of 250 images to be classified by every study participant. Classification performance improved with increasing resolution up to a threshold, plateauing at 224 × 224 pixels. At 224 × 224 pixels, the overall classification sensitivity was 0.767 (95% CI, 0.737-0.796), and specificity was 0.862 (95% CI, 0.831-0.888). A resolution of 224 × 224 pixels ensures reliable human expert classification and aligns with the input requirements of many common AI-based architectures. Thus, the results of this study substantially guide projected AI development.