17-year-patient with Crohn disease

17-year-patient with Crohn disease. Axial T2-weighted SSFSE images show greatest terminal thickness—without (top) and with (bottom) four ROI segmentations. (Green = whole-bowel ROI; yellow = bowel-core ROI; red = whole-fat ROI; orange = fat-core ROI.) 


August 2, 2023 — An accepted manuscript published in the American Journal of Roentgenology (AJR) found that deploying a radiomic-based model with T2-weighted MRI data could increase diagnostic accuracy for pediatric Crohn disease (CD). 

Noting that ileal-wall radiomic features were strongly predictive of CD—and that model performance improved when ensembled with clinical data—“a radiomic machine learning model predicted CD diagnosis with better performance than two of three expert radiologists,” wrote corresponding author and AJR Pediatric Imaging Section Editor Jonathan R. Dillman, MD, MSc.  

Dillman et al.’s manuscript identified patients who underwent MR enterography (MRE) for suspected ileal CD—enrolling participants with newly diagnosed ileal CD or serving as healthy controls from December 2018 to October 2021. Using axial T2-weighted SSFSE images, one radiologist selected two slices showing the greatest terminal ileal wall thickening. Four ROIs were then segmented, radiomic features were extracted from each, and support-vector machine models were trained to catalog the presence of ileal CD. Three fellowship-trained pediatric abdominal radiologists independently classified the presence of ileal CD on SSFSE images, with clinical diagnosis following positive endoscopy and biopsy serving as the reference standard. 

Ultimately, the best-performing radiomic-only model in this AJR accepted manuscript used a round bowel-wall ROI in the area of greatest terminal ileum thickening, having AUC of 0.95 and accuracy of 89.6%. Ensembling this radiomic-only model with a clinical-only model achieved AUC of 0.98 and accuracy of 93.5%. Meanwhile, the three specialized radiologists achieved accuracies of 83.7%, 86.7%, and 88.1%. 

For more information: www.arrs.org 


Related Content

News | Imaging Software Development

June 12, 2025 — GE HealthCare has announced the combination of GE HealthCare’s proprietary features and algorithms with ...

Time June 12, 2025
arrow
News | Ultrasound Imaging

June 3, 2025 — In a collaborative study between the Departments of Radiology at the Children’s Hospital of Philadelphia ...

Time June 04, 2025
arrow
News | Radiology Business

The issue of sustainability in healthcare has gained increasing focus over the past several years. During a 2022 plenary ...

Time May 06, 2025
arrow
News | Pediatric Imaging

April 10, 2025 — Cincinnati Children’s and GE HealthCare will form a strategic research program focused on driving ...

Time April 10, 2025
arrow
News | Radiology Imaging

Jan. 15, 2025 — University of California, San Francisco (UCSF) Department of Radiology & Biomedical Imaging and GE ...

Time January 27, 2025
arrow
News | Contrast Media

Jan. 10, 2025 – Bayer has announced positive topline results of the Phase III QUANTI studies evaluating the efficacy and ...

Time January 14, 2025
arrow
News | Radiology Imaging

Nov. 13, 2024 — Agfa Radiology Solutions will feature live demonstrations of state-of-the-art digital X-ray rooms ...

Time November 14, 2024
arrow
News | Women's Health

Aug. 19, 2024 — GE HealthCare recently announced a collaboration with the University of California San Diego School of ...

Time August 29, 2024
arrow
News | Computed Tomography (CT)

SPONSORED CONTENT — Fujifilm’s latest CT technology brings exceptional image quality to a compact and user- and patient ...

Time August 06, 2024
arrow
News | Radiology Business

July 31, 2024 — The American Registry of Radiologic Technologists (ARRT) announced the three Registered Technologists (R ...

Time July 31, 2024
arrow
Subscribe Now