Machine Learning Diagnosis of Small-Bowel Crohn Disease Using T2-Weighted MRI Radiomic and Clinical Data
pubmed.ncbi.nlm.nih.gov shows its articles on its own site.
Read the article on pubmed.ncbi.nlm.nih.gov ↗Article · Aug 2023 · 1 min read
In brief
In brief
This study developed a machine learning model using radiomic features from T2-weighted MRI to diagnose small-bowel Crohn disease, comparing its performance against expert pediatric radiologists. The approach addresses significant interreader variability in MR enterography interpretation for suspected Crohn disease.
Written by the GCMD Library team from the article.
Statements in this article
Radiologists have variable diagnostic performance and considerable interreader variability when interpreting MR enterography examinations for suspected Crohn disease.
The study included patients who underwent MRE for suspected ileal Crohn disease from January 1, 2020, to January 31, 2021, and prospectively enrolled participants from December 2018 to October 2021.
Two axial T2-weighted SSFSE image slices showing greatest terminal ileal wall thickening were selected for analysis.
Four regions of interest were segmented and radiomic features were extracted from each ROI.
Support-vector machine models were trained to classify the presence of ileal Crohn disease after feature selection.
Three fellowship-trained pediatric abdominal radiologists independently classified the presence of ileal Crohn disease on SSFSE images.
The reference standard was clinical diagnosis of ileal Crohn disease based on endoscopy and biopsy results.
Radiomic-only, clinical-only, and radiomic-clinical ensemble models were trained and evaluated by nested cross-validation.
The study included 135 participants with 67 female and 68 male patients.