Automatic detection of Crohn's disease using quantified motility in magnetic resonance enterography: initial experiences

Abstract

•Automated detection of Crohn's disease appears feasible in free-breathing MRE.•Regions-of-interest (ROIs) can be generated automatically using neural networks.•Motility quantification without ROI placement shows good performance.•Longer cine series and utilizing multiple coronal planes improves detection.•The presented algorithm shows initial promise in primary diagnostics. AIMTo report initial experiences of automatic detection of Crohn's disease (CD) using quantified motility in magnetic resonance enterography (MRE).MATERIALS AND METHODSFrom 302 patients, three datasets with roughly equal proportions of CD and non-CD cases with various illnesses were drawn for testing and neural network training and validation. All datasets had unique MRE parameter configurations and were performed in free breathing. Nine neural networks were devised for automatic generation of three different regions of interests (ROI): small bowel, all bowel, and non-bowel. Additionally, a full-image ROI was tested. The motility in an MRE series was quantified via a registration procedure, which, accompanied with given ROIs, resulted in three motility indices (MI). A subset of the indices was used as an input for a binary logistic regression classifier, which predicted whether the MRE series represented CD.RESULTSThe highest mean area under the curve (AUC) score, 0.78, was reached using the full-image ROI and with the dataset with the highest cine series length. The best AUC scores for the other two datasets were only 0.54 and 0.49.CONCLUSIONThe automatic system was able to detect CD in the group of MRE studies with lower temporal resolution and longer cine series showing potential in primary bowel disorder diagnostics. Larger ROI selections and utilising all available cine series for motility registration yielded slight performance improvements. To report initial experiences of automatic detection of Crohn's disease (CD) using quantified motility in magnetic resonance enterography (MRE). From 302 patients, three datasets with roughly equal proportions of CD and non-CD cases with various illnesses were drawn for testing and neural network training and validation. All datasets had unique MRE parameter configurations and were performed in free breathing. Nine neural networks were devised for automatic generation of three different regions of interests (ROI): small bowel, all bowel, and non-bowel. Additionally, a full-image ROI was tested. The motility in an MRE series was quantified via a registration procedure, which, accompanied with given ROIs, resulted in three motility indices (MI). A subset of the indices was used as an input for a binary logistic regression classifier, which predicted whether the MRE series represented CD. The highest mean area under the curve (AUC) score, 0.78, was reached using the full-image ROI and with the dataset with the highest cine series length. The best AUC scores for the other two datasets were only 0.54 and 0.49. The automatic system was able to detect CD in the group of MRE studies with lower temporal resolution and longer cine series showing potential in primary bowel disorder diagnostics. Larger ROI selections and utilising all available cine series for motility registration yielded slight performance improvements.

Topics & Concepts