Deep learning in magnetic resonance enterography for Crohn's disease assessment: a systematic review.

Crohn's disease (CD) poses significant morbidity, underscoring the need for effective, non-invasive inflammatory assessment using magnetic resonance enterography (MRE). This literature review evaluates recent publications on the role of deep learning in improving MRE for CD assessment. We searched MEDLINE/PUBMED for studies that reported the use of deep learning algorithms for assessment of CD activity. The study was conducted according to the PRISMA guidelines. The risk of bias was evaluated using the QUADAS-2 tool. Five eligible studies, encompassing 468 subjects, were identified. Our study suggests that diverse deep learning applications, including image quality enhancement, bowel segmentation for disease burden quantification, and 3D reconstruction for surgical planning are useful and promising for CD assessment. However, most of the studies are preliminary, retrospective studies, and have a high risk of bias in at least one category. Future research is needed to assess how deep learning can impact CD patient diagnostics, particularly when considering the increasing integration of such models into hospital systems.

Multipolar Electrograms: A New Configuration That Increases the Measurement Accuracy of Intracardiac Signals.

BACKGROUND: Accurate measurements of intracardiac electrograms (EGMs) remain a clinical challenge because of the suboptimal attenuation of far-field potentials. Multielectrode mapping catheters provide an opportunity to construct multipolar instead of bipolar EGMs for rejecting common far-field potentials recorded from a multivectorial space. OBJECTIVES: The purpose of this study was to develop a multipolar EGM and compare its characteristics to those of bipolar EGMs METHODS: Using a 36-electrode array catheter (Optrell-36; Biosense Webster), a far-field component was mathematically constructed from clusters of electrodes surrounding each inspected electrode. This component was subtracted from the unipolar waveform to produce a local unipolar, referred to as a "multipolar EGM." The performance of multipolar EGMs was evaluated in 7 swine with healed anteroseptal infarction. RESULTS: Multipolar EGMs proved superior in attenuating far-field potentials in infarct border zones, increasing the near-field to far-field ratio from 0.92 ± 0.2 to 2.25 ± 0.3 (P < 0.001). Removal of far-field components reduced the voltage amplitude (P < 0.001) and enlarged the infarct surface area (P = 0.02), aligning more closely with histological findings. Of 379 EGMs with ≥20 ms activation time difference between bipolar and multipolar EGMs, 95.3% (361 of 379) were accurately annotated using multipolar EGMs, while annotation based on bipolar EGM was predominantly made on far-field components. CONCLUSIONS: Multielectrode array catheters provide a unique platform for constructing multipolar EGMs. This new EGM may be beneficial for "purifying" local potentials within a complex electrical field, resulting in more accurate voltage and activation maps.