Cine-MRI detection of abdominal adhesions with spatio-temporal deep learning

TL;DR

This paper presents a deep learning approach using spatio-temporal ConvGRU architectures to detect abdominal adhesions in cine-MRI, improving classification accuracy over static models.

Contribution

It introduces a hybrid ResNet-ConvGRU model for whole-series classification, demonstrating improved performance in adhesion detection from cine-MRI.

Findings

AUROC increased from 0.74 to 0.83 with the full temporal model

Hybrid architecture adds minimal parameters (~5%)

Temporal modeling enhances adhesion classification accuracy

Abstract

Adhesions are an important cause of chronic pain following abdominal surgery. Recent developments in abdominal cine-MRI have enabled the non-invasive diagnosis of adhesions. Adhesions are identified on cine-MRI by the absence of sliding motion during movement. Diagnosis and mapping of adhesions improves the management of patients with pain. Detection of abdominal adhesions on cine-MRI is challenging from both a radiological and deep learning perspective. We focus on classifying presence or absence of adhesions in sagittal abdominal cine-MRI series. We experimented with spatio-temporal deep learning architectures centered around a ConvGRU architecture. A hybrid architecture comprising a ResNet followed by a ConvGRU model allows to classify a whole time-series. Compared to a stand-alone ResNet with a two time-point (inspiration/expiration) input, we show an increase in classification performance (AUROC) from 0.74 to 0.83 ($p<0.05$). Our full temporal classification approach adds only a small amount (5%) of parameters to the entire architecture, which may be useful for other medical imaging problems with a temporal dimension.