Cine-MRI detection of abdominal adhesions with spatio-temporal deep learningDownload PDF

Apr 06, 2021 (edited Jun 15, 2021)MIDL 2021 Conference Short SubmissionReaders: Everyone
  • Keywords: cine-MRI, adhesion detection, spatio-temporal, ConvGRU
  • TL;DR: An efficient recurrent deep learning architecture, based on a ConvGRU model, to detect abdominal adhesions on Cine-MRI
  • 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.
  • Paper Type: both
  • Primary Subject Area: Detection and Diagnosis
  • Secondary Subject Area: Application: Radiology
  • Paper Status: original work, not submitted yet
  • Source Code Url: Due to the IP protocol of the hospital I work in, I can only disclose my source code upon explicit approval. Currently, this has not been requested yet.
  • Data Set Url: The data is a private dataset obtained from the hospital I work in. This is only shared with known parties, with whom we have a DTA.
  • Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
  • Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
4 Replies

Loading