Pericardial effusion detection on post-mortem computed tomography images using convolutional neural networks

Haoyu Kong, Jia Rong, Chris Bain, Xinyu Zhang, Sarah Parsons, Guanliang Chen, Richard Bassed

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Pericardial effusion can be a sign of significant underlying diease and, in some cases, may lead to death. Post-mortem computed tomography (PMCT) is a well-established tool to assist death investigation processes in the forensic setting. In practice, the scarcity of well-trained radiologists is a challenge in processing raw whole-body PMCT images for pericardial effusion detection. In this work, we propose a Pericardial Effusion Automatic Detection (PEAD) framework to automatically process raw whole-body PMCT images to filter out the irrelevant images with heart organ absent and focus on pericardial effusion detection. In PEAD, the standard convolutional neural network architectures of VGG and ResNet are carefully modified to fit the specific characteristics of PMCT images. The experimental results prove the effectiveness of the proposed framework and modified models. The modified VGG and ResNet models achieved superior detection accuracy than the standard architecture with reduced processing speed.

Original languageEnglish
Title of host publicationMEDINFO 2023 — The Future Is Accessible
Subtitle of host publicationProceedings of the 19th World Congress on Medical and Health Informatics
EditorsJen Bichel-Findlay, Paula Otero, Philip Scott, Elaine Huesing
Place of PublicationAmsterdam Netherlands
PublisherIOS Press
Pages745-749
Number of pages5
ISBN (Electronic)9781643684574
ISBN (Print)9781643684567
DOIs
Publication statusPublished - 2024
EventWorld Congress on Medical and Health Informatics 2023 - International Conference Centre, Sydney, Australia
Duration: 8 Jul 202312 Aug 2023
Conference number: 19th
https://medinfo2023.org/
https://ebooks.iospress.nl/volume/medinfo-2023-the-future-is-accessible-proceedings-of-the-19th-world-congress-on-medical-and-health-informatics (Published proceedings)

Publication series

NameStudies in Health Technology and Informatics
PublisherIOS Press
Volume310
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

ConferenceWorld Congress on Medical and Health Informatics 2023
Abbreviated titleMEDINFO 2023
Country/TerritoryAustralia
CitySydney
Period8/07/2312/08/23
OtherTheme: The Future is Accessible
Internet address

Keywords

  • convolutional neural network
  • Pericardial effusion detection
  • post-mortem computed tomography

Cite this