Influence of input image configurations on output of a convolutional neural network to detect cerebral aneurysms

Kazuhiro Watanabe, Hitomi Anzai, Norman Juchler, Sven Hirsch, Philippe Bijlenga, Makoto Ohta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Rupture of cerebral aneurysms is the main cause of subarachnoid hemorrhage, which can have devastating effects on quality of life. The identification and assessment of unruptured aneurysms from medical images is therefore of significant clinical relevance. In recent years, the availability of clinical imaging data has rapidly increased, which calls for computer assisted detection (CAD) systems. Previous studies have shown that CAD systems based on convolutional neural networks (CNN) can help to detect cerebral aneurysms from magnetic resonance angiographies (MRAs). However, these CAD systems require large datasets of annotated medical images. Thus, more efficient tools for processing and categorizing medical imaging data are required. Previous studies of CNN-based classification for medical images used various patch configurations of input data. These studies showed that classification accuracy was affected by the patch size or image representation. Thus, we hypothesize that the accuracy of CADs to detect cerebral aneurysms can be improved by adjusting the configuration of the input patches. In the present study, we performed CNN-based medical imaging classification for varying input data configurations to examine the relationship between classification accuracy and data configuration.

Original languageEnglish
Title of host publicationBiomedical and Biotechnology Engineering
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791859407
DOIs
Publication statusPublished - 2019 Jan 1
EventASME 2019 International Mechanical Engineering Congress and Exposition, IMECE 2019 - Salt Lake City, United States
Duration: 2019 Nov 112019 Nov 14

Publication series

NameASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)
Volume3

Conference

ConferenceASME 2019 International Mechanical Engineering Congress and Exposition, IMECE 2019
CountryUnited States
CitySalt Lake City
Period19/11/1119/11/14

Keywords

  • Cerebral aneurysm
  • Computer assisted detection
  • Convolutional neural network

ASJC Scopus subject areas

  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Influence of input image configurations on output of a convolutional neural network to detect cerebral aneurysms'. Together they form a unique fingerprint.

  • Cite this

    Watanabe, K., Anzai, H., Juchler, N., Hirsch, S., Bijlenga, P., & Ohta, M. (2019). Influence of input image configurations on output of a convolutional neural network to detect cerebral aneurysms. In Biomedical and Biotechnology Engineering (ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE); Vol. 3). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/IMECE2019-11125