Combining symmetric and standard deep convolutional representations for detecting brain hemorrhage

Arko Barman, Victor Lopez-Rivera, Songmi Lee, Farhaan S. Vahidy, James Z. Fan, Sean I. Savitz, Sunil A. Sheth, Luca Giancardo

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

6 Scopus citations


Brain hemorrhage (BH) is a severe type of stroke resulting in high mortality and morbidity. Detection and diagnosis of BH is commonly performed using neuroimaging tools such as Computed Tomography (CT). We compare and contrast symmetry-aware, symmetry-naive feature representations and their combination for the detection of BH using CT imaging. One of the proposed architectures, e-DeepSymNet, achieves AUC 0.99 [0.97- 1.00] for BH detection. An analysis of the activation values shows that both symmetry-aware and symmetry-naive representations offer complementary information with symmetry-aware representation naive contributing 20% towards the final predictions.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2020
Subtitle of host publicationComputer-Aided Diagnosis
EditorsHorst K. Hahn, Maciej A. Mazurowski
ISBN (Electronic)9781510633957
StatePublished - 2020
EventMedical Imaging 2020: Computer-Aided Diagnosis - Houston, United States
Duration: Feb 16 2020Feb 19 2020

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ISSN (Print)1605-7422


ConferenceMedical Imaging 2020: Computer-Aided Diagnosis
Country/TerritoryUnited States


  • brain hemorrhage
  • computer-aided detection
  • deep learning
  • deep symmetry-sensitive networks
  • machine learning
  • precision medicine
  • quantitative imaging

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Combining symmetric and standard deep convolutional representations for detecting brain hemorrhage'. Together they form a unique fingerprint.

Cite this