Synaps

Developing novel photodynamic therapies for neurosurgery

Synaps
  • About
    • Overview
    • Partnership >
      • Onco-THAI Inserm U1189
      • University of Lille
      • Lille University Hospital
      • Inserm
      • ECRIN
      • Leitat Technological Center
      • IDDI
      • Medical University of Graz
      • OP2
      • Erasme Hospital
  • Research
    • Overview
    • Clinical trial
    • Publications
  • Medical information
    • Overview
    • Glioblastoma
    • PhotoDynamic Therapies
  • News
  • Contact

  • About
    • Overview
    • Partnership >
      • Onco-THAI Inserm U1189
      • University of Lille
      • Lille University Hospital
      • Inserm
      • ECRIN
      • Leitat Technological Center
      • IDDI
      • Medical University of Graz
      • OP2
      • Erasme Hospital
  • Research
    • Overview
    • Clinical trial
    • Publications
  • Medical information
    • Overview
    • Glioblastoma
    • PhotoDynamic Therapies
  • News
  • Contact

News

Our newest paper dedicated to automatic brain segmentation

11/25/2016

 
 Our paper entitled "Stacking denoising auto-encoders in a deep network to segment the brainstem on MRI in brain cancer patients: A clinical study" has been recently published in Computerized Medical Imaging and Graphics (vol. 52).

This paper introduces a deep learning approach based on stacking denoising auto-encoders in order to segment the brainstem on magnetic resonance images in brain cancer context. Additionally to classical features used in machine learning to segment brain structures, two new features are suggested. Four experts participated in this study by segmenting the brainstem on 9 patients who underwent radiosurgery. Analysis of variance on shape and volume similarity metrics indicated that there were significant differences (p < 0.05) between the groups of manual annotations and automatic segmentations. Experimental evaluation also showed an overlapping higher than 90% with respect to the ground truth. These results are comparable, and often higher, to those of the state of the art segmentation methods but with a considerably reduction of the segmentation time.

This paper is available on Science Direct or here.
Picture
Facebook LinkedIn Twitter

Comments are closed.
Université Lille 2
Onco Thai
Inserm
CHRU Lille
Picture
 Legal notice - Credits