Skip to Main content Skip to Navigation
Conference papers

Automatic segmentation of hippocampus in histological images of mouse brains using deformable models and random forest

Abstract : We perform a two-step segmentation of the hippocam-pus in histological images. First, we maximize the overlap of an empirically-derived parametric Deformable Model with two crucial landmark sub-structures in the brain image using Differential Evolution. Then, the points located in the previous step determine the region where a thresh-olding technique based on Otsu's method is to be applied. Finally, the segmentation is expanded employing Random Forest in the regions not covered by the model. Our approach showed an average segmentation accuracy of the 92.25% and 92.11% on test sets comprising 15 real and 15 synthetic images, respectively.
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/hal-01221660
Contributor : Pablo Mesejo Santiago <>
Submitted on : Wednesday, October 28, 2015 - 1:27:02 PM
Last modification on : Thursday, October 29, 2015 - 1:09:00 AM
Long-term archiving on: : Friday, January 29, 2016 - 1:18:36 PM

File

PID2332607.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Pablo Mesejo, Roberto Ugolotti, Ferdinando Di Cunto, Stefano Cagnoni, Mario Giacobini. Automatic segmentation of hippocampus in histological images of mouse brains using deformable models and random forest. 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS’12), Jun 2012, Rome, Italy. pp.1-4, ⟨10.1109/CBMS.2012.6266318⟩. ⟨hal-01221660⟩

Share

Metrics

Record views

195

Files downloads

206