Brain lesion detection in 3D PET images using max-trees and a new spatial context criterion

Abstract :

In this work, we propose a new criterion based on spatial context to select relevant nodes in a max-tree representation of an image, dedicated to the detection of 3D brain tumors for \textsuperscript{18}$F$-FDG PET images. This criterion prevents the detected lesions from merging with surrounding physiological radiotracer uptake. A complete detection method based on this criterion is proposed, and was evaluated on five patients with brain metastases and tuberculosis, and quantitatively assessed using the true positive rates and positive predictive values. The experimental results show that the method detects all the lesions in the PET.

Complete list of metadatas

https://hal.telecom-paristech.fr/hal-02287551
Contributor : Telecomparis Hal <>
Submitted on : Friday, September 13, 2019 - 5:05:18 PM
Last modification on : Thursday, October 17, 2019 - 12:37:00 PM

Identifiers

  • HAL Id : hal-02287551, version 1

Citation

Hélène Urien, Irène Buvat, N. F. Rougon, Michael Soussan, Isabelle Bloch. Brain lesion detection in 3D PET images using max-trees and a new spatial context criterion. International Symposium on Mathematical Morphology (ISMM 2017), 2017, Fontainebleau, France. pp.455-466. ⟨hal-02287551⟩

Share

Metrics

Record views

11