Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions

Samya Amiri, Mohamed Ali Mahjoub, Islem Rekik (Lead / Corresponding author)

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

2 Citations (Scopus)
166 Downloads (Pure)

Abstract

We introduce a dynamic multiscale tree (DMT) architecture that learns how to leverage the strengths of different state-of-the-art classifiers for supervised multi-label image segmentation. Unlike previous works that simply aggregate or cascade classifiers for addressing image segmentation and labeling tasks, we propose to embed strong classifiers into a tree structure that allows bi-directional flow of information between its classifier nodes to gradually improve their performances. Our DMT is a generic classification model that inherently embeds different cascades of classifiers while enhancing learning transfer between them to boost up their classification accuracies. Specifically, each node in our DMT can nest a Structured Random Forest (SRF) classifier or a Bayesian Network (BN) classifier. The proposed SRF-BN DMT architecture has several appealing properties. First, while SRF operates at a patch-level (regular image region), BN operates at the super-pixel level (irregular image region), thereby enabling the DMT to integrate multi-level image knowledge in the learning process. Second, the proposed DMT robustly overcomes the limitations of the aggregated classifiers through the ascending and descending flow of contextual information between each parent node and its children nodes. Third, we train DMT using different scales to capture a coarse-to-fine image details. Last, DMT demonstrates its outperformance in comparison to several state-of-the-art segmentation methods for multi-labeling of brain images with gliomas.
Original languageEnglish
Title of host publication Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
EditorsAlain Tremeau, Jose Braz, Francisco Imai
Place of PublicationPortugal
PublisherSciTePress
Pages419-426
Number of pages8
Volume4
ISBN (Electronic)9789897582905
DOIs
Publication statusPublished - 29 Jan 2018
EventVISAPP 2018: 13th International Conference on Computer Vision Theory and Applications - Madeira, Portugal
Duration: 27 Jan 201829 Jan 2018
http://www.visapp.visigrapp.org//Home.aspx

Publication series

NameVISIGRAPP 2018 - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume4

Conference

ConferenceVISAPP 2018
CountryPortugal
CityMadeira
Period27/01/1829/01/18
Internet address

Keywords

  • Autocontext model
  • Bayesian network
  • Brain tumor segmentation
  • Dynamic learning
  • Ensemble classifiers
  • MRI
  • Structured random forest

Fingerprint Dive into the research topics of 'Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions'. Together they form a unique fingerprint.

  • Cite this

    Amiri, S., Ali Mahjoub, M., & Rekik, I. (2018). Dynamic Multiscale Tree Learning Using Ensemble Strong Classifiers for Multi-label Segmentation of Medical Images with Lesions. In A. Tremeau, J. Braz, & F. Imai (Eds.), Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Vol. 4, pp. 419-426). (VISIGRAPP 2018 - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 4). SciTePress. https://doi.org/10.5220/0006630004190426