Ensemble of Weak Spectral Total Variation Learners: a PET-CT Case Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rosenberg, Anna, Kennedy, John, Keidar, Zohar, Zeevi, Yehoshua Y., Gilboa, Guy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913938397986816
author Rosenberg, Anna
Kennedy, John
Keidar, Zohar
Zeevi, Yehoshua Y.
Gilboa, Guy
author_facet Rosenberg, Anna
Kennedy, John
Keidar, Zohar
Zeevi, Yehoshua Y.
Gilboa, Guy
contents Solving computer vision problems through machine learning, one often encounters lack of sufficient training data. To mitigate this we propose the use of ensembles of weak learners based on spectral total-variation (STV) features (Gilboa 2014). The features are related to nonlinear eigenfunctions of the total-variation subgradient and can characterize well textures at various scales. It was shown (Burger et-al 2016) that, in the one-dimensional case, orthogonal features are generated, whereas in two-dimensions the features are empirically lowly correlated. Ensemble learning theory advocates the use of lowly correlated weak learners. We thus propose here to design ensembles using learners based on STV features. To show the effectiveness of this paradigm we examine a hard real-world medical imaging problem: the predictive value of computed tomography (CT) data for high uptake in positron emission tomography (PET) for patients suspected of skeletal metastases. The database consists of 457 scans with 1524 unique pairs of registered CT and PET slices. Our approach is compared to deep-learning methods and to Radiomics features, showing STV learners perform best (AUC=0.87), compared to neural nets (AUC=0.75) and Radiomics (AUC=0.79). We observe that fine STV scales in CT images are especially indicative for the presence of high uptake in PET.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08735
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ensemble of Weak Spectral Total Variation Learners: a PET-CT Case Study
Rosenberg, Anna
Kennedy, John
Keidar, Zohar
Zeevi, Yehoshua Y.
Gilboa, Guy
Computer Vision and Pattern Recognition
Solving computer vision problems through machine learning, one often encounters lack of sufficient training data. To mitigate this we propose the use of ensembles of weak learners based on spectral total-variation (STV) features (Gilboa 2014). The features are related to nonlinear eigenfunctions of the total-variation subgradient and can characterize well textures at various scales. It was shown (Burger et-al 2016) that, in the one-dimensional case, orthogonal features are generated, whereas in two-dimensions the features are empirically lowly correlated. Ensemble learning theory advocates the use of lowly correlated weak learners. We thus propose here to design ensembles using learners based on STV features. To show the effectiveness of this paradigm we examine a hard real-world medical imaging problem: the predictive value of computed tomography (CT) data for high uptake in positron emission tomography (PET) for patients suspected of skeletal metastases. The database consists of 457 scans with 1524 unique pairs of registered CT and PET slices. Our approach is compared to deep-learning methods and to Radiomics features, showing STV learners perform best (AUC=0.87), compared to neural nets (AUC=0.75) and Radiomics (AUC=0.79). We observe that fine STV scales in CT images are especially indicative for the presence of high uptake in PET.
title Ensemble of Weak Spectral Total Variation Learners: a PET-CT Case Study
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.08735