Ensemble of Weak Spectral Total Variation Learners: a PET-CT Case Study
This addresses a hard real-world medical imaging problem for patients suspected of skeletal metastases, showing incremental improvement over existing methods.
The paper tackled the problem of insufficient training data in computer vision by proposing ensembles of weak learners based on spectral total-variation features, applied to a medical imaging task of predicting high uptake in PET from CT scans for skeletal metastases, achieving an AUC of 0.87 compared to 0.75 for neural nets and 0.79 for Radiomics.
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.