# Tensor Radiomics: Paradigm for Systematic Incorporation of Multi-Flavoured Radiomics Features

arXiv: https://arxiv.org/abs/2203.06314 · HTML: https://mlsanity.com/paper/2203.06314/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 62 references that are in the map.
- First posted on arXiv 12 Mar 2022.

## Builds on (most cited first, 5 of 5)

- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [Image biomarker standardisation initiative](https://mlsanity.com/paper/1612.07003/) (2016)
- [Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer](https://mlsanity.com/paper/1703.08516/) (2017)
- [Assessing robustness of radiomic features by image perturbation](https://mlsanity.com/paper/1806.06719/) (2018)
- [AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging: Towards Radiophenomics](https://mlsanity.com/paper/2110.10332/) (2021)

## Built on by (most cited first, 1 of 1)

- [Handcrafted vs. Deep Radiomics vs. Fusion vs. Deep Learning: A Comprehensive Review of Machine Learning -Based Cancer Outcome Prediction in PET and SPECT Imaging](https://mlsanity.com/paper/2507.16065/) (2025)

## Abstract (arXiv)

Radiomics features extract quantitative information from medical images, towards the derivation of biomarkers for clinical tasks, such as diagnosis, prognosis, or treatment response assessment. Different image discretization parameters (e.g. bin number or size), convolutional filters, segmentation perturbation, or multi-modality fusion levels can be used to generate radiomics features and ultimately signatures. Commonly, only one set of parameters is used; resulting in only one value or flavour for a given RF. We propose tensor radiomics (TR) where tensors of features calculated with multiple combinations of parameters (i.e. flavours) are utilized to optimize the construction of radiomics signatures. We present examples of TR as applied to PET/CT, MRI, and CT imaging invoking machine learning or deep learning solutions, and reproducibility analyses: (1) TR via varying bin sizes on CT images of lung cancer and PET-CT images of head & neck cancer (HNC) for overall survival prediction. A hybrid deep neural network, referred to as TR-Net, along with two ML-based flavour fusion methods showed improved accuracy compared to regular rediomics features. (2) TR built from different segmentation perturbations and different bin sizes for classification of late-stage lung cancer response to first-line immunotherapy using CT images. TR improved predicted patient responses. (3) TR via multi-flavour generated radiomics features in MR imaging showed improved reproducibility when compared to many single-flavour features. (4) TR via multiple PET/CT fusions in HNC. Flavours were built from different fusions using methods, such as Laplacian pyramids and wavelet transforms. TR improved overall survival prediction. Our results suggest that the proposed TR paradigm has the potential to improve performance capabilities in different medical imaging tasks.