Publications

List of key publications featuring SPAARC

  • Vincenzi MM, Mori M, Passoni P, Tummineri R, Slim N, Midulla M, Palazzo G, Belardo A, Spezi E, Picchio M, Reni M, Chiti A, Del Vecchio A, Fiorino C and Di Muzio NG (2025) '', Cancers, https://doi.org/10.3390/cancers17061036
    Key Findings: Pancreatic cancer is a highly aggressive disease with a poor prognosis, even when detected in its early stages. This study temporally validated and improved a model using radiomic features derived from [18F]FDG-PET imaging to predict distant relapse-free survival in patients with locally advanced pancreatic cancer. Data from 215 patients treated with chemoradiotherapy were analyzed. The original model, which included two radiomic features and a cancer stage, showed moderate accuracy in predicting patient outcomes. Simplifying the model to a single radiomic feature improved performance slightly, while adding another complementary feature further enhanced accuracy. Although all versions of the model showed moderate ability to differentiate risk levels, these radiomic features demonstrate potential for patient stratification. Further validation is ongoing with independent cohorts from external centers, ensuring robustness beyond the analyzed patient group.
  • Duman A, Sun X, Thomas S, Powell J R and Spezi E. (2024) 'Reproducible and Interpretable Machine Learning-Based Radiomic Analysis for Overall Survival Prediction in Glioblastoma Multiforme', Cancers, https://doi.org/10.3390/cancers16193351
    Key Findings: In this study, we analyzed a multicenter dataset of 289 patients and extracted 660 radiomic features from the tumor volumes. Our final clinical–radiomic model combines patient age, and two robust radiomic features. We achieved (a) C-Index of 0.69 for predicting Overall Survival (OS), (b) significant patient stratification, (c) integrated AUC (iAUC) of 0.81 at 11 months. This model showcases great potential in stratifying Glio-Blastoma Multiforme (GBM) patients into low- and high-risk groups, providing important insights for personalized treatment planning.
  • Whybra P, Zwanenburg A, Andrearczyk V et al (2024) 'The Image Biomarker Standardization Initiative: Standardized Convolutional Filters for Reproducible Radiomics and Enhanced Clinical Insights', Radiology, https://doi.org/10.1148/radiol.231319
    Key Findings: This work, researchers who developed radiomics software participated in a three-phase study to establish a standardized set of imaging filters. Standardizing convolutional filters that enhance specific structures and patterns in medical imaging enables reproducible radiomics analyses, improves consistency and reliability for enhanced clinical insights. Thirty-three reference filtered images and 323 reference feature values computed from filtered images were established to standardize radiomics analyses across various imaging modalities. This is another milestone in the field, after the original IBSI paper published in 2020 https://doi.org/10.1148/radiol.2020191145.
  • Whybra P, Spezi E (2023) 'Sensitivity of standardised radiomics algorithms to mask generation across different software platforms', Scientific Reports, https://doi.org/10.1038/s41598-023-41475-w
    Key Findings: In this study we have interfaced SPAARC with several medical image processing software using their proprietary application programming interface (API). The study shows that even when working on the same dataset, mask and feature discrepancy occurs depending on the contour-to-mask conversion technique implemented in various medical imaging software. We also show that this can also affect patient clustering and radiomic-based modelling in multi-centre studies where a mix of mask generation software is used. We provide recommendations to negate this issue and facilitate reproducible and reliable radiomics.
  • Loi S, Mori M, Palumbo D, Crippa S, Palazzo G, Spezi E, Del Vecchio A, Falconi M, De Cobelli F & Fiorino C (2023) 'Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients', La Radiologia Medica, http://dx.doi.org/10.1007/s11547-023-01649-y
    Key Findings: In this work SPAARC was used to extract imaging features from 144 patients with pre-surgical high contrast Computed Tomography (CT) to investigate the variation of the discriminative power of CT radiomic features (RF) against image discretization/interpolation in predicting early distant relapses (EDR) in pancreatic cancer. We found that such discriminative power is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.
  • Mori M, Deantoni C, Olivieri M, Spezi E, Chiara A, Baroni S, et al. (2023) 'External validation of an 18F-FDG-PET radiomic model predicting survival after radiotherapy for oropharyngeal cancer', Eur J Nucl Med Mol Imaging, https://doi.org/10.1007/s00259-022-06098-9
    Key Findings: In this work SPAARC was used to extract imaging features from 18F-FDG-PET of 100 oropharyngeal cancer patients (stage IV: 78/100). A previously published PET radiomic model for cancer-specific survival prediction was independently validated. Performances of the model were similar to the ones of using only the metabolic tumour volume with no improvement in prediction accuracy.
  • Mori M, Palumbo D, Muffatti F, Partelli S, Mushtaq J, Andreasi V, et al. (2022) 'Prediction of the Characteristics of Aggressiveness of Pancreatic Neuroendocrine Neoplasms (PanNENs) Based on CT Radiomic Features', Eur Radiol, https://doi.org/10.1007/s00330-022-09351-9
    Key Findings: This work combined SPAARC radiomic features extracted from preoperative contrast-enhanced CT images and clinical-radiological features to predict before surgery the histological characteristics of pancreatic neuroendocrine neoplasms.
  • Whybra P (2021) 'Standardisation and Optimisation of Radiomic Techniques for the Identification of Robust Imaging Biomarkers in Oncology', PhD Thesis, Cardiff University, https://orca.cardiff.ac.uk/id/eprint/144441
    Key Findings: This work laid the foundation to the development of SPAARC. Results from this work significantly contributed to a large collaborative consensus benchmarking effort to address the need of standardisation in quantitative image analysis.
  • Palumbo D, Mori M, Prato F, Crippa S, Belfiori G, Reni M, et al. (2021) 'Prediction of Early Distant Recurrence in Upfront Resectable Pancreatic Adenocarcinoma: A Multidisciplinary, Machine Learning-Based Approach', Cancers (Basel), https://doi.org/10.3390/cancers13194938
    Key Findings: This work developed a preoperative model to accurately stratify upfront resectable pancreatic cancer patients according to the risk of early distant disease relapse after surgery. SPAARC based radiomic feature, combined with a biochemical marker and radiological finding was found to be significantly associated with early distant recurrence. The model allowed, in the studied cohort, the identification of patients at high risk for early distant disease relapse who would benefit from neoadjuvant chemotherapy instead of upfront surgery.
  • Zwanenburg A, Vallières M, Abdalah MA, Aerts HJWL, Andrearczyk V, Apte A, et al. (2020) 'The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping', Radiology, https://doi.org/10.1148/radiol.2020191145