Chiara Arilli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chiara Arilli has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Cinzia Talamonti
Dep. of Experimental and Biomedical Clinical Science,University of Florence,Florence,Italy; Istituto Nazionale di Fisica Nucleare, Sezione di Firenze,Florence,Italy, Italy
3 shared publications - Livia Marrazzo
University of Florence, Department of Experimental and Clinical Biomedical Sciences "Mario Serio", Firenze, Italy; Careggi University Hospital, Medical Physics Unit, Firenze, Italy
3 shared publications - Lorenzo Livi
Department of Experimental and Clinical Biomedical Sciences “M. Serio”, University of Florence, 50134 Florence, Italy
2 shared publications - Marta Casati
Medical Physics Unit,Azienda Ospedaliero-Universitaria Careggi,Florence,Italy, Italy
2 shared publications - Stefania Pallotta
Department of Experimental and Clinical Biomedical Sciences "M. Serio", University of Florence, 50134 Florence, Italy; Medical Physics Unit, Azienda Ospedaliero-Universitaria Careggi, Florence, Italy
2 shared publications - Alessandra Retico
National Institute for Nuclear Physics (INFN), Pisa Division, 56127 Pisa, Italy
1 shared publication
Latest Publications
- Open Access
- 30 October 2026
- Published by MDPI AG in Preprints.org
A Robust and Explainable Radiomics Pipeline for Small Multimodal Datasets to Predict Metastasis in Patients with Soft Tissue Sarcoma
Preoperative radiotherapy and surgery are standard treatments for high-risk soft tissue sarcomas (STS), yet distant metastasis remains a significant clinical challenge. This study aims to develop a robust and interpretable multi-omics predictive model for metastasis, specifically addressing the limitations of small datasets. A retrospective analysis included 40 STS patients (23 with metastasis) treated with preoperative radiotherapy and surgery. Using PyRadiomics, 107 radiomic and dosiomic features were extracted from CT scans, dose distributions, and post-treatment contrast-enhanced T1-weighted MRI. A Logistic Regression classifier with L1 regularization was identified as optimal and rigorously evaluated via Stratified 5-Fold Cross-Validation repeated 100 times. Single-modality models demonstrated limited predictive performance, yielding mean AUC-ROC values of 0.52 for CT, 0.59 for dose distribution, and 0.62 for normalized MRI. Integrating these features into a combined multi-omics signature substantially improved the mean AUC-ROC to 0.75. Furthermore, model explainability was ensured using Log-Odds to identify key predictive features. Combining anatomical, dosiomic, and MRI-derived features significantly enhances the prediction of metastatic relapse in STS patients. This interpretable approach shows strong potential for guiding personalized clinical treatments.
- 30 October 2026
- Published by MDPI AG in Preprints.org
Open AccessA Robust and Explainable Radiomics Pipeline for Small Multimodal Datasets to Predict Metastasis in Patients with Soft Tissue Sarcoma
Preoperative radiotherapy and surgery are standard treatments for high-risk soft tissue sarcomas (STS), yet distant metastasis remains a significant clinical challenge. This study aims to develop a robust and interpretable multi-omics predictive model for metastasis, specifically addressing the limitations of small datasets. A retrospective analysis included 40 STS patients (23 with metastasis) treated with preoperative radiotherapy and surgery. Using PyRadiomics, 107 radiomic and dosiomic features were extracted from CT scans, dose distributions, and post-treatment contrast-enhanced T1-weighted MRI. A Logistic Regression classifier with L1 regularization was identified as optimal and rigorously evaluated via Stratified 5-Fold Cross-Validation repeated 100 times. Single-modality models demonstrated limited predictive performance, yielding mean AUC-ROC values of 0.52 for CT, 0.59 for dose distribution, and 0.62 for normalized MRI. Integrating these features into a combined multi-omics signature substantially improved the mean AUC-ROC to 0.75. Furthermore, model explainability was ensured using Log-Odds to identify key predictive features. Combining anatomical, dosiomic, and MRI-derived features significantly enhances the prediction of metastatic relapse in STS patients. This interpretable approach shows strong potential for guiding personalized clinical treatments.
- 1 October 2021
- Published by Elsevier in Physica Medica
- Vol. 90, 115-122
Automatic VMAT technique to treat glioblastoma: A two years’ experience
- 1 October 2021
- Published by Elsevier in Physica Medica
- Vol. 90, 115-122
Automatic VMAT technique to treat glioblastoma: A two years’ experience
- Open Access
- 28 October 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (21) , 7611
Combined Use of a Transmission Detector and an EPID-Based In Vivo Dose Monitoring System in External Beam Whole Breast Irradiation: A Study with an Anthropomorphic Female Phantom
We evaluate the combined usage of two systems, the Integral Quality Monitor (IQM) transmission detector and SoftDiso software, for in vivo dose monitoring by simultaneous detection of delivery and patient setup errors in whole breast irradiation. An Alderson RANDO phantom was adapted with silicon breast prostheses to mimic the female anatomy. Plans with simulated delivery errors were created from a reference left breast plan, and patient setup errors were simulated by moving the phantom. Deviations from reference values recorded by both monitoring systems were measured for all plans and phantom positions. A 2D global gamma analysis was performed in SoftDiso for all phantom displacements. Both IQM signals and SoftDiso R-values are sensitive to small MU variations. However, only IQM is sensitive to jaw position variations. Conversely, IQM is unable to detect patient positioning errors, and the R-value has good sensitivity to phantom displacements. A gamma comparison analysis allows one to determine alert thresholds to detect phantom shifts or relatively large rotations. The combined use of the IQM and SoftDiso allows for fast identification of both delivery and setup errors and substantially reduces the impact of error identification and correction on the treatment workflow.
- 28 October 2020
- Published by MDPI AG in Applied Sciences
- Vol. 10 (21) , 7611
Open AccessCombined Use of a Transmission Detector and an EPID-Based In Vivo Dose Monitoring System in External Beam Whole Breast Irradiation: A Study with an Anthropomorphic Female Phantom
We evaluate the combined usage of two systems, the Integral Quality Monitor (IQM) transmission detector and SoftDiso software, for in vivo dose monitoring by simultaneous detection of delivery and patient setup errors in whole breast irradiation. An Alderson RANDO phantom was adapted with silicon breast prostheses to mimic the female anatomy. Plans with simulated delivery errors were created from a reference left breast plan, and patient setup errors were simulated by moving the phantom. Deviations from reference values recorded by both monitoring systems were measured for all plans and phantom positions. A 2D global gamma analysis was performed in SoftDiso for all phantom displacements. Both IQM signals and SoftDiso R-values are sensitive to small MU variations. However, only IQM is sensitive to jaw position variations. Conversely, IQM is unable to detect patient positioning errors, and the R-value has good sensitivity to phantom displacements. A gamma comparison analysis allows one to determine alert thresholds to detect phantom shifts or relatively large rotations. The combined use of the IQM and SoftDiso allows for fast identification of both delivery and setup errors and substantially reduces the impact of error identification and correction on the treatment workflow.