Search

Your search keyword '"Cobelli F"' showing total 21 results
Start Over Author "Cobelli F" Journal physica medica
21 results on '"Cobelli F"'

3. BOOTSTRAP-BASED MACHINE LEARNING TO ROBUSTLY CHARACTERIZE PANCREATIC NEUROENDOCRINE NEOPLASMS (PANNEN) BASED ON CT RADIOMIC FEATURES

Author

Mori, M., primary, Palumbo, D., additional, Muffatti, F., additional, Partelli, S., additional, Mushtaq, J., additional, Andreasi, V., additional, Prato, F., additional, Ubeira-Gabellini, M.G., additional, Palazzo, G., additional, Falconi, M., additional, Del Vecchio, A., additional, De Cobelli, F., additional, and Fiorino, C., additional

Published
2023
Full Text
View/download PDF

11. Predicting early mortality of COVID-19 patients of the first pandemic wave based on automatically extracted lung densitometry parameters

Author

Fiorino, C., primary, Mori, M., additional, Palumbo, D., additional, De Lorenzo, R., additional, Broggi, S., additional, Compagnone, N., additional, Guazzarotti, G., additional, Esposito, P.G., additional, Mazzilli, A., additional, Steidler, S., additional, Vitali, G.P., additional, Del Vecchio, A., additional, Querini, P.R., additional, and De Cobelli, F., additional

Published
2021
Full Text
View/download PDF

21. Robustness of CT radiomic features against image discretization and interpolation in characterizing pancreatic neuroendocrine neoplasms

Author

Massimo Falconi, Sara Loi, Claudio Fiorino, Giovanni Mauro Cattaneo, Diego Palumbo, Stefano Partelli, Francesco De Cobelli, Sara Broggi, M. Mori, Giulia Benedetti, Francesca Muffatti, Loi, S., Mori, M., Benedetti, G., Partelli, S., Broggi, S., Cattaneo, G. M., Palumbo, D., Muffatti, F., Falconi, M., De Cobelli, F., and Fiorino, C.

Subjects
Scanner, Percentile, Discretization, Biophysics, Contrast Media, General Physics and Astronomy, computer.software_genre, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Discriminative model, Voxel, Image Interpretation, Computer-Assisted, Image scaling, Humans, Radiology, Nuclear Medicine and imaging, Retrospective Studies, Mathematics, Pancreatic tumors, Radiomics, Pixel, business.industry, Pattern recognition, General Medicine, Tumor Burden, Pancreatic Neoplasms, Neuroendocrine Tumors, ROC Curve, Area Under Curve, 030220 oncology & carcinogenesis, CT imaging, Artificial intelligence, Neoplasm Grading, Tomography, X-Ray Computed, business, computer, Interpolation
Abstract

Purpose: To explore the variation of the discriminative power of CT radiomic features (RF) against image discretization/interpolation in characterizing pancreatic neuro-endocrine (PanNEN) neoplasms. Materials and methods: Thirty-nine PanNEN patients with pre-surgical high contrast CT available were considered. Image interpolation and discretization parameters were intentionally changed, including pixel size (0.73–2.19 mm2), slice thickness (2–5 mm) and binning (32–128 grey levels) and their combination generated 27 parameter's set. The ability of 69 RF in discriminating post-surgically assessed tumor grade (>G1), positive nodes, metastases and vascular invasion was tested: AUC changes when changing the parameters were quantified for selected RF, significantly associated to each end-point. The analysis was repeated for the corresponding images with contrast medium and in a sub-group of 29/39 patients scanned on a single scanner. Results: The median tumor volume was 1.57 cm3 (16%-84% percentiles: 0.62–34.58 cm3). RF variability against discretization/interpolation parameters was large: only 21/69 RF showed %COV < 20%. Despite this variability, AUC changes were limited for all end-points: with typical AUC values around 0.75–0.85, AUC ranges for the 27 parameter's set were on average 0.062 (1SD:0.037) for all end-points with maximum %COV equal to 5.5% (mean:2.3%). Performances significantly improved when excluding the 5 mm thickness case and fixing the binning to 64 (mean AUC range: 0.036, 1SD:0.019). Using contrast images or limiting the population to single-scanner patients had limited impact on AUC variability. Conclusions: The discriminative power of CT RF for panNEN is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results