Details

Autor(en) / Beteiligte

• Loi, Sara
• Mori, Martina
• Benedetti, Giulia
• Partelli, Stefano
• Broggi, Sara
• Cattaneo, Giovanni Mauro
• Palumbo, Diego
• Muffatti, Francesca
• Falconi, Massimo
• De Cobelli, Francesco
• Fiorino, Claudio

Titel

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

Ist Teil von

• Physica medica, 2020-08, Vol.76, p.125-133

Ort / Verlag

Elsevier Ltd

Erscheinungsjahr

2020

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• [Display omitted] •CT RF show large variations against voxel/pixel size and binning for PanNEN patients.•Despite this, the corresponding AUC changes in characterizing PanNEN are limited.•Using a single scanner or contrast images does not significantly affect the results.•Limiting the parameter’s set to “more clinical” ranges further reduces AUC changes. To explore the variation of the discriminative power of CT radiomic features (RF) against image discretization/interpolation in characterizing pancreatic neuro-endocrine (PanNEN) neoplasms. 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. 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. The discriminative power of CT RF for panNEN is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.