A field strength independent MR radiomics model to predict pathological complete response in locally advanced rectal cancer

Davide Cusumano, Gert Meijer, Jacopo Lenkowicz, Giuditta Chiloiro, Luca Boldrini, Carlotta Masciocchi, Nicola Dinapoli, Roberto Gatta, Calogero Casà, Andrea Damiani, Brunella Barbaro, Maria Antonietta Gambacorta, Luigi Azario, Marco De Spirito, Martijn Intven, Vincenzo Valentini

Research output: Contribution to journalArticlepeer-review

Abstract

PURPOSE: Aim of this study was to develop a generalised radiomics model for predicting pathological complete response after neoadjuvant chemo-radiotherapy in locally advanced rectal cancer patients using pre-CRT T2-weighted images acquired at a 1.5 T and a 3 T scanner.

METHODS: In two institutions, 195 patients were scanned: 136 patients were scanned on a 1.5 T MR scanner, 59 patients on a 3 T MR scanner. Gross tumour volumes were delineated on the MR images and 496 radiomic features were extracted, applying the intensity-based (IB) filter. Features were standardised with Z-score normalisation and an initial feature selection was carried out using Wilcoxon-Mann-Whitney test: The most significant features at 1.5 T and 3 T were selected as main features. Several logistic regression models combining the main features with a third one selected by those resulting significant were elaborated and evaluated in terms of area under curve (AUC). A tenfold cross-validation was repeated 300 times to evaluate the model robustness.

RESULTS: Three features were selected: maximum fractal dimension with IB = 0-50, energy and grey-level non-uniformity calculated on the run-length matrix with IB = 0-50. The AUC of the model applied to the whole dataset after cross-validation was 0.72, while values of 0.70 and 0.83 were obtained when 1.5 T and 3 T patients were considered, respectively.

CONCLUSIONS: The model elaborated showed good performance, even when data from patients scanned on 1.5 T and 3 T were merged. This shows that magnetic field intensity variability can be overcome by means of selecting appropriate image features.

Original languageEnglish
Pages (from-to)421-429
Number of pages9
JournalRadiol. Med.
Volume126
Issue number3
DOIs
Publication statusPublished - Mar 2021

Fingerprint Dive into the research topics of 'A field strength independent MR radiomics model to predict pathological complete response in locally advanced rectal cancer'. Together they form a unique fingerprint.

Cite this