ESTRO 2024 - Abstract Book

S5086

Physics - Radiomics, functional and biological imaging and outcome prediction

ESTRO 2024

et al. (2017) may need to be revisited to enhance interpretability and increase agreement between readers, particularly with RQS 2.0 still under development [3].

Keywords: systematic reviews, reproducibility, quality score

References:

1. Lambin, P., Leijenaar, R.T., Deist, T.M., Peerlings, J., De Jong, E.E., Van Timmeren, J., Sanduleanu, S., Larue, R.T., Even, A.J., Jochems, A. and Van Wijk, Y., 2017. Radiomics: the bridge between medical imaging and personalized medicine. Nature reviews Clinical oncology, 14(12), pp.749-762. 2. Spadarella, G., Stanzione, A., Akinci D’Antonoli, T., Andreychenko, A., Fanni, S.C., Ugga, L., Kotter, E. and Cuocolo, R., 2023. Systematic review of the radiomics quality score applications: an EuSoMII Radiomics Auditing Group Initiative. European Radiology, 33(3), pp.1884-1894.

3. https://www.radiomics.world/rqs2

1848

Digital Poster

Validating a PET radiomics model to predict distant relapse free survival for pancreatic cancer

Gabriele Palazzo 1 , Martina Mori 2 , Paolo Passoni 3 , Stefano Villa 3 , Sara Broggi 2 , Emiliano Spezi 4 , Maria Picchio 5 , Antonella Del Vecchio 2 , Claudio Fiorino 2 , Nadia Gisella Di Muzio 3,6 1 IRCCS San Raffaele Scientific Institute, Medical Physics, MIlan, Italy. 2 IRCCS San Raffaele Scientific Institute, Medical Physics, Milan, Italy. 3 IRCCS San Raffaele Scientific Institute, Radiotherapy, Milan, Italy. 4 Cardiff University, School of Engineering, Cardiff, United Kingdom. 5 IRCCS San Raffaele Scientific Institute, Nuclear Medicine, Milan, Italy. 6 Vita Salute San Raffaele University,, Medicine and Surgery, Milan, Italy

Purpose/Objective:

To validate the radiomics Cox survival model defined in Mori et al., Radiother Onc, 2020 (https://doi.org/10.1016/j.radonc.2020.07.003) [1] for the prediction of distant relapse free survival (DRFS) (176 patients: 116 train + 60 validation). Current results report the independent validation on patients treated at the same Institute at a different time with respect to the development of the model (i.e.: temporal validation).

Material/Methods:

The data cohort of the study consists of 36 patients from the same institution of the 176 patients on which the model was trained with Locally Advanced Pancreatic Cancer (LAPC) treated with radio-chemotherapy. Two radiomics