The 2nd UPLIFT School for “Artificial Intelligence in Radiotherapy”

Session

Session B

6 Nov 2026, 13:00

Congressi Stefano Franscini (CSF)

75. Accuracy of an open-source, deep-learning body composition measurement on PET/CTs in a large cohort

Nick Hardcastle (Peter MacCallum Cancer Centre)

06/11/2026, 13:00

oral/poster

Objectives
Sarcopenia is characterised by loss of skeletal muscle mass and strength, impacting physical performance and quality of life in people with cancer. In neuroendocrine tumours (NETs) it is associated with poor prognosis, but large-scale evidence quantifying its prevalence and changes with disease progression, treatment and nutritional interventions is lacking. Whole-body CTs acquired...

67. Structure-Level Uncertainty for Quality Control in Prostate MRI Segmentation under Image Degradation

Chuxin Zhang (UCLouvain)

06/11/2026, 13:30

1

oral/poster

Objective

In MR-guided adaptive radiotherapy (MRgRT) for prostate cancer, daily target re-delineation is required to account for inter-fraction anatomical changes, requiring rapid and reliable auto-segmentation. Image-quality degradation from acquisition- and patient-related factors can impair prostate MRI segmentation and may also affect uncertainty estimates. We systematically...

71. Quantitative imaging and explainable AI identify survival phenotypes for personalised radiotherapy in locally advanced NSCLC

Alessandra Catalano (Fondazione IRCCS Istituto Nazionale dei Tumori, Milano)

06/11/2026, 14:00

oral/poster

Objective
To develop an explainable artificial intelligence framework integrating radiotherapy dosimetry and quantitative imaging to identify survival-related patient phenotypes and inform personalised dose optimisation in locally advanced non-small cell lung cancer (LA-NSCLC).

Methods
This multicentre retrospective study included 388 patients treated with curative-intent...

69. A real association is not a usable predictor: a five-stage workflow for machine learning on routine radiotherapy QA data

Alejandro del Pozo Domínguez

06/11/2026, 14:30

oral/poster

Objective
Radiotherapy services routinely generate machine and dosimetric QA data, rarely analysed together. We propose a reproducible five-stage workflow for developing machine-learning models from such data, focusing on the step least often addressed: establishing whether exploitable signal exists, and distinguishing a genuine but weak physical association from useful predictive...