One scale to rule them all: interpretable multi-scale Deep Learning for predicting cell survival after proton and carbon ion irradiation

TL;DR

This paper introduces an interpretable deep learning model that predicts cell survival after proton and carbon ion irradiation by integrating multi-scale physical and biological data, providing insights into energy deposition effects.

Contribution

The study presents a novel multi-scale, interpretable deep learning approach that combines various physical quantities to predict biological damage, enhancing understanding of energy deposition scales in radiobiology.

Findings

High predictive accuracy for cell survival and RBE.

Multiple energy deposition scales contribute without a single dominant scale.

Smaller spatial domain quantities have greater influence than LET.

Abstract

The relationship between the physical characteristics of the radiation field and biological damage is central to both radiotherapy and radioprotection, yet the link between spatial scales of energy deposition and biological effects remains not entirely understood. To address this, we developed an interpretable deep learning model that predicts cell survival after proton and carbon ion irradiation, leveraging sequential attention to highlight relevant features and provide insight into the contribution of different energy deposition scales. Trained and tested on the PIDE dataset, our model incorporates, beside LET, nanodosimetric and microdosimetric quantities simulated with MC-Startrack and Open-TOPAS, enabling multi-scale characterization. While achieving high predictive accuracy, our approach also emphasizes transparency in decision-making. We demonstrate high accuracy in predicting RBE for in vitro experiments. Multiple scales are utilized concurrently, with no single spatial scale being predominant. Quantities defined at smaller spatial domains generally have a greater influence, whereas the LET plays a lesser role.