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

• URL: http://arxiv.org/abs/2601.15106v1
• Date: Wed, 21 Jan 2026 15:47:25 GMT
• Title: One scale to rule them all: interpretable multi-scale Deep Learning for predicting cell survival after proton and carbon ion irradiation
• Authors: Giulio Bordieri, Giorgio Cartechini, Anna Bianchi, Anna Selva, Valeria Conte, Marta Missiaggia, Francesco G. Cordoni,
• Abstract summary: Relationship between physical characteristics of the radiation field and biological damage is central to both radiotherapy and radioprotection.<n>We develop an interpretable deep learning model that predicts cell survival after proton and carbon ion irradiation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Linearized Optimal Transport for Analysis of High-Dimensional Point-Cloud and Single-Cell Data [45.87606039212519]
  Single-cell technologies generate high-dimensional point clouds of cells.<n>Each patient is represented by an irregular point cloud rather than a simple vector.<n>We adapt the Linear Optimal Transport framework to embed irregular point clouds into a fixed-dimensional Euclidean space.
  arXiv  Detail & Related papers  (2025-10-24T21:33:12Z)
• Foundation Models for Discovery and Exploration in Chemical Space [57.97784111110166]
  MIST is a family of molecular foundation models trained on large unlabeled datasets.<n>We demonstrate the ability of these models to solve real-world problems across chemical space.
  arXiv  Detail & Related papers  (2025-10-20T17:56:01Z)
• Engineering atomic superradiance scaling in cavity QED system with collective and individual emission channels [10.183516825271765]
  atom-photon coupling can significantly alter the emission behavior--suppressing the collective superradiant scaling while enhancing the scaling associated with individual atomic emissions.<n>Our study provides a pathway toward controllable collective emission in state-of-the-art experimental platforms.
  arXiv  Detail & Related papers  (2025-10-14T02:48:51Z)
• Latent-space Field Tension for Astrophysical Component Detection An application to X-ray imaging [0.0]
  We introduce a novel multi-frequency Bayesian model of the sky emission field that leverages latent-space tension as an indicator of model misspecification.<n>We demonstrate the effectiveness of this method on synthetic multi-frequency imaging data and apply it to observational X-ray data from the eROSITA Early Data Release (EDR) of the SN1987A region in the Large Magellanic Cloud (LMC)<n>Our results highlight the method's capability to reconstruct astrophysical components with high accuracy, achieving sub-pixel localization of point sources, robust separation of extended emission, and detailed uncertainty quantification.
  arXiv  Detail & Related papers  (2025-06-25T18:45:18Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• Directional superradiance in a driven ultracold atomic gas in free-space [0.0]
  We study a dense ensemble illuminated by a strong coherent drive while interacting via dipole-dipole interactions. Although the steady-state features some similarities to the reported superradiant to normal non-induced transition, we observe significant qualitative and quantitative differences. We develop a simple theoretical model that explains the scaling properties by accounting for interaction-equilibrium inhomogeneous effects and spontaneous emission.
  arXiv  Detail & Related papers  (2024-03-22T18:14:44Z)
• Disentangling CO Chemistry in a Protoplanetary Disk Using Explanatory Machine Learning Techniques [0.0]
  Molecular abundances in protoplanetary disks are highly sensitive to the local physical conditions. We present a new approach to understanding these chemical and physical interdependencies using machine learning.
  arXiv  Detail & Related papers  (2023-12-08T18:59:22Z)
• Machine learning enabled experimental design and parameter estimation for ultrafast spin dynamics [54.172707311728885]
  We introduce a methodology that combines machine learning with Bayesian optimal experimental design (BOED) Our method employs a neural network model for large-scale spin dynamics simulations for precise distribution and utility calculations in BOED. Our numerical benchmarks demonstrate the superior performance of our method in guiding XPFS experiments, predicting model parameters, and yielding more informative measurements within limited experimental time.
  arXiv  Detail & Related papers  (2023-06-03T06:19:20Z)
• Data-Efficient Learning via Minimizing Hyperspherical Energy [48.47217827782576]
  This paper considers the problem of data-efficient learning from scratch using a small amount of representative data. We propose a MHE-based active learning (MHEAL) algorithm, and provide comprehensive theoretical guarantees for MHEAL.
  arXiv  Detail & Related papers  (2022-06-30T11:39:12Z)
• Electronic-structure properties from atom-centered predictions of the electron density [0.0]
  electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models. We propose a gradient-based approach to minimize the loss function of the regression problem in an optimized and highly sparse feature space. We show that starting from the predicted density a single Kohn-Sham diagonalization step can be performed to access total energy components that carry an error of just 0.1 meV/atom.
  arXiv  Detail & Related papers  (2022-06-28T15:35:55Z)
• Deep Learning Models of the Discrete Component of the Galactic Interstellar Gamma-Ray Emission [61.26321023273399]
  A significant point-like component from the small scale (or discrete) structure in the H2 interstellar gas might be present in the Fermi-LAT data. We show that deep learning may be effectively employed to model the gamma-ray emission traced by these rare H2 proxies within statistical significance in data-rich regions.
  arXiv  Detail & Related papers  (2022-06-06T18:00:07Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.