Saved in:
Bibliographic Details
Main Authors: Imbriani, Manuela, Belmonte, Gina, Massink, Mieke, Tofani, Alessandro, Ciancia, Vincenzo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.12741
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911109825429504
author Imbriani, Manuela
Belmonte, Gina
Massink, Mieke
Tofani, Alessandro
Ciancia, Vincenzo
author_facet Imbriani, Manuela
Belmonte, Gina
Massink, Mieke
Tofani, Alessandro
Ciancia, Vincenzo
contents This paper presents preliminary results in the definition of a comprehensive benchmark framework designed to systematically evaluate spatial reasoning capabilities in neural networks, with a particular focus on morphological properties such as connectivity and distance relationships. The framework is currently being used to study the capabilities of nnU-Net, exploiting the spatial model checker VoxLogicA to generate two distinct categories of synthetic datasets: maze connectivity problems for topological analysis and spatial distance computation tasks for geometric understanding. Each category is evaluated across multiple resolutions to assess scalability and generalization properties. The automated pipeline encompasses a complete machine learning workflow including: synthetic dataset generation, standardized training with cross-validation, inference execution, and comprehensive evaluation using Dice coefficient and IoU (Intersection over Union) metrics. Preliminary experimental results demonstrate significant challenges in neural network spatial reasoning capabilities, revealing systematic failures in basic geometric and topological understanding tasks. The framework provides a reproducible experimental protocol, enabling researchers to identify specific limitations. Such limitations could be addressed through hybrid approaches combining neural networks with symbolic reasoning methods for improved spatial understanding in clinical applications, establishing a foundation for ongoing research into neural network spatial reasoning limitations and potential solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12741
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Multi-Resolution Benchmark Framework for Spatial Reasoning Assessment in Neural Networks
Imbriani, Manuela
Belmonte, Gina
Massink, Mieke
Tofani, Alessandro
Ciancia, Vincenzo
Machine Learning
Applied Physics
Medical Physics
This paper presents preliminary results in the definition of a comprehensive benchmark framework designed to systematically evaluate spatial reasoning capabilities in neural networks, with a particular focus on morphological properties such as connectivity and distance relationships. The framework is currently being used to study the capabilities of nnU-Net, exploiting the spatial model checker VoxLogicA to generate two distinct categories of synthetic datasets: maze connectivity problems for topological analysis and spatial distance computation tasks for geometric understanding. Each category is evaluated across multiple resolutions to assess scalability and generalization properties. The automated pipeline encompasses a complete machine learning workflow including: synthetic dataset generation, standardized training with cross-validation, inference execution, and comprehensive evaluation using Dice coefficient and IoU (Intersection over Union) metrics. Preliminary experimental results demonstrate significant challenges in neural network spatial reasoning capabilities, revealing systematic failures in basic geometric and topological understanding tasks. The framework provides a reproducible experimental protocol, enabling researchers to identify specific limitations. Such limitations could be addressed through hybrid approaches combining neural networks with symbolic reasoning methods for improved spatial understanding in clinical applications, establishing a foundation for ongoing research into neural network spatial reasoning limitations and potential solutions.
title A Multi-Resolution Benchmark Framework for Spatial Reasoning Assessment in Neural Networks
topic Machine Learning
Applied Physics
Medical Physics
url https://arxiv.org/abs/2508.12741