Saved in:
Bibliographic Details
Main Authors: Caragliano, Alice Natalina, Farina, Giulia, Aksu, Fatih, Caruso, Camillo Maria, Tacconi, Claudia, Greco, Carlo, Nibid, Lorenzo, Ippolito, Edy, Fiore, Michele, Perrone, Giuseppe, Ramella, Sara, Soda, Paolo, Guarrasi, Valerio
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.15100
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915866670530560
author Caragliano, Alice Natalina
Farina, Giulia
Aksu, Fatih
Caruso, Camillo Maria
Tacconi, Claudia
Greco, Carlo
Nibid, Lorenzo
Ippolito, Edy
Fiore, Michele
Perrone, Giuseppe
Ramella, Sara
Soda, Paolo
Guarrasi, Valerio
author_facet Caragliano, Alice Natalina
Farina, Giulia
Aksu, Fatih
Caruso, Camillo Maria
Tacconi, Claudia
Greco, Carlo
Nibid, Lorenzo
Ippolito, Edy
Fiore, Michele
Perrone, Giuseppe
Ramella, Sara
Soda, Paolo
Guarrasi, Valerio
contents Major pathological response (pR) following neoadjuvant therapy is a clinically meaningful endpoint in non-small cell lung cancer, strongly associated with improved survival. However, accurate preoperative prediction of pR remains challenging, particularly in real-world clinical settings characterized by limited data availability and incomplete clinical profiles. In this study, we propose a multimodal deep learning framework designed to address these constraints by integrating foundation model-based CT feature extraction with a missing-aware architecture for clinical variables. This approach enables robust learning from small cohorts while explicitly modeling missing clinical information, without relying on conventional imputation strategies. A weighted fusion mechanism is employed to leverage the complementary contributions of imaging and clinical modalities, yielding a multimodal model that consistently outperforms both unimodal imaging and clinical baselines. These findings underscore the added value of integrating heterogeneous data sources and highlight the potential of multimodal, missing-aware systems to support pR prediction under realistic clinical conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15100
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning from Limited and Incomplete Data: A Multimodal Framework for Predicting Pathological Response in NSCLC
Caragliano, Alice Natalina
Farina, Giulia
Aksu, Fatih
Caruso, Camillo Maria
Tacconi, Claudia
Greco, Carlo
Nibid, Lorenzo
Ippolito, Edy
Fiore, Michele
Perrone, Giuseppe
Ramella, Sara
Soda, Paolo
Guarrasi, Valerio
Computer Vision and Pattern Recognition
Major pathological response (pR) following neoadjuvant therapy is a clinically meaningful endpoint in non-small cell lung cancer, strongly associated with improved survival. However, accurate preoperative prediction of pR remains challenging, particularly in real-world clinical settings characterized by limited data availability and incomplete clinical profiles. In this study, we propose a multimodal deep learning framework designed to address these constraints by integrating foundation model-based CT feature extraction with a missing-aware architecture for clinical variables. This approach enables robust learning from small cohorts while explicitly modeling missing clinical information, without relying on conventional imputation strategies. A weighted fusion mechanism is employed to leverage the complementary contributions of imaging and clinical modalities, yielding a multimodal model that consistently outperforms both unimodal imaging and clinical baselines. These findings underscore the added value of integrating heterogeneous data sources and highlight the potential of multimodal, missing-aware systems to support pR prediction under realistic clinical conditions.
title Learning from Limited and Incomplete Data: A Multimodal Framework for Predicting Pathological Response in NSCLC
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.15100