Multimodal multi-instance evidence fusion neural networks for cancer survival prediction

Abstract Accurate cancer survival prediction plays a crucial role in assisting clinicians in formulating treatment plans. Multimodal data, such as histopathological images, genomic data, and clinical information, provide complementary and comprehensive information, significantly enhancing the accura...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Luo, Jiashuang Huang, Hengrong Ju, Tianyi Zhou, Weiping Ding
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-93770-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850208140584288256
author Hui Luo
Jiashuang Huang
Hengrong Ju
Tianyi Zhou
Weiping Ding
author_facet Hui Luo
Jiashuang Huang
Hengrong Ju
Tianyi Zhou
Weiping Ding
author_sort Hui Luo
collection DOAJ
description Abstract Accurate cancer survival prediction plays a crucial role in assisting clinicians in formulating treatment plans. Multimodal data, such as histopathological images, genomic data, and clinical information, provide complementary and comprehensive information, significantly enhancing the accuracy of this task. However, existing methods, despite achieving some promising results, still exhibit two significant limitations: they fail to effectively utilize global context and overlook the uncertainty of different modalities, which may lead to unreliable predictions. In this study, we propose a multimodal multi-instance evidence fusion neural network for cancer survival prediction, called M2EF-NNs. Specifically, to better capture global information from images, we employ a pre-trained vision transformer model to extract patch feature embeddings from histopathological images. Additionally, we are the first to apply the Dempster–Shafer evidence theory to the cancer survival prediction task and introduce subjective logic to estimate the uncertainty of different modalities. We then dynamically adjust the weights of the class probability distribution after multimodal fusion based on the estimated evidence from the fused multimodal data to achieve trusted survival prediction. Finally, the experimental results on three cancer datasets demonstrate that our method significantly improves cancer survival prediction regarding overall C-index and AUC, thereby validating the model’s reliability.
format Article
id doaj-art-bcf5fc4ecaaa4b948852b2d07ee8dcae
institution OA Journals
issn 2045-2322
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-bcf5fc4ecaaa4b948852b2d07ee8dcae2025-08-20T02:10:17ZengNature PortfolioScientific Reports2045-23222025-03-0115111510.1038/s41598-025-93770-3Multimodal multi-instance evidence fusion neural networks for cancer survival predictionHui Luo0Jiashuang Huang1Hengrong Ju2Tianyi Zhou3Weiping Ding4Faculty of Data Science, City University of MacauSchool of Artificial Intelligence and Computer Science, Nantong UniversitySchool of Artificial Intelligence and Computer Science, Nantong UniversitySchool of Artificial Intelligence and Computer Science, Nantong UniversityFaculty of Data Science, City University of MacauAbstract Accurate cancer survival prediction plays a crucial role in assisting clinicians in formulating treatment plans. Multimodal data, such as histopathological images, genomic data, and clinical information, provide complementary and comprehensive information, significantly enhancing the accuracy of this task. However, existing methods, despite achieving some promising results, still exhibit two significant limitations: they fail to effectively utilize global context and overlook the uncertainty of different modalities, which may lead to unreliable predictions. In this study, we propose a multimodal multi-instance evidence fusion neural network for cancer survival prediction, called M2EF-NNs. Specifically, to better capture global information from images, we employ a pre-trained vision transformer model to extract patch feature embeddings from histopathological images. Additionally, we are the first to apply the Dempster–Shafer evidence theory to the cancer survival prediction task and introduce subjective logic to estimate the uncertainty of different modalities. We then dynamically adjust the weights of the class probability distribution after multimodal fusion based on the estimated evidence from the fused multimodal data to achieve trusted survival prediction. Finally, the experimental results on three cancer datasets demonstrate that our method significantly improves cancer survival prediction regarding overall C-index and AUC, thereby validating the model’s reliability.https://doi.org/10.1038/s41598-025-93770-3Survival predictionMultimodal fusionVision transformerDempster–Shafer evidence theory
spellingShingle Hui Luo
Jiashuang Huang
Hengrong Ju
Tianyi Zhou
Weiping Ding
Multimodal multi-instance evidence fusion neural networks for cancer survival prediction
Scientific Reports
Survival prediction
Multimodal fusion
Vision transformer
Dempster–Shafer evidence theory
title Multimodal multi-instance evidence fusion neural networks for cancer survival prediction
title_full Multimodal multi-instance evidence fusion neural networks for cancer survival prediction
title_fullStr Multimodal multi-instance evidence fusion neural networks for cancer survival prediction
title_full_unstemmed Multimodal multi-instance evidence fusion neural networks for cancer survival prediction
title_short Multimodal multi-instance evidence fusion neural networks for cancer survival prediction
title_sort multimodal multi instance evidence fusion neural networks for cancer survival prediction
topic Survival prediction
Multimodal fusion
Vision transformer
Dempster–Shafer evidence theory
url https://doi.org/10.1038/s41598-025-93770-3
work_keys_str_mv AT huiluo multimodalmultiinstanceevidencefusionneuralnetworksforcancersurvivalprediction
AT jiashuanghuang multimodalmultiinstanceevidencefusionneuralnetworksforcancersurvivalprediction
AT hengrongju multimodalmultiinstanceevidencefusionneuralnetworksforcancersurvivalprediction
AT tianyizhou multimodalmultiinstanceevidencefusionneuralnetworksforcancersurvivalprediction
AT weipingding multimodalmultiinstanceevidencefusionneuralnetworksforcancersurvivalprediction