Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency

Graph neural networks could compare the difference among all samples (nodes in graph) and transmit the interrelationship among them to obtain a global landscape. Compared with radiomics and clinical feature‐based machine learning methods, whether a graph convolutional neural network (GCNN) based on...

Full description

Saved in:
Bibliographic Details
Main Authors: Renjie Xu, Zhanlue Liang, Dan Wang, Rui Zhang, Jiayi Li, Lingfeng Bi, Kai Zhang, Weimin Li
Format: Article
Language:English
Published: Wiley 2025-08-01
Series:Advanced Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1002/aisy.202400874
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849230095787491328
author Renjie Xu
Zhanlue Liang
Dan Wang
Rui Zhang
Jiayi Li
Lingfeng Bi
Kai Zhang
Weimin Li
author_facet Renjie Xu
Zhanlue Liang
Dan Wang
Rui Zhang
Jiayi Li
Lingfeng Bi
Kai Zhang
Weimin Li
author_sort Renjie Xu
collection DOAJ
description Graph neural networks could compare the difference among all samples (nodes in graph) and transmit the interrelationship among them to obtain a global landscape. Compared with radiomics and clinical feature‐based machine learning methods, whether a graph convolutional neural network (GCNN) based on radiomics and clinical features improve the performance in distinguishing benign and malignant pulmonary nodules is not well studied. We propose an approach based on multimodal GCNNs that integrates patients’ lung computed tomography images with clinical information to differentiate between benign and malignant pulmonary nodules. Leveraging large‐scale and multisource data from multiple hospitals (i.e., 6033/290/524 patients for three hospitals respectively) enhances the diversity of features. Accuracy, sensitivity, specificity, precision, and area under the receiver operating characteristic curve (AUROC) are used to evaluate the performance. We achieved the average accuracy/sensitivity/specificity/AUROC of 0.8612/0.9425/0.6786/0.9025 for the main dataset via the novel GCNN proposed, respectively, maintaining the robustness of the deep learning procedures. Especially for the external testing dataset (hospital 2/hospital 3), the specificity is much higher than comparison methods (0.6250–0.6731 vs. 0.2569–0.2788). The graph neural network‐based deep learning method holds the potential to assist clinicians, aiding in treatment planning, patient management, follow‐up strategies, resource optimization, and overall healthcare decision‐making.
format Article
id doaj-art-8b6af75564f645d48b0c9ee0181bde18
institution Kabale University
issn 2640-4567
language English
publishDate 2025-08-01
publisher Wiley
record_format Article
series Advanced Intelligent Systems
spelling doaj-art-8b6af75564f645d48b0c9ee0181bde182025-08-21T11:05:47ZengWileyAdvanced Intelligent Systems2640-45672025-08-0178n/an/a10.1002/aisy.202400874Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity ProficiencyRenjie Xu0Zhanlue Liang1Dan Wang2Rui Zhang3Jiayi Li4Lingfeng Bi5Kai Zhang6Weimin Li7Department of Pulmonary and Critical Care Medicine West China Hospital Sichuan University Chengdu 610041 Sichuan ChinaDepartment of Pulmonary and Critical Care Medicine West China Hospital Sichuan University Chengdu 610041 Sichuan ChinaDepartment of Pulmonary and Critical Care Medicine West China Hospital Sichuan University Chengdu 610041 Sichuan ChinaDepartment of Pulmonary and Critical Care Medicine West China Hospital Sichuan University Chengdu 610041 Sichuan ChinaDepartment of Pulmonary and Critical Care Medicine West China Hospital Sichuan University Chengdu 610041 Sichuan ChinaDepartment of Pulmonary and Critical Care Medicine West China Hospital Sichuan University Chengdu 610041 Sichuan ChinaInstitute of Advanced Research Infervision Medical Technology Co., Ltd. Shanghai 200032 ChinaDepartment of Pulmonary and Critical Care Medicine West China Hospital Sichuan University Chengdu 610041 Sichuan ChinaGraph neural networks could compare the difference among all samples (nodes in graph) and transmit the interrelationship among them to obtain a global landscape. Compared with radiomics and clinical feature‐based machine learning methods, whether a graph convolutional neural network (GCNN) based on radiomics and clinical features improve the performance in distinguishing benign and malignant pulmonary nodules is not well studied. We propose an approach based on multimodal GCNNs that integrates patients’ lung computed tomography images with clinical information to differentiate between benign and malignant pulmonary nodules. Leveraging large‐scale and multisource data from multiple hospitals (i.e., 6033/290/524 patients for three hospitals respectively) enhances the diversity of features. Accuracy, sensitivity, specificity, precision, and area under the receiver operating characteristic curve (AUROC) are used to evaluate the performance. We achieved the average accuracy/sensitivity/specificity/AUROC of 0.8612/0.9425/0.6786/0.9025 for the main dataset via the novel GCNN proposed, respectively, maintaining the robustness of the deep learning procedures. Especially for the external testing dataset (hospital 2/hospital 3), the specificity is much higher than comparison methods (0.6250–0.6731 vs. 0.2569–0.2788). The graph neural network‐based deep learning method holds the potential to assist clinicians, aiding in treatment planning, patient management, follow‐up strategies, resource optimization, and overall healthcare decision‐making.https://doi.org/10.1002/aisy.202400874computed tomographydeep learninggraph neural networksmultimodal featurespersonalized diagnosespulmonary nodules
spellingShingle Renjie Xu
Zhanlue Liang
Dan Wang
Rui Zhang
Jiayi Li
Lingfeng Bi
Kai Zhang
Weimin Li
Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency
Advanced Intelligent Systems
computed tomography
deep learning
graph neural networks
multimodal features
personalized diagnoses
pulmonary nodules
title Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency
title_full Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency
title_fullStr Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency
title_full_unstemmed Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency
title_short Classification of Pulmonary Nodules Using Multimodal Feature‐Driven Graph Convolutional Networks with Specificity Proficiency
title_sort classification of pulmonary nodules using multimodal feature driven graph convolutional networks with specificity proficiency
topic computed tomography
deep learning
graph neural networks
multimodal features
personalized diagnoses
pulmonary nodules
url https://doi.org/10.1002/aisy.202400874
work_keys_str_mv AT renjiexu classificationofpulmonarynodulesusingmultimodalfeaturedrivengraphconvolutionalnetworkswithspecificityproficiency
AT zhanlueliang classificationofpulmonarynodulesusingmultimodalfeaturedrivengraphconvolutionalnetworkswithspecificityproficiency
AT danwang classificationofpulmonarynodulesusingmultimodalfeaturedrivengraphconvolutionalnetworkswithspecificityproficiency
AT ruizhang classificationofpulmonarynodulesusingmultimodalfeaturedrivengraphconvolutionalnetworkswithspecificityproficiency
AT jiayili classificationofpulmonarynodulesusingmultimodalfeaturedrivengraphconvolutionalnetworkswithspecificityproficiency
AT lingfengbi classificationofpulmonarynodulesusingmultimodalfeaturedrivengraphconvolutionalnetworkswithspecificityproficiency
AT kaizhang classificationofpulmonarynodulesusingmultimodalfeaturedrivengraphconvolutionalnetworkswithspecificityproficiency
AT weiminli classificationofpulmonarynodulesusingmultimodalfeaturedrivengraphconvolutionalnetworkswithspecificityproficiency