文献类型：期刊文献

英文题名：MI2A: A Multimodal Information Interaction Architecture for Automated Diagnosis of Lung Nodules Using PET/CT Imaging

作者：Li, Kai[1];Li, Tongtong[2];Zhang, Lei[3];Mao, Junfeng[4,5];Shi, Xuerong[2];Yao, Zhijun[2];Fang, Lei[6];Hu, Bin[2]

第一作者：Li, Kai

通信作者：Yao, ZJ[1];Hu, B[1];Fang, L[2]

机构：[1]Lanzhou Univ, Sch Math & Stat, Lanzhou 730000, Peoples R China;[2]Lanzhou Univ, Sch Informat Sci & Engn, Gansu Prov Key Lab Wearable Comp, Lanzhou 730000, Peoples R China;[3]Hexi Univ, Coll Informat Technol & Commun, Zhangye 734000, Peoples R China;[4]Chinese Peoples Liberat Army, Hosp Joint Logist Support Force 940, Dept Nucl Med, Lanzhou 730050, Peoples R China;[5]Gansu Univ Chinese Med, Sch Basic Med Sci, Lanzhou 730000, Peoples R China;[6]Taikang Tongji Wuhan Hosp, Dept Nucl Med, Wuhan 430050, Peoples R China

第一机构：Lanzhou Univ, Sch Math & Stat, Lanzhou 730000, Peoples R China

通信机构：[1]corresponding author), Lanzhou Univ, Sch Informat Sci & Engn, Gansu Prov Key Lab Wearable Comp, Lanzhou 730000, Peoples R China;[2]corresponding author), Taikang Tongji Wuhan Hosp, Dept Nucl Med, Wuhan 430050, Peoples R China.

年份：2025

卷号：25

期号：15

起止页码：28547

外文期刊名：IEEE SENSORS JOURNAL

收录：;EI(收录号：20252618692062);Scopus(收录号：2-s2.0-105009299019);WOS:【SCI-EXPANDED(收录号:WOS:001542419600026)】；

基金：This work was supported in part by the Central Government Guides Local Science and Technology Development Fund Projects under Grant 25ZYJA017, in part by the Department of Education of Gansu Province: "Innovation Star" Project for Excellent Postgraduates under Grant 2025 CXZX-050, and in part by the Fundamental Research Funds for the Central Universities under Grant lzujbky-2024-it16.

语种：英文

外文关键词：Lungs; Feature extraction; Lung cancer; Solid modeling; Imaging; Computed tomography; Deep learning; Accuracy; Three-dimensional displays; Training; lung nodules classification; multimodal fusion; positron emission tomography-computed tomography (PET/CT)

摘要：Lung cancer is one of the most common malignancies globally, with malignant nodules being an early indicator of the disease. Thus, accurate early diagnosis of lung nodules is imperative. Positron emission tomography-computed tomography (PET/CT) is a noninvasive imaging technique that provides both anatomical and metabolic information, playing a crucial role in the diagnosis of cancer. Existing deep learning-based multimodal fusion strategies often rely on the simple concatenation of features from two modalities, overlooking the intricate interactions between them. In this study, we proposed a multimodal information interaction framework named multimodal information interaction architecture (MI2A) for the automated diagnosis of lung nodules using PET/CT imaging. Specifically, the lung parenchymal regions were cropped as regions of interest (ROIs) using a pretrained U-Net model. Second, higher-order multimodal features from PET/CT scans were extracted and integrated using a custom-designed PET-CT imaging encoder (PCIE) module and a cross-attention multimodal encoder (CAME) module, respectively. Predictions were generated using multipath pooling layers and a multilayer perceptron (MLP) layer. Furthermore, an alignment loss function was designed to minimize the discrepancy between modality features during training. Finally, the proposed model was evaluated on an actual clinical dataset, achieving accuracy (Acc), precision (Prec), recall (Rec), specificity (Spec), and the ${F}1$ -score ( ${F}\text {-}{1}$ ) of 0.9179, 0.8972, 0.8937, 0.9335, and 0.8954, respectively. In addition, the findings revealed that certain benign lesions, particularly those related to inflammatory or infectious conditions, displayed high metabolic activity, which is the main reason for limiting the model's performance. This insight provides a promising direction for future research.