AUTHOR=Chen Yuyao , Liu Lei , Feng Bao , Chen Yehang , Xu Jun , Lin Huan , Li Kunwei , Chen Xiaodong , Ke Yuting , Zhou Haoyang , Hu Qinghui , Jin Qinggeng , Long Wansheng , Li Qiong , Chen Xiangmeng 

TITLE=A meta-learning-based robust federated learning for diagnosing lung adenocarcinoma and tuberculosis granulomas

JOURNAL=Frontiers in Oncology

VOLUME=Volume 15 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2025.1666937

DOI=10.3389/fonc.2025.1666937

ISSN=2234-943X

ABSTRACT=BackgroundDifferentiating between lung adenocarcinoma (LAC) and tuberculosis granuloma (TBG) of solitary pulmonary solid nodules (SPSNs) based on CT images alone is a daunting task for clinical diagnosis. Thus, it is crucial to fully utilize CT imaging data to explore effective noninvasive diagnostic methods to improve the identification of TBG and LAC.PurposeThis study aimed to leverage CT imaging datasets from multiple hospitals for the diagnosis of TBG and LAC in SPSNs. It achieved this by deploying a meta-learning method within a federated learning framework while protecting data privacy.MethodsA total of 1,026 patients, along with their CT images of solitary pulmonary solid nodules (SPSNs) and corresponding clinical data, were collected from six medical institutions. Subsequently, the data from these six institutions were systematically partitioned into five cohorts. Each cohort was divided into two parts: the training set and the test set. A meta-learning-based robust federated learning model by training set data was proposed to construct personalized federated learning signatures (PFLS) without uploading raw data from each medical institutions. Receiver operating characteristic curve (ROC), area under curve (AUC), decision curve analysis (DCA), net reclassification improvement (NRI) and integrated discrimination improvement (IDI) are used to analyze the performance of the PFLS.ResultsThe PFLS trained by the proposed meta-learning-based robust federated learning framework shows superior performance compared to alternative methods. The AUC range on the training sets of the five cohorts is 0.866-0.939, AUC range on the testing sets is 0.808-0.927). The significant difference of AUC between the proposed method and the clinical model was demonstrated by the NRI and IDI. The decision curves indicated a higher net benefit of our proposed method.ConclusionThe PFLS mitigates overfitting issues arising from limited sample size in local hospitals. It also alleviates the problem that a single global model is not applicable to all hospitals due to the heterogeneity of data distribution among different hospitals.