Artificial intelligence propels lung cancer screening:innovations and the challenges of explainability and reproducibility

作     者：Mario Mascalchi Chiara Marzi Stefano Diciotti Mario Mascalchi;Chiara Marzi;Stefano Diciotti

作者机构：Experimental and Clinical Biomedical Sciences“Mario Serio”University of FlorenceFirenzeItaly Department of StatisticsComputer ScienceApplications“G.Parenti”University of FirenzeFirenzeItaly Department of ElectricalElectronicand Information Engineering“Guglielmo Marconi”-DEIUniversity of BolognaCesenaItaly Alma Mater Research Institute for Human-Centered Artificial IntelligenceUniversity of BolognaBolognaItaly 

出 版 物：《Signal Transduction and Targeted Therapy》 (信号转导与靶向治疗(英文))

年 卷 期：2025年第10卷第2期

页      面：492-494页

核心收录：

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

基　　金：funding from the European Union-NextGenerationEU through the Italian Ministry of University and Research under PNRR-M4C2-I1.3 Project PE_00000019“HEAL ITALIA”to Stefano Diciotti-CUP J33C22002920006 

主　　题：screening low dosecomputedtomography explainability reproducibility nodule risk stratificatio noduleriskstratification malignant nodules artificialintelligence 

摘      要：In a recent study published in Nature Medicine,Wang,Shao,and colleagues successfully addressed two critical issues of lung cancer(LC)screening with low-dose computed tomography(LDCT)whose widespread implementation,despite its capacity to decrease LC mortality,remains challenging:(1)the difficulty in accurately distinguishing malignant nodules from the far more common benign nodules detected on LDCT,and(2)the insufficient coverage of LC screening in resource-limited areas.1 To perform nodule risk stratification,Wang et *** and validated a multi-step,multidimensional artificial intelligence(AI)-based system(Fig.1)and introduced a data-driven Chinese Lung Nodules Reporting and Data System(C-Lung-RADS).1 A Lung-RADS system was developed in the US to stratify lung nodules into categories of increasing risk of LC and to provide corresponding management recommendations.