Value of AI-assisted lung nodule CT diagnosis in the teaching of standardized training of radiology residents
Lv Peng
Tang Min
Lin Jiang
Liu Liheng
Abstract：Objective To explore the value of AI-assisted lung nodule CT diagnosis in the teaching of standardized training of radiology residents.Methods Ten radiology residents were selected for the study.Each resident independently reviewed the lung CT of 100 patients.Two senior radiologists provided AI-assisted pulmonary nodule CT diagnosis teaching to the residents.After that,the residents reviewed chest CT scans again,both with and without the assistance of the AI software.The residents'abilities to identify pulmonary nodules,classify nodule risk levels,and enhance their interpretive skills before and after AI-assisted teaching were compared.Results With the AI-assisted teaching,the radiology residents demonstrated a significant improvement in their ability to identify pulmonary nodules,with accuracy increasing from 85.4%to 94.3%and 91.5%(all P<0.05).Interpretive assessment scores also increased from(72.3±9.3)to(83.5±5.3)and(80.7±7.1)(all P<0.05).After AI-assisted review,the diagnostic ability for high-risk and medium-risk nodules increased,and the instances of underestimating the risk level of the nodules decreased.Conclusion AI-assisted lung nodule CT diagnosis can help radiology residents improve their ability to recognize and qualitatively diagnose lung nodules,as well as their interpretive skills.It demonstrates an excellent educational outcomes.
Keywords：artificial intelligencelung noduleCTresidentsstandardized trainingteaching
Publication Date：2024-02-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 107-110 )