Predicting Invasiveness of Lung Adenocarcinoma from Chest CT with Few-shot Vision-Language Ternary Classification Model.
Authors
Affiliations (20)
Affiliations (20)
- School of Health Management, China Medical University, Shenyang, Liaoning, China.
- Shengjing Hospital of China Medical University, Shenyang, Liaoning, China.
- Department of Medical Imaging, Zhuhai People's Hospital (The Affiliated Hospital of Beijing Institute of Technology, Zhuhai Clinical Medical College of Jinan University), Zhuhai, Guangdong, China.
- Department of Infectious Diseases, Shengjing Hospital of China Medical University, Shenyang, Liaoning, China.
- Shenzhen Maternity and Child Healthcare Hospital, Women and Children's Medical Center, Southern Medical University, No. 2004, Hongli Road, Futian District, Shenzhen, Guangdong, China.
- Department of Obstetrics and Gynecology, Shengjing Hospital of China Medical University, Shenyang, Liaoning, China.
- The First Hospital of China Medical University, Shenyang, Liaoning, China.
- The Second Clinical College, China Medical University, Shenyang, Liaoning, China.
- The Fourth Clinical College, China Medical University, Shenyang, Liaoning, China.
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, Liaoning, China.
- Department of Radiology, Cancer Hospital of Dalian University of Technology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, Liaoning, China.
- Department of Radiology, The First Hospital of China Medical University, Shenyang, Liaoning, China.
- Department of Radiology, The Forth Hospital of China Medical University, Shenyang, Liaoning, China.
- Department of Interventional Radiology, The First Hospital of China Medical University, Shenyang, Liaoning, China.
- Department of Nuclear Medicine, The First Hospital of China Medical University No.155 Nanjing Bei Street, Heping District, Shenyang, Liaoning, China. [email protected].
- Department of Epidemiology and Health Statistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China. [email protected].
- Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, Liaoning, China. [email protected].
- Department of Radiology, Cancer Hospital of Dalian University of Technology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, Liaoning, China. [email protected].
- Department of Radiology, The Forth Hospital of China Medical University, Shenyang, Liaoning, China. [email protected].
- School of Health Management, China Medical University, Shenyang, Liaoning, China. [email protected].
Abstract
Preoperative differentiation of preinvasive lesions, minimally invasive adenocarcinomas, and invasive adenocarcinomas within pure ground-glass nodules (pGGNs) is challenging. Herein, this study investigated the potential of vision-language models to assist radiologists in noninvasively predicting pGGN invasiveness on CT scans. This retrospective multicenter study enrolled 848 patients with pathologically-confirmed lung adenocarcinoma manifesting as pGGNs. GPT-4o was tasked with localizing pGGNs on CT scans to detect ten pGGN invasiveness-associated features to generate a diagnosis and was compared with Molmo. The twenty-shot GPT-4o model demonstrated superior performance in the ternary classification of pGGN invasiveness (Delong test, P < 0.01). Six radiologists' assessments revealed that GPT-4o output showed high reliability, willingness to use, reliance, low risk of harm, inappropriate content, and missing content. With GPT-4o assistance, another six radiologists achieved an average improvement in pGGN invasiveness diagnosis. The twenty-shot-based GPT-4o model exhibited superior diagnostic capability for pGGN invasiveness in lung adenocarcinoma, achieving significantly improved diagnostic accuracy by radiologists.