Predicting Invasiveness of Lung Adenocarcinoma from Chest CT with Few-shot Vision-Language Ternary Classification Model

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.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-12-20
DOI
https://doi.org/10.1038/s41746-025-02229-2
Primary Topic
Lung Cancer Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Predicting Invasiveness of Lung Adenocarcinoma from Chest CT with Few-shot Vision-Language Ternary Classification Model

Enyu Li, Lina Zhang, Qianqian He, Yan Dong et al.
npj Digital Medicine
Lung Cancer Diagnosis and Treatment
article

Predicting Invasiveness of Lung Adenocarcinoma from Chest CT with Few-shot Vision-Language Ternary Classification Model

Enyu Li, Lina Zhang, Qianqian He, Yan Dong, Nan Xu, Jing Qiu, Bosinan Chen, Yunan Wang, Shang Gao, Qiuju Sheng, Fan Yang, Gao Si, Jiangdian Song, Zhihui Chang, Yue Dong, Haotian Wang, Song Chen, Jie Zhang, Zhijian Zhang, Shimin Zhang, Lu Wang, Sun Jianing, Guanyu Liu, Jiaping Yu, Zhang Zhiwen, Mingke Tian
article en

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.

npj Digital MedicineVol. 9(1)
Shandong University (CN), Fourth Affiliated Hospital of China Medical University (CN), Shenzhen Maternity and Child Healthcare Hospital (CN), Zhuhai People's Hospital (CN), First Hospital of China Medical University (CN), Liaoning Cancer Hospital & Institute (CN), China Medical University (CN)
Openalex Percentile: Top 40%
Lung Cancer Diagnosis and Treatment
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.