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