China News Service, Guangzhou, October 10 (Reporter Cai Minjie) "In the new era of AI, scientific research must be 'for the people'." Zhong Nanshan, an academician of the Chinese Academy of Engineering, said in Guangzhou on the 10th that "top of the sky" means using AI technology and new technologies; "standing on the ground" means making it affordable for the common people and making it easy, cheap, effective and safe to use.
The AI Empowered Lung Cancer Precision Diagnosis and Treatment Summit Forum and the National Center for Respiratory Medicine’s lung cancer precision diagnosis and treatment standardization project launch meeting were held in Guangzhou on the 10th. At the meeting, DeepGEM2.0, a large multi-modal model of lung cancer pathological genes, was released, and a multi-center scientific research project jointly participated by 50 medical institutions across the country was launched, marking the official entry of this large model into large-scale clinical application verification.
Lung cancer is a malignant tumor with the highest morbidity and mortality in my country, and genetic testing is the prerequisite for targeted therapy. However, due to factors such as testing accessibility and economic conditions, a considerable proportion of patients fail to complete necessary genetic testing and miss opportunities for targeted and precise treatment.
In order to solve this problem, in 2025, the First Affiliated Hospital of Guangzhou Medical University joined hands with KingMed and Tencent to release DeepGEM, a large multi-modal pathological gene model that "looks at images to identify genes". It uses pathological slices as input to predict the probability of lung cancer-related gene mutations and their spatial distribution within tissues.
After nearly a year of multi-center data verification and clinical polishing, and relying on iterative optimization of data from nearly 8,000 digital pathology slides from 31 provinces across the country, DeepGEM has been officially upgraded to version 2.0, opening up the path for DeepGEM to be applied in clinical scenarios, with good applicability and compatibility.
Liang Wenhua, deputy director of the First Affiliated Hospital of Guangzhou Medical University and deputy director of the National Center for Respiratory Medicine, said that DeepGEM2.0 can complete "identifying genes by looking at pictures" in as little as 1 minute, and can complete the pre-screening of target genes corresponding to approved lung cancer targeted drugs in the mainland at once, and will be deployed in more than 500 medical institutions in the future. Relying on the model of "AI preliminary screening + specific gene targeting verification", this technology is expected to reduce the cost of lung cancer genetic testing to a few hundred yuan.
Zhong Nanshan said that the significance of the upgrade of DeepGEM2.0 lies not only in how to use the most advanced technology at the grassroots level; but also in that it embodies the integration of industry, academia, research, medicine, teaching and research. "I hope that the scientific research team can turn it from a sample into a product or commodity, promote the results of the paper to the grassroots, and practice it in the motherland, truly achieving 'strengthening the foundation and reducing costs.'"
Liu Si, the person in charge of KingMed Medical's artificial intelligence project, said that DeepGEM2.0 has now opened up a standardized development path for new genes. In the future, genes can be dynamically and rapidly expanded according to the approval of new drugs. The development cycle only takes 12-16 weeks, and the model gene library and cutting-edge targeted drugs can be updated simultaneously.
As the path for the technology to be implemented in medical institutions has been fully opened, the DeepGEM2.0 multi-center prospective randomized controlled research project and health economics research initiated by Liang Wenhua's team have also been launched simultaneously. They provide high-level evidence-based basis for the application of AI-assisted pathological diagnosis in precision treatment of lung cancer from the two levels of large-scale clinical application verification and economic accessibility respectively.
At the meeting, the National Respiratory Medicine Center of the First Affiliated Hospital of Guangzhou Medical University also joined hands with KingMed, as well as dozens of provincial and ministerial-level medical institutions and grassroots hospitals, including the Second Affiliated Hospital of Zhejiang University School of Medicine, Fuzhou University Provincial Hospital, Gongyi Municipal People's Hospital, and Pingyu County People's Hospital, to jointly establish the National Respiratory Medicine Center Lung Cancer Precision Diagnosis and Treatment Alliance to carry out standard formulation, MDT discussions, teaching and coaching, and promote the standardized implementation of precision diagnosis and treatment of lung cancer.
