Health

Artificial Intelligence Empowers Pathology Development: More Accurate Diagnosis, Large Industrialization Space

2025-04-14   

On the 12th, the Future International Pathology Conference with the theme of "Technology Leading, Intelligent Mapping of the Future" was held in Hangzhou, Zhejiang. The conference focuses on cutting-edge technologies such as artificial intelligence, multimodal imaging, and spatial genomics, gathering top experts from home and abroad to build a high-energy platform for international pathology cooperation and translational innovation. Pathology is the cornerstone of modern medicine and an important bridge connecting basic research and clinical practice. In recent years, artificial intelligence technology has developed rapidly, giving rise to large models such as ChatGPT, especially the emergence of Deepseek big model technology. We have ushered in a good opportunity for the deep application of intelligent technology in pathology. The combination of the two not only provides a new perspective for the diagnosis and treatment of diseases, but also opens up unprecedented possibilities for personalized medicine and precision medicine Chen Chun, an academician of the CAE Member and a professor of Zhejiang University, said. With the rapid development of molecular diagnosis, digital pathology and other technologies, hospitals are constantly exploring the combination of artificial intelligence and pathology. Liang Tingbo, Secretary of the Party Committee of the First Affiliated Hospital of Zhejiang University School of Medicine (hereinafter referred to as Zhejiang University First Hospital), introduced that as a medical institution committed to digital construction, Zhejiang University First Hospital has always attached great importance to the construction and development of digital intelligent pathology department. In July 2024, the hospital established the largest digital pathology center in China, equipped with nearly 40 high-throughput scanners. Currently, nearly 6 million digital section scans have been completed, and all daily pathological sections have been digitized. AI also plays an important role in assisting diagnosis. Taking OmniPT, a human-machine interactive AI pathology universal assistant jointly developed by the Pathology Department of Zhejiang University First Hospital and the School of Computer Science at Zhejiang University, as an example. In the past, even an experienced pathologist would often spend more than ten minutes reviewing films and making pathological diagnoses, but in the era of artificial intelligence, this time will be shortened to less than one minute. OmniPT is like giving doctors a detection mirror that can quickly locate tiny lesions within 1 to 3 seconds with an accuracy rate of over 95% Professor Zhang Jing, Director of the Pathology Department of Zhejiang University First Hospital, introduced that the system has made breakthroughs in key technologies such as cross level efficient feature locking and prompt guided detail feature completion, solving the problem of second level reasoning and accurate analysis of large-sized pathological images. It strongly links text semantics with visual features, providing strong technical support for one click generation of pathological reports. In addition to OmniPT, this conference also systematically presented the latest scientific research progress of China in the fields of medical big models, human-machine collaboration, intelligent diagnosis, etc., demonstrating the technological breakthroughs and landing explorations of Chinese teams in the fields of digital pathology and molecular pathology. Chen Gang, member of the Standing Committee of the Party Committee and Vice President of Zhejiang University, stated that past practice has shown that artificial intelligence is not only a tool, but also a strategic pivot to redefine the boundaries of pathology. He admitted that although the application prospects of artificial intelligence in pathology are broad, there are still many challenges in its actual promotion process, such as data security and ethical issues, poor credibility of AI models, and a lack of cross disciplinary talents. The cross research and application of "AI+pathology" still has a long way to go. In order to promote the integration of China's pathology discipline with the international community and establish an international cooperation mechanism of "bringing in and going out", the conference also launched the "Future Pathology International Alliance" to promote standard building, talent exchange, joint scientific research, and resource exchange, and establish a globally influential cooperation network in key technology fields such as digital pathology and spatial genomics. At present, the industrialization process of AI pathology has also attracted attention from all walks of life. This event also set up a "Special Forum on the Implementation of Intelligent Pathology Industrialization", focusing on key issues such as model standards and the improvement of universality. Hospitals, regulatory industries, enterprises, etc. were invited to have in-depth discussions, promote the exploration and development of industry equipment and data standards, explore the Yangtze River Delta region as a demonstration area, carry out industrial pilot practices, and help achieve rapid implementation of results. (New Society)

Edit:Ou Xiaoling Responsible editor:Shu Hua

Source:China News Network

Special statement: if the pictures and texts reproduced or quoted on this site infringe your legitimate rights and interests, please contact this site, and this site will correct and delete them in time. For copyright issues and website cooperation, please contact through outlook new era email:lwxsd@liaowanghn.com

Recommended Reading Change it

Links