"Through the acquisition of ophthalmic images and intelligent analysis of images, the screening model based on artificial intelligence developed by the team has achieved 75% accuracy in screening Alzheimer's disease for multiple community populations." On the 6th, Zhao Yitian, researcher of the Intelligent Medical Imaging (iMED) team of the Ningbo Institute of Materials, Chinese Academy of Sciences, introduced to the reporter of Science and Technology Daily, through in-depth analysis and exploration of the relationship between eye structure changes and neurodegenerative diseases, It can potentially form an early detection scheme for neurodegenerative diseases. Neurodegenerative diseases have a long course of onset, are difficult to be noticed in daily life, and are often irreversible, and have a long-term impact on human health. At this stage, the diagnosis of such diseases requires the use of expensive means such as magnetic resonance imaging, or the use of cognitive function scale, gene testing, spinal cord puncture and cerebrospinal fluid extraction. The relevant methods also have defects such as vague indications, trauma and radioactivity, which are not suitable for large-scale screening of grass-roots population. In order to explore the relationship between the structural changes of retina and Alzheimer's disease, the iMED team cooperated with many medical institutions such as West China Hospital of Sichuan University, Zhejiang Provincial People's Hospital, the Third Hospital of Peking University, and the People's Hospital of Ningbo University to collect a large number of eye and brain data of Alzheimer's patients, and took the fundus images of optical coherence tomography (OCTA) as the main analysis object. The iMED team introduced that optical tomography is an advanced non-invasive imaging technology, which can present the structures of different depths of the fundus, including retina and choroid, and can also scan the blood flow changes in the fundus structure with high accuracy to generate OCTA images, which is of great significance for the relevant research on the changes of fundus blood vessels caused by Alzheimer's disease. Through the self-developed intelligent analysis algorithm, the team automatically quantifies the fundus structure of Alzheimer's patients, and carries out cross-sectional statistical analysis of the calculated biological indicators and clinical data. The analysis showed that there were significant correlations between various quantitative indicators and the incidence of Alzheimer's disease, including vascular density, vascular fractal dimension, vascular curvature, etc. This result is consistent with the clinical consensus. Based on this, the team designed an advanced AI model for the detection of Alzheimer's disease according to the blood flow imaging image information. After inputting only ophthalmic images into the AI model, it can quickly determine whether the subject has Alzheimer's disease. In addition, the team also carried out ophthalmic image analysis and intelligent diagnosis model establishment of brain diseases such as stroke and Parkinson's disease. The results showed that some biological indicators of the eye were statistically correlated with the onset of disease, providing a new way to realize rapid and portable screening of various brain diseases. It is reported that at present, the team is relying on multi-center to carry out large-scale population tracking research, collect sequence data of clinical research significance, and further analyze the relationship between changes in fundus structure and the pathogenesis of related brain diseases. (Xinhua News Agency)