Shulou(Shulou.com)11/24 Report--

According to the official account of Ningbo Institute of Materials of the Chinese Academy of Sciences, the intelligent medical imaging (iMED) team of the institute developed a screening model based on artificial intelligence through ophthalmic image acquisition and intelligent analysis, according to the official account of Ningbo Institute of Materials of the Chinese Academy of Sciences on February 7. The screening accuracy of Alzheimer's disease in multiple communities reached 75%.

Fundus structure quantitative map CTOnews.com learned that the pathogenesis of neurodegenerative diseases is long, it is difficult to be noticed in daily life, and often irreversible, which has a long-term impact on human health. At this stage, the diagnosis of this kind of disease needs the help of expensive means such as magnetic resonance imaging, or through cognitive function scale, gene detection, spinal cord puncture and so on. The related methods also have some defects such as vague indication, trauma, radioactivity and so on, so they are not suitable for large-scale screening of grass-roots people.

IMED team believes that it is of great research value and clinical significance to explore a method for early prediction or diagnosis of neurodegenerative diseases, which takes into account safety, ease of operation, economy and accuracy.

In order to explore the relationship between fundus retinal structural changes and Alzheimer's disease, the team cooperated with many medical institutions, such as West China Hospital of Sichuan University, people's Hospital of Zhejiang Province, third Hospital of Peking University, people's Hospital affiliated to Ningbo University, etc., collected a large number of eye and brain data of Alzheimer patients, and took the fundus images of optical coherence tomography (OCTA) as the main analysis object.

According to the iMED team, optical tomography is an advanced non-invasive imaging technology, which can show the structure of the fundus at different depths, including the retina and choroid, and can also scan the blood flow changes in the fundus structure with high precision to generate OCTA images, which is of great significance for the study of fundus vascular changes caused by Alzheimer's disease.

The team automatically quantified the fundus structure of Alzheimer patients through self-developed intelligent analysis algorithm, and made a cross-sectional statistical analysis of the calculated biological indicators and clinical data. According to statistical analysis, a variety of quantitative indicators are significantly correlated with the incidence of Alzheimer's disease, including vascular density, vascular fractal dimension, vascular curvature and so on. This result is consistent with the clinical prior 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 only inputting the ophthalmic image into the AI model, the team can quickly determine whether the subject has Alzheimer's disease. At present, the screening model based on artificial intelligence developed by the team has more than 75% accuracy in community screening for Alzheimer's disease.

In addition, the team also carried out ophthalmic image analysis and the establishment of intelligent diagnosis models for brain diseases such as stroke and Parkinson's disease. the results showed that some eye biological indexes were statistically correlated with the morbidity. It provides a new idea for rapid and portable screening of a variety of brain diseases.

It is reported that at present, the team is relying on multi-center to carry out large-scale population tracking research, aiming to collect sequence data of clinical significance through 5-10 years of return survey, and further analyze the relationship between fundus structural changes and the pathogenesis of related brain diseases.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.