From October 8th to 12th, MICCAI 2023, the most internationally recognized academic conference in the field of medical image analysis, was held in Vancouver, Canada. A total of 8 papers of Eagle pupil Technology Airdoc stood out and were finally included, and one of them was presented at the conference as one of the few oral reports (Oral), fully reflecting the company's comprehensive and outstanding innovation ability in the field of medical artificial intelligence.

What is MICCAI?

MICCAI is the International Conference on Medical Image Computing and computer-aided intervention (International Conference on Medical Image Computing and Computer Assisted Intervention). It is a comprehensive international top academic conference in the fields of medical image computing (MIC) and computer-aided intervention (CAI). It has a very strong international influence and authority in the industry.

Is it difficult to be selected for MICCAI?

It is not easy to be selected into MICCAI. Every selected paper has to undergo strict double-blind peer review. Selected papers often represent the highest academic level in this field, and will also become a hot weather vane in the field of medical image analysis, leading the future development direction of this field.

According to Tanveer Syeda-Mahmood, chairman of the conference, the number of contributions to this year's conference reached a new high, an increase of 30% over 2022 to more than 2300. Finally, 730 papers were included, of which only 68 were presented in the form of oral reports.

ThisWhich papers have been selected by Secondary Eagle pupil Airdoc?

The eight papers selected by Eagle pupil Airdoc are led by Professor GE Zongyuan, chief scientist of Eagle pupil Airdoc Monash Research and Development Center (Airdoc-Monash Research Centre). They cover many hot research fields of artificial intelligence, such as retinal disease recognition, skin disease recognition and brain imaging, and the results have been or will be widely used in hospital clinical and scientific research projects.

Specifically, one of the studies proposed an innovative method for retinal age estimation (Retinal Age Estimation), which was verified on a large data set of 130000 retinal images from multiple cohorts. The results show that the model achieves a smaller age prediction error than the existing methods on multiple queues and provides a more accurate retinal age estimation.

In recent years, retinal age has become a reliable biomarker for assessing the risk of aging-related diseases. With the increasing aging of the population, the accurate estimation of individual biological age will have a far-reaching impact on the health management and disease prevention of the elderly. Retinal age estimation, as a rapid, non-invasive and economical method, will bring new hopes and opportunities to this field.

Coincidentally, another retinal age assessment model developed by Eagle pupil has been used in artificial intelligence evaluation of Eagle pupil Airdoc retinal images since 2019, which provides an important reference for users' health management.

In addition, in the field of skin lesion recognition, researchers have proposed innovative methods and verified them respectively to solve the problems in previous models, such as only recognizing predefined samples and relying too much on image artifacts that have nothing to do with the disease. These innovative methods can make full use of the knowledge of known categories to discover new semantic categories, and effectively improve the generalization ability and robustness of skin lesion recognition in various environments, and help to enhance the ability of skin lesion recognition.

Is this the first time that the research result of Eagle pupil Airdoc has been selected into MICCAI?

In fact, the research results of Eagle pupil Airdoc have been selected into MICCAI for many years. In the past three years, seven papers of the company were collected and publicized by the conference in 2021, one of which won the best paper award in the FAIR forum of the conference. In 2022, the company also had seven papers selected, and another eight papers were selected this year, which reflects the company's continuous innovation ability and determination to invest in research and development.

What are the published research results of Eagle pupil Airdoc?

Eagle pupil Airdoc has always attached importance to R & D investment and scientific research innovation, and strengthened industry-university-research cooperation. Up to now, the company has published more than 60 high-level papers in authoritative peer-reviewed journals such as the Lancet series, Nature series, British Journal of Ophthalmology, as well as MICCAI and other top international conferences, and undertaken more than 10 national, provincial and municipal projects.

At the same time, as a national specialized and innovative "Little Giant" enterprise and national intellectual property advantage enterprise, the company currently has more than 300 patents and patent applications, as well as more than 10 issued PCT applications and international patents; has twice won the "China artificial Intelligence highest Award" Wu Wenjun artificial Intelligence Science and Technology Progress Award, and won the Beijing Science and Technology Progress Award and other honors.

In the future, Eagle pupil Airdoc will continue to uphold the mission of "making health everywhere", rely on the cutting-edge technology of artificial intelligence, continue to invest in research and development, speed up the transformation of scientific research results and clinical application, and make medical services more efficient and temperature.

List of papers included in Eagle pupil Airdoc MICCAI 2023

Main conference:

Ruyi Zha, Xuelian Cheng, Hongdong Li, Mehrtash Harandi, ZongYuan Ge, "EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos" in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.

Zhen Yu, Ruiye Chen, Peng Gui, Lie Ju, Xianwen Shang, Lisa Zhuoting Zhu Zhu, Mingguang He, ZongYuan Ge, "Retinal Age Estimation with Temporal Fundus Images Enhanced Progressive Label Distribution Learning" in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.

Dwarikanath Mahapatra, Antonio Jose Jimeno Yepes, Shiba Kuanar, Sudipta Roy, Behzad Bozorgtabar, Mauricio Reyes, ZongYuan Ge, "Class Specific Feature Disentanglement And Text Embeddings For Multi-Label Generalized Zero Shot CXR Classification" in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.

Siyu Liu, Linfeng Liu, Craig Engstrom, Xuan Vinh To, ZongYuan Ge, "Style-based Manifold for Weakly-supervised Disease Characteristic Discovery" in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.

Siyuan Yan, Chi Liu, Zhen Yu, Lie Ju, Dwarikanath Mahapatra, Victoria Mar, Monika Janda, H. Peter Soyer Soyer, ZongYuan Ge, "EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition" in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.

Deval Mehta, Sh ó bi Sivathamboo Sivathamboo, Hugh Simpson, Patrick Kwan, Terence O'Brien O'Brien, Zongyuan Ge, "Privacy-preserving Early Detection of Epileptic Seizures in Videos" in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.

Wei Feng, Lie Ju, Lin Wang, Kaimin Song, ZongYuan Ge, "Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering" in International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023.

Workshops:

Xin Zhang, Deval Mehta, Chao Zhu, Daniel Merlo, Yanan Hu, Melissa Gresle, David Darby, Anneke van der Walt, Helmut Butzkueven and Zongyuan Ge, "Deep Survival Analysis in Multiple Sclerosis" in Predictive Intelligence in Medicine (PRIME), 2023.

The above research is mainly done by the Eagle pupil Airdoc algorithm team, the Eagle pupil Airdoc Monash Research Center to jointly train doctoral students and the Origin Institute of artificial Intelligence (IIAI).

Brief introduction of Eagle pupil Airdoc

Eagle pupil Technology (Airdoc), founded in September 2015, is committed to providing comprehensive and multi-faceted artificial intelligence solutions for early screening and management of chronic diseases, myopia prevention and control, etc., and is a global leader and forerunner in the field of retinal image artificial intelligence. On November 5, 2021, Eagle pupil Technology was successfully listed on the Hong Kong Stock Exchange under the stock code 02251.HK, becoming the "first share of Medical AI".

Eagle pupil technology's diabetic retinopathy assistant diagnosis software is the first of its kind to obtain the Class III medical device certificate of the State Drug Administration, and has been used in medical institutions to assist doctors in medical diagnosis. In order to solve the unmet medical and health needs, the company has developed a rich product pipeline related to artificial intelligence retinal imaging, which has been widely used in community clinics, physical examination centers, insurance companies, optometry centers and pharmacies and other places to provide users with disease diagnosis and health risk assessment. By the end of 2022, Eagle pupil Technology's retinal imaging artificial intelligence products have served nearly 20 million users.

In the face of the increasingly severe situation of myopia prevention and control, Eagle pupil Technology has also launched myopia prevention and control products for children and adolescents, relying on the company's powerful retinal image artificial intelligence technology to provide safe and efficient myopia prevention and control solutions.

Eagle pupil Technology, headquartered in Beijing, has set up subsidiaries, production bases and R & D centers in Beijing, Shanghai, Guangzhou, Shenzhen, Changsha, Hong Kong, Melbourne and offices in Nanjing, Xi'an, Chengdu and Wuhan. In view of its technological advantages and social value in the field of medical treatment and science and technology, Eagle pupil Technology has twice won the "highest Award in the Field of artificial Intelligence in China" Wu Wenjun artificial Intelligence Science and Technology Progress Award, and won the Beijing Science and Technology Progress Award and other honors.

Adhering to the corporate mission of "making health everywhere", Eagle pupil Technology will join hands with the majority of partners to make high-quality medical and health services like air, accessible anytime, anywhere.