China: Ping An Technology, world champion in medical imaging evaluationSingapour - Published Tuesday, January 23, 2018 - 16:36 - #5563 In early January 2018, Yingxiang platform of Chinese company Ping An TechnologyPing An Technology stated that it had set world records for nodule detection and false positive reduction with average sensitivity rates of 95.1% and 96.8% respectively in the authoritative LUNALUNALUng Nodule Analysis rankings for medical imaging, a global medical imaging and analysis competition.
This is the first time that Ping An Technology has set world records in the sector, becoming a world leader in medical imaging.
LUNA: a high level international competition
LUNA is an internationally recognized evaluation system for the detection of pulmonary nodules, setting the benchmark for all players in the field of medical imaging.
A challenge raised by renowned universities and companies wordly
The evaluation, organized in the form of a competition, is being carried out by more than 3,600 professional teams from academia and industries worldwide since 2016, including the University of Hong Kong, Peking University, Zhejiang University, the Chinese companies Alibaba, iFLYTEK and Fosun as well as many start-ups.
Each competing team have to analyze the lung CTCTcomputed tomography samples of nearly 1,000 people and locate the nodules, which is difficult because most of the nodules diameters are smaller than three millimeters.
Lung cancer: computed tomography screening is booming
Lung cancer is the leading cause of cancer-related deaths worldwide.
Screening high risk individuals for lung cancer with low-dose CT scans is now being implemented in the United States, and other countries are expected to adopt this technique very soon.
A complex method
In CT lung cancer screening, millions of scans need to be analyzed, creating a huge burden for radiologists. Thus, it has become necessary to develop intelligent algorithms that are optimized for the detection of lung cancer.
* A CT scan uses X-rays and a computer to create detailed images of the inside of the body. It uses safe amounts of radiation to create detailed images, which can help doctors to detect problems.
Ping An Technology has created advanced AIAIArtificial intelligence algorithms to overcome the challenge
Ping An Technology's medical imaging team has come up with an innovative solution to overcome this challenge. Its technology incorporates robust control theory with advanced AI algorithms including deep learning and transfer learning. Transfer learning is a research problem in machine learning that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem.
Pulmonary nodule detection: Ping An Technology is becoming the world leader
This new solution has enabled the company to achieve excellent results and world-leading status in pulmonary nodule detection, localization and recognition.
The technology is being implemented in collaboration with the Shanghai Institute of Respiratory Diseases and several leading Grade III, Class A hospitals.
A team of international experts
Ping An Technology's medical imaging team, led by Dr. Xiao Jing, is comprised of medical and artificial intelligence experts from leading global universities including Harvard University (USA), Princeton University (United States), Carnegie Mellon University (United States), the University of Florida (United States), UCLA (United States), Zhejiang University (China), Tsinghua University (China) and Huazhong University of Science and Technology (China).
The team provides a wide range of medical AIAIArtificial intelligence capabilities to screen gastric, liver, cervical and thyroid cancer as well as detect diabetic retinopathy and thorax related diseases, and estimate bone age.
Regional projects on medical imaging technologies
Concerning the application of medical imaging technologies, Ping An Technology is collaborating with the Shanghai, Shenzhen and Chongqing HFPC but also with several of their provincial counterparts to jointly build platforms based on big data and AI technologies in addition to research into related topics.
Ping An Technology: the core high-tech division of Ping An Group
As the high-technology division of the Ping An Group, Ping An Technology designs and manages the key platforms and services that support the development and maintenance of the group's insurance, banking, investment and internet businesses.
The company also acts as Ping An's technology incubator, with strong research, development and application abilities in the areas of artificial intelligence, big data and cloud technology.
Since its founding in 2008, Ping An Technology has accumulated vast experience in three key areas: technology, the internet and finance.
In addition to the Ping An Yingxiang platform, the firm owns many of "black technologies", as they call it in Chinese, which have applications across a wide range of disciplines. There are highly-advanced new technologies including:
- voiceprint recognition;
- facial recognition;
- Q&A chatbot;
- physical robots.
Ping An Technology is a customer-centric company, where exploration, innovation and the unremitting dedication to achieving breakthroughs in technology are part and parcel of its corporate culture, says the organization on its website.
Ping An Technology
Founded in 2008 in Shenzhen, China, Ping An Technology is the key technology arm of Ping An Group, developing and operating the mission critical platforms and services that support the insurance, banking, investment and internet businesses of the group.
The company is also the technology incubator for Ping An, with strong research and development capabilities in cloud, artificial intelligence and big data technologies.