Infervision has introduced its deep learning solution to help radiologists identify suspicious lesions and nodules in lung cancer patients faster than ever before. The Infervision AI platform is the world's first to reshape the workflow of radiologists and it is already showing dramatic results at several top hospitals in China. The company founder, Chen Kuan, will present a talk on the company and its use of AI for medical diagnoses at the NVIDIA GPU Tech Conference in San Jose.
Infervision's AI-aided CT diagnosis, with its high-performance parallel computing power, effectively learns the core characteristics of lung cancer and efficiently detects suspected cancer features in different CT image sequences, helping with early diagnosis and, consequently, early treatment.
The technology is also used to assist in X-ray diagnosis and has achieved extremely high accuracy so that it is close to that of a deputy chief physician in the diagnosis of cardiothoracic diseases at one of the top Chinese hospitals where the software is now in use.
For the past six months, the technology has been in use at several top hospitals in China, a country experiencing hundreds of thousands of new lung cancer patients annually, while it has too few radiologists.
After rigorous testing and integrating the software with the standard PACS (Picture Archiving and Communication System), Infervision's technology is proving to be extremely effective and is enhancing the work of Chinese doctors by acting as a second pair of eyes.
The Infervision solution improves the workflow of radiologists, delivering a faster reading of hundreds of images for each patient, and bringing to the doctor's attention those scans that may have malignant lesions or nodules so radiologists will thoroughly review them.
"Our goal at Infervision is to build a stronger medical industry and help accelerate diagnoses, which is so important for patients," said Chen Kuan, founder and CEO of Infervision. "In China, we have a severe shortage of radiologists, particularly in lower-level hospitals all over the country".
"There are 80,000 radiologists who must diagnose 1.4 billion radiology scans a year. By using artificial intelligence and deep learning, the Infervision platform augments the work of these doctors so they can get through scans quickly. A process that used to take 15 minutes can be dramatically reduced so detection and treatment of lung cancer is faster. This could be life changing for many."
Additionally, Infervision's technology and a group of radiologists recently went head-to-head in a report reading experiment with different types and sizes of nodules. Infervision's AI-CT predicted more accurately than radiologists in every category.
"In no way will this technology ever replace doctors. It is intended to eliminate much of the highly repetitive work. Infervision empowers doctors and helps them deliver more accurate reports and do it much faster," continued Kuan.
The Infervision artificial intelligence continues to learn as more data becomes available and also as it analyses past results. Lung cancer is particularly rampant in China, due to both air pollution and smoking, with between 600,000 and 700,000 new lung cancer cases are diagnosed annually. While this is an unfortunate statistic, it provides a huge trove of medical data that can make the Infervision technology stronger and even more effective.