How deep learning, image recognition are assisting Chinese radiologists
According to Forbes, lung cancer is the leading cause of death in China. With thousands of people being affected, it is increasingly difficult for radiologists to examine hundreds of images each day with complete accuracy.
For this reason, Chen Kuan, founder of startup Infervision, decided he wanted to focus his work with deep learning and image recognition in medicine. He and various team members at Szechwan Hospital created a tool that is able to predict if an x-ray is normal or not, cutting back on required time investment from radiologists.
They found a way to integrate PACS and train their algorithms using real data to increase accuracy and spot warning signs of potential cancerous nodule growth in lung tissue. This specific method developed by Kuan and team is called "supervised learning."
“In China, there are just 80,000 radiologists who have to work through 1.4 billion radiology scans every year,” said Kuan in a statement to Forbes. “By using [artificial intelligence] and deep learning, we can augment the work of those doctors. In no way will this technology ever replace doctors—it is intended to eliminate much of the highly repetitive work and empower them to work much faster.”
Read the full article here:
Jodelle joined TriMed Media Group in 2016 as a senior writer, focusing on content for Radiology Business and Health Imaging. After receiving her master's from DePaul University, she worked as a news reporter and communications specialist.