Cancer
is one of the leading causes of morbidity and mortality worldwide, with lung
cancer being the most common cause of cancer death. Around 70% of lung cancer
patients will survive for at least a year if diagnosed at the earliest stage,
compared to around 14% for people diagnosed at the most advanced stage of
disease. Unfortunately, there is a lack of access to quality healthcare in many
countries and rural areas, meaning that cancers often go unnoticed until it’s
too late.
The
Beijing-based startup Infervision is determined to improve the lung cancer
diagnosis process and is applying a deep learning technology to assist analysis
of medical images. To improve the detection rate of early stage tumors, their technology
is based on tens of thousands of X-rays and CT scans that previously have been
used to perform a diagnosis. Through this knowledge, they have developed a
software that evaluate future scans. The system is already in trials at
multiple hospitals across China, and according to the startup, it triples the
speed at which radiologists can diagnose CT scans, and has helped reduce the
rate of missed cancer diagnoses by 50%. And although predominantly used in
early-stage lung cancer screening, it could be applied to research and the
diagnosis of multiple cardiothoracic diseases.
![]() |
Lung
cancer is the second most common cancer, accounting for about one out of five
malignancies in men and one out of nine in women. A staggering 600,000 people
die from lung cancer every year in China alone, a number that is expected to
increase to 800,000 cases per year by 2020. Infervision has developed a
powerful tool that could increase access to appropriate care for millions of
cancer patients around the world. There is a major lack of radiologists and
qualified personnel, especially in rural areas, which delay diagnosis and
worsen health outcomes. The startup does not aim to make doctors and
radiologists obsolete, but want to help cut down the amount of time
radiologists spend reviewing each scan. They envision it can be used to double
check and point out potential trouble spots, easing a clinical bottleneck that
often leads to delayed care. Earlier diagnosis and care of lung cancer patients
could make more treatment options available, potentially reducing cost of care.
Most importantly, it could significantly improve treatment outcomes, quality of
life, and increase the survival rate for one of the most hard to treat diseases.
Infervision
was founded by Chen Kuan in 2015 after his aunt was one of thousands of people
in China whose cancer went undiagnosed for lack of appropriate care. In January
2017, the startup announced they had raised RMB 50 million in Series A funding,
with investors including Sequoia Capital China, Innovation angel funds and GFXINDE Investment Management. In addition, they are also working with GE Healthcare, Cisco and Nvidia to develop and refine their technology.