Proving the Business Case for the Internet of Things

Philips turns to AI to diagnose breast cancer

Steve Rogerson
April 11, 2017



Philips and PathAI, a Massachusetts-based company that develops artificial intelligence technology for pathology, are collaborating to improve the precision and accuracy of routine diagnosis of breast cancer and other diseases.
 
The partnership aims to build deep learning applications in computational pathology, enabling this form of artificial intelligence to be applied to massive pathology data sets to inform diagnostic and treatment decisions. The initial focus of this effort is on developing applications to detect and quantify automatically cancerous lesions in breast cancer tissue.
 
The accurate quantitative assessment of cancer involvement and scale is a central and challenging task for pathologists. This task, while critical to diagnosis and treatment, is very time consuming and can place increased pressure on pathologists to conduct slide readings and analysis faster.
 
Historically, pathologists have manually reviewed and analysed tumour tissue slides using a microscope, but the rising shortage of pathologists and the increase in cancer caseloads require digital pathology and smart image analysis software to reduce pathologists' routine workload, improve diagnostic accuracy and precision, and reduce error rates.
 
"Breast cancer is the most common cancer in women worldwide, with over 250,000 new cases diagnosed every year in the USA," said Andy Beck, CEO of PathAI. "Our goal is to help patients receive fast, accurate diagnosis and support treating physicians to deliver optimal care by empowering pathologists with decision support tools powered by artificial intelligence. For example, identifying the presence or absence of cancer in lymph nodes is a routine and critically important task for a pathologist. However, it can be extremely laborious using conventional methods. Research indicates that pathologists supported with computational tools could be both more accurate and faster."
 
Deep learning is an algorithmic technique that is revolutionising what is possible in areas such as finance, communications, automotive, natural language processing and computer vision. It allows computers to analyse vast amounts of data, automatically detect patterns and make accurate predictions.
 
Dutch company Philips has already implemented deep learning in its clinical informatics products for radiology, such as Illumeo and IntelliSpace Portal 9.0. With the proliferation of digital pathology and whole slide imaging, computers will soon be able to learn and unlock the big data potential of thousands of digital tumour tissue (histology) images and related patient data.
 
"Digitising images in pathology has the potential to transform the field by unlocking new opportunities in image recognition," said Russ Granzow, general manager of digital pathology at Philips. "With computational pathology and the application of artificial intelligence there is an opportunity to increase efficiencies, enable greater accuracy and precision, and allow pathologists to see things and access insights not previously available."
 
Last year, Andy Beck and his colleagues from Harvard Medical School and MIT, won a global challenge on the detection of metastatic lesions in lymph nodes with a performance that rivals human error rates consistently. Now Philips and PathAI are partnering to ensure such highly promising technologies could find a practical application in aiding pathologists in their effort to deliver high quality, high confidence diagnosis.