Computers Spot Lung Cancer as Well as Doctors Do


In the new study, Tse and his colleagues fed Google AI with CT scans of people suspected of having lung cancer.

An innovative system to predict lung cancer could make a huge change in survival rates, with Google exploring how artificial intelligence could dramatically improve diagnosis rates.

"More specifically, we were interested in replicating a more complete part of a radiologist's workflow, including full assessment of LDCT volume, focus on regions of concern, comparison to prior imaging when available, and calibration against biopsy-confirmed outcomes", the authors wrote. It compared the results against six board-certified radiologists. The machine edged out the physicians, making fewer false positives and false negatives than its human counterparts.

This research is incredibly important, as lung cancer has the highest rate of mortality among all cancers, and there are many challenges in the way of broad adoption of screening, said Shravya Shetty, technical lead at Google.

Google has published an academic paper detailing the project in the latest issue of Nature Medicine.

As of now, lung cancer claims to be having more than $1.7 Million death every year and is also considered to be the deadliest of all cancers.

A team of researchers at Google is planning to use deep learning to look for signs of lung cancer in people. The software detected lung cancer in early stages with an accuracy ratio of 94 percent.

More news: Australian Labor leader concedes election defeat to incumbent PM
More news: Family of murdered pregnant teen demands answers from hospital
More news: Rising Democratic candidate Pete Buttigieg comes to Wynwood

The researchers conducted two studies - one in which a prior scan was available, and one in which it wasn't. The AI can also help to reveal the growth rate of suspicious tissue.

While analyzing a single computed tomography (CT) scan, Google's AI model detected five percent more cancer cases while reducing false-positive exams by more than 11 percent compared to unassisted radiologists in the study.

The scientists found the artificial-intelligence-powered system was able to spot sometimes-minuscule malignant lung nodules with a model AUC of 0.94 test cases.

"The system can categorize a lesion with more specificity", said co-author Dr. Mozziyar Etemadi of Northwestern University in a statement.

Tse and colleagues applied a form of AI called deep learning to 42,290 LDCT scans, which they accessed from the Northwestern Electronic Data Warehouse and other data sources belonging to the Northwestern Medicine hospitals in Chicago, IL. "Not only can we better diagnose someone with cancer, we can also say if someone doesn't have cancer, potentially saving them from an invasive, costly and risky lung biopsy", explained Etemadi.

The researchers cautioned that these findings need to be clinically validated in large patient populations.