Computers Spot Lung Cancer as Well as Doctors Do

Ruben Fields
May 23, 2019

In the pair of studies, the AI was trained on CT scans of people with lung cancer, people without lung cancer, and people whose CT scans showed nodules that would later go on to develop into cancer.

The paper will be published in Nature Medicine May 20.

By feeding AI programs with large amounts of data, the technology can be trained to identify different medical conditions that would otherwise be too hard or too time-consuming for human doctors to detect.

AI involves using accumulated data and software known as "machine learning" to enable computers to mimic human thought processes. The model and the radiologists achieved almost identical results when they were given access to multiple scans of a patient's chest. "We started wanting to push the boundaries of basic science to find interesting and cool applications to work on".

Large clinical trials across the United States and Europe have shown that chest screening can identify the cancer and reduce death rates, researchers said.

Doctors have long recommended the diagnostic to detect cancer risks for people who have a long history of smoking.

Terminator: Dark Fate trailer blurs lines between humans and Terminators
Terminator: Dark Fate is due for release on 23 October in the United Kingdom , 31 October in Australia, and 1 November in the US. Back in 2015, Arnie returned as the T-800 for Terminator Genisys , the fifth entry in the time travel franchise.

Instead of viewing hundreds of individual 2D slices from a single low-dose CT scan as a radiologist would, the AI examines the lungs as a single 3D object-while also noting any changes over time by comparing differences with a patient's previous scans in order to help measure the growth rates of any suspicious lesions.

Coauthor Daniel Tse of Google tells STAT that the company has discussed with the Food and Drug Administration the steps that will be needed to get the artificial intelligence program approved for clinical use.

However, these medical tests have their limitations. "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. Major contributing factors to the development in lung cancer in never-smokers include second-hand smoke, occupational carcinogen exposure, and outdoor pollution.

The work demonstrates the potential for Artificial Intelligence (AI) to increase both accuracy and consistency, which could help accelerate adoption of lung cancer screening worldwide. However, there is room for improvement as screening results aren't always accurate-there tends to be high rates of false positives and false negatives because certain spots on the lungs can be mistaken for malignancies, while others are thought to be benign. However, by combining the experience of a human doctor with the brains of a deep learning algorithm, it's likely that fewer errors in diagnosis will be made, resulting in better overall quality of life for all of us.

With the AI capable of processing huge amounts of data, it could detect subtle patterns in cancer diagnoses that humans simply might not be able to identify.

Other reports by

Discuss This Article