Google engineers have developed a new AI program capable of diagnosing lung cancer in patients more accurately than radiologists.
In order to screen for lung cancer, radiologists usually view hundreds of images from a single CT scan. With this new AI model, Google is able to generate a 3D model of overall lung cancer prediction and identify subtle malignant tissue, or lung nodules, which are often hard to see.
Additionally, the AI also factors in previous scans that can help reveal the growth rate of suspicious tissue. In order to test the model, Google asked its AI to examine 45,856 chest CT scans for various cancer stages.
The results were compared against six board-certified radiologists. Initially, Google’s AI detected 5% more cancer cases as compared to radiologists. Also, it reduced false-positive exams by over 11%.
At present, the AI model needs extra clinical research and testing before it can be deployed, but Google claims that the initial results are encouraging. “This creates an opportunity to optimize the screening process via computer assistance and automation,” the study authors said.
“While the vast majority of patients remain unscreened, we show the potential for deep learning models to increase the accuracy, consistency and adoption of lung cancer screening worldwide.”