Google researchers developed a deep learning tool that can detect lung cancer with a level of accuracy that is on par or better than human radiologists.
A deep learning tool built by researchers at Google detected lung cancer as well as or better than human radiologists, showing the potential for AI to boost chances of survival for patients at risk.
In a study published in Nature Medicine, researchers said that lung cancer caused an estimated 160,000 deaths in 2018, making it the most common cause of cancer death in the US. Lung cancer screenings that use low-dose tomography have been shown to reduce mortality by 20-43 percent, but there are still challenges that result in unclear diagnoses, subsequent unnecessary procedures, and high costs.
Radiologists also usually have to look through dozens of 2D images within a single CT scan, and cancer can be hard to spot.
Want to publish your own articles on DistilINFO Publications?
Send us an email, we will get in touch with you.
Deep learning can offer a viable solution to these problems. The team developed a model using 45,856 de-identified chest CT screening cases from NIH’s National Lung Screening Trial study and Northwestern University. Researchers then compared the model’s performance to that of six board-certified radiologists.
When using a single CT scan for diagnosis, the model performed on par or better than human radiologists. The algorithm demonstrated a state-of-the-art performance, at 94.4 percent AUC. The model also reduced false positives by 11 percent and false negatives by five percent.
In addition to determining a patient’s overall lung malignancy, the model can detect subtle malignant tissue in the lungs. The deep learning algorithm can also factor in information from previous scans, which is helpful because the growth rate of suspicious tissue can be indicative of malignancy.
The researchers believe their findings show that deep learning and AI can significantly improve lung cancer screenings.
“Despite the value of lung cancer screenings, only 2-4 percent of eligible patients in the US are screened today. This work demonstrates the potential for AI to increase both accuracy and consistency, which could help accelerate adoption of lung cancer screening worldwide,” Shravya Shetty, MS, lead author on the study wrote in a blog post.
This study builds on Google’s past efforts to apply AI to problems in healthcare. In May 2018, researchers developed a deep learning algorithm that analyzed big data from the EHR to predict inpatient mortality, unexpected readmissions, and long length of stay more accurately than traditional predictive models.
The team at Google has also used machine learning and imaging analytics to detect breast cancer. Researchers found that the machine learning algorithms were able to flag breast cancer cells that had spread to nearby lymph nodes, which is a critical factor when determining how to best treat patients. The machine learning models outperformed other automated methods and rivaled human clinicians.
Although all this research seems to point only to the strength and promise of deep learning, the group noted that more investigation will be necessary before the technology can be used in real-world settings. Google Cloud’s Healthcare API will play a key role in advancing this technology and bridging the gap between care systems so that providers everywhere will have the power to unlock key data insights.
“These initial results are encouraging, but further studies will assess the impact and utility in clinical practice,” Shetty concluded. “We’re collaborating with Google Cloud Healthcare and Life Sciences team to serve this model through the Cloud Healthcare API and are in early conversations with partners around the world to continue additional clinical validation research and deployment.”
Date: May 29, 2019
Source: Health IT Analytics
