All Things Trending

Google’s AI predicts Lung Cancer

by Winnifred-Dmonte
May 22, 2019 19:18

https://f002.backblazeb2.com/b2api/v1/b2_download_file_by_id?fileId=4_za8a2358db1d7f91b68b30916_f11694c6d00bfdd30_d20190718_m123615_c002_v0001125_t0016

Being the world’s deadliest cancer, many die as a result of lung cancer. In the recent years there has been a stream of new life-extending treatments for lung cancer, yet it remains a deadly disease. According to Dr. Alan Sandler, Group Medical Director at Roche, “It remains one of the most difficult-to-treat cancers”. If cancer is caught early, the interventions are much more successful. Sadly, majority of the cancers are not caught until the later stages which makes it difficult to treat. Over the past three years, Google has been applying AI to solve the problems related to healthcare which includes diagnosing eye disease, predicting patient’s outcomes in medical records and much more.

Today a new research came up which shows that how AI can help predicting lung cancer that could boost the chances of survival for many people at risk around the world with a 94.4 percent success rate. The research was initiated in late 2017. Google’s AI for lung cancer diagnosis proves more accurate than certified radiologists in some regards. The AI-powered model uses a current CT scan and if possible, a previous CT scan, as input for each patient. Based on this, the model provides an overall malignancy prediction, which can help increasing the survival rate because medical treatment can be more successful when the cancer is caught early. Google said, “We created a model that can not only generate the overall lung cancer malignancy prediction (viewed in 3D volume) but also identify subtle malignant tissue in the lungs.

The model can also factor in information from previous scans, useful in predicting lung cancer risk because the growth rate of suspicious lung nodules can be indicative of malignancy”. Explaining the process followed by radiologists Google said, “It’s tedious. Radiologists look through hundreds of 2D images of a single CT scan where cancer is minuscule and can be easily missed”. Google claimed that its AI model has worked better than six radiologists, detecting five percent more cases. Google confirmed that further studies will be carried out to assess the impact and utility in clinical practice. Google says, “The initial results are encouraging but the model needs additional clinical research and testing before it can be deployed”. Google hopes that this one might make early detection more accessible. Following this research, we are starting to see how the technology could one day lead to far better patient outcomes. Link - https://youtu.be/1YVAxhi2tLE