Google AI can spot advanced breast cancer more effectively than humans

Donna Miller
October 17, 2018

Google hopes the tool could at one point serve as a "spell check" for doctors treating breast cancer patients.

However, Google's LYNA isn't ideal.

Despite misidentifying giant cells, germinal cancers and histiocytes, LYNA managed to perform better than a pathologist. The results were remarkable when LYNA worked as a companion to pathologists.

Hunting for small (micro) metastases was subjectively "easier", scientists reported, when working alongside the AI, which reduced average slide review time by 50 percent.

Up and coming Belfast model Mairead O'Neill dies age 21
An initial target of £4,000 was reached within just two hours of the page being opened with the total passing £6,000 last night. Mairead O'Neill, a young model, has died shortly after her mother died from a battle with cancer.

The scientific report published on this issue explains that: "Artificial Intelligence Algorithms can exhaustively evaluate each occurrence, individually and in detail".

In a new study, titled "Artificial Intelligence Based Breast Cancer Nodal Metastasis Detection", researchers outline how an AI called LYNA (short for "Lymph Node Assistant") can be trained how to spot breast cancer that has metastasized (spread beyond its original location) and compromised the lymph nodes, which are a system of tubes spread across the body that help filter and fight harmful substances. As the investigators explained, it examines a 299-pixel image (Inception-v3 default image size), then analyzes volumes at the pixel level and then exports them as labels - that is, predictions and classifies them as benign or malignant. The team used two sets of pathological slides to train the algorithm to identify characteristics of tumors in varying conditions.

Google has invested enough money in artificial intelligence applications for health care.

"In the first paper, we applied our algorithm to de-identified pathology slides from both the Camelyon Challenge and an independent dataset provided by our co-authors at the Naval Medical Center San Diego", Google said in its blog post. Additionally, Verily, which is Alphabet's life sciences subsidiary, is developing a system that determines a person's risk of heart disease using retinal scans.

Other reports by

Discuss This Article

FOLLOW OUR NEWSPAPER