Metastatic tumours — cancerous cells which break away from their tissue of origin, travel through the body through the circulatory or lymph systems, and form new tumours in other parts of the body — are notoriously difficult to detect. But Google on Friday claimed that its algorithm can assist doctors in metastatic breast cancer detection with 99 percent accuracy, according to their papers published in the Archives of Pathology and Laboratory Medicine and The American Journal of Surgical Pathology.
This AI is based on Inception-v3, which is an open source image recognition deep learning model. The researchers tested out their AI against the Lymph Node 2016 challenge dataset which contains 399 whole-slide images of lymph node sections from the Radboud University Medical Center and the University Medical Center Utrecht, and like we said, they claim that it managed to score 99.3% in accuracy.
For cancer detection and treatment, pathologists’ microscopic examination, which based on the results of reviewing patients slides, plays a vital role in the therapy. But analyzing the disease from those megapixel photos is a difficult task, doctors who are competent for the job must have years of training and experience.
Post Your Comments