Google Research Blog

The latest news from Research at Google

Assisting Pathologists in Detecting Cancer with Deep Learning

Friday, March 03, 2017

Posted by Martin Stumpe, Technical Lead, and Lily Peng, Product Manageras low as 48%similarly lowRadboud University Medical Center2016 ISBI Camelyon Challenge¹Inception (aka GoogLeNet) worked reasonably well

Left: Images from two lymph node biopsies. Middle: earlier results of our deep learning tumor detection. Right: our current results. Notice the visibly reduced noise (potential false positives) between the two versions.

FROC²scores as high as 81%Detecting Cancer Metastases on Gigapixel Pathology Images

A closeup of a lymph node biopsy. The tissue contains a breast cancer metastasis as well as macrophages, which look similar to tumor but are benign normal tissue. Our algorithm successfully identifies the tumor region (bright green) and is not confused by the macrophages.

Like most metrics, the FROC localization score is not perfect. Here, the FROC score is defined as the sensitivity (percentage of tumors detected) at a few pre-defined average false positives per slide. It is pretty rare for a pathologist to make a false positive call (mistaking normal cells as tumor). For example, the score of 73% mentioned above corresponds to a 73% sensitivity and zero false positives. By contrast, our algorithm’s sensitivity rises when more false positives are allowed. At 8 false positives per slide, our algorithms had a sensitivity of 92%.

These algorithms perform well for the tasks for which they are trained, but lack the breadth of knowledge and experience of human pathologists — for example, being able to detect other abnormalities that the model has not been explicitly trained to classify (e.g. inflammatory process, autoimmune disease, or other types of cancer).

To ensure the best clinical outcome for patients, these algorithms need to be incorporated in a way that complements the pathologist’s workflow. We envision that algorithm such as ours could improve the efficiency and consistency of pathologists. For example, pathologists could reduce their false negative rates (percentage of undetected tumors) by reviewing the top ranked predicted tumor regions including up to 8 false positive regions per slide. As another example, these algorithms could enable pathologists to easily and accurately measure tumor size, a factor that is associated with prognosis.

1 For those who might be interested, the Camelyon17 challenge, which builds upon the 2016 challenge, is currently underway.^↩

2 The pathologist ended up spending 30 hours on this task on 130 slides.^↩