Each year, the treatment decisions for more than 230 , 000 breast cancer patients in the U.S. hinge on whether the cancer has metastasized away from the breast. Metastasis detection is currently performed by pathologists reviewing large expanses of biological tissues. This process is labor intensive and error-prone. They present a framework to automatically detect and localize tumors as small as 100 ×100 pixels in gigapixel microscopy images sized 100 , 000 ×100 , 000 pixels. The method leverages a convolutional neural network (CNN) architecture and obtains state-of-the-art results on the Camelyon16 dataset in the challenging lesion-level tumor detection task. At 8 false positives per image, we detect 92 .4% of the tumors, relative to 82 .7% by the previous best automated approach. For comparison, a human pathologist attempting exhaustive search achieved 73.2% sensitivity. They achieve image-level AUC scores above 97% on both the Camelyon16 test set and an independent set of 110 slides. In addition, they discover that two slides in the Camelyon16 training set were erroneously labeled normal. This approach could considerably reduce false negative rates in metastasis detection.
Input variables : Pathology images
Output Variables : Tumor patches
Visit Model : arxiv.org
Additional links : arxiv.org
| Model Category | : | Public |
| Date Published | : | March, 2017 |
| Healthcare Domain | : |
Medical Technology
Provider |
| Code | : | github.com |
| Health Risk Management |
| Disease Detection |