Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach

Explore this paper's citation graph

Summary

This work proposes a method for disease available during training that is able to demonstrate performance comparable with models trained with strong annotations on the Camelyon-16 lymph node metastases detection challenge, and achieves this through the use of pre-trained deep convolutional networks, feature embedding, as well as learning via top instances and negative evidence.

Type
preprint
Published
2018-02-01
Cited by
128
References
36
Access
Open access

Keywords

Artificial intelligence, Computer science, Digital pathology, Segmentation, Pattern recognition (psychology)

References

Cited by

Related papers