eduzhai > Applied Sciences > Engineering >

Unsupervised Learning of Deep-Learned Features from Breast Cancer Images

  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: Detecting cancer manually in whole slide images requires significant time andeffort on the laborious process. Recent advances in whole slide image analysishave stimulated the growth and development of machine learning-based approachesthat improve the efficiency and effectiveness in the diagnosis of cancerdiseases. In this paper, we propose an unsupervised learning approach fordetecting cancer in breast invasive carcinoma (BRCA) whole slide images. Theproposed method is fully automated and does not require human involvementduring the unsupervised learning procedure. We demonstrate the effectiveness ofthe proposed approach for cancer detection in BRCA and show how the machine canchoose the most appropriate clusters during the unsupervised learningprocedure. Moreover, we present a prototype application that enables users toselect relevant groups mapping all regions related to the groups in whole slideimages.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...