Published January 1, 2017 | Version v1
Conference paper Open

Automated cancer stem cell recognition in H&E stained tissue using convolutional neural networks and color deconvolution

  • 1. Fraunhofer Inst Integrated Circuits IIS, Image Proc & Med Engn Dept, Erlangen, Germany
  • 2. Bilkent Univ, Ankara, Turkey
  • 3. Middle East Tech Univ, Canc Syst Biol Lab, Ankara, Turkey
  • 4. Hacettepe Univ, Ankara, Turkey
  • 5. Friedrich Alexander Univ Erlangen Nuremberg FAU, Comp Graph Grp, Erlangen, Germany

Description

The analysis and interpretation of histopathological samples and images is an important discipline in the diagnosis of various diseases, especially cancer. An important factor in prognosis and treatment with the aim of a precision medicine is the determination of so-called cancer stem cells (CSC) which are known for their resistance to chemotherapeutic treatment and involvement in tumor recurrence. Using immunohistochemistry with CSC markers like CD13, CD133 and others is one way to identify CSC. In our work we aim at identifying CSC presence on ubiquitous Hematoxilyn & Eosin (H&E) staining as an inexpensive tool for routine histopathology based on their distinct morphological features.

Files

bib-bbc26ff0-23d6-4afc-94de-a051491a5eee.txt

Files (295 Bytes)

Name Size Download all
md5:a4781abfabc39d3b144f31f071f21782
295 Bytes Preview Download