Automatic Segmentation Framework for Fluorescence in Situ Hybridization Cancer Diagnosis

1 0
  • 0 Collaborators

A method for the cancer diagnosis on the basis of FISH (Fluorescence In Situ Hybridization) test. ...learn more

Artificial Intelligence

Groups
Student Developers for AI

Overview / Usage

Algorithms: FISH Pattern recognition, Image processing, Computer aided diagnosis, Breast cancer, Nuclei segmentation, neural networks, SOM, PCA

In this project we address a problem of HER2 and CEN-17 reactions detection in fluorescence in situ hybridization images. These images are very often used in situation where typical biopsy examination is not able to provide enough information to decide on the type of treatment the patient should undergo. Here the main focus is placed on the automatization of the procedure. Using an unsupervised neural network and principal component analysis, we present a segmentation framework that is able to keep the high segmentation accuracy. For comparison purposes we test the neural network approach against an automatic threshold method.

Learn more: https://link.springer.com/chapter/10.1007/978-3-319-45378-1_14

Comments (0)