English

Image Segmentation to Distinguish Between Overlapping Human Chromosomes

Computer Vision and Pattern Recognition 2017-12-21 v1 Machine Learning Quantitative Methods Machine Learning

Abstract

In medicine, visualizing chromosomes is important for medical diagnostics, drug development, and biomedical research. Unfortunately, chromosomes often overlap and it is necessary to identify and distinguish between the overlapping chromosomes. A segmentation solution that is fast and automated will enable scaling of cost effective medicine and biomedical research. We apply neural network-based image segmentation to the problem of distinguishing between partially overlapping DNA chromosomes. A convolutional neural network is customized for this problem. The results achieved intersection over union (IOU) scores of 94.7% for the overlapping region and 88-94% on the non-overlapping chromosome regions.

Keywords

Cite

@article{arxiv.1712.07639,
  title  = {Image Segmentation to Distinguish Between Overlapping Human Chromosomes},
  author = {R. Lily Hu and Jeremy Karnowski and Ross Fadely and Jean-Patrick Pommier},
  journal= {arXiv preprint arXiv:1712.07639},
  year   = {2017}
}

Comments

Presented at NIPS 2017 Machine Learning for Health

R2 v1 2026-06-22T23:25:02.109Z