Deep Learning Pipeline for Chromosome Segmentation

Deep Learning Pipeline for Chromosome Segmentation

Paper in proceedings (conference paper)

Chromosome segmentation is a challenging and time-consuming part of karyotyping and requires a high level of expertise. Computer segmentation algorithms still require the assistance of cytologists in more complicated cases with overlapping or touching chromosomes. Deep learning models have the potential to make the segmentation process completely automated, and their applications are currently actively re-searched. This paper proposes a segmentation pipeline by using deep learning models and traditional computer vision algorithms. This process can be split into four steps, in which we use U-Net architecture to remove any background noises of the metaphase image. Next, we use thresholding and skeletonization to extract and classify single chromosomes and chromosome clusters. As a final step, we use Mask R-CNN, for instance, segmentation on the overlapping and touching chromosomes, and apply test-time augmentation to improve the model's precision.

Chromosome segmentation is a challenging and time-consuming part of karyotyping and requires a high level of expertise. Computer segmentation algorithms still require the assistance of cytologists in more complicated cases with overlapping or touching chromosomes. Deep learning models have the potential to make the segmentation process completely automated, and their applications are currently actively re-searched. This paper proposes a segmentation pipeline by using deep learning models and traditional computer vision algorithms. This process can be split into four steps, in which we use U-Net architecture to remove any background noises of the metaphase image. Next, we use thresholding and skeletonization to extract and classify single chromosomes and chromosome clusters. As a final step, we use Mask R-CNN, for instance, segmentation on the overlapping and touching chromosomes, and apply test-time augmentation to improve the model's precision.

chromosome segmentation, karyotyping, deep learning, image processing, instance segmentation, test-time augmentation

chromosome segmentation, karyotyping, deep learning, image processing, instance segmentation, test-time augmentation

PIJÁČKOVÁ, K.; GÖTTHANS, T.; GÖTTHANS, J.

2023

03.05.2022

IEEE

978-1-7281-8686-3

2022 32nd International Conference Radioelektronika (RADIOELEKTRONIKA)

197

201

5

https://ieeexplore.ieee.org/document/9764950