A Novel Application of Image-to-Image Translation: Chromosome Straightening Framework by Learning from a Single Image

TL;DR

This paper introduces a novel image-to-image translation framework for chromosome straightening that learns from a single image, producing more accurate and continuous banding patterns than traditional geometric methods, and improves classification accuracy.

Contribution

It proposes a new deep learning-based framework for chromosome straightening that requires only one training image, overcoming data scarcity issues in medical imaging.

Findings

Outperforms geometric algorithms in straightening quality

Produces realistic, continuous chromosome banding patterns

Enhances chromosome classification accuracy by up to 1.39%

Abstract

In medical imaging, chromosome straightening plays a significant role in the pathological study of chromosomes and in the development of cytogenetic maps. Whereas different approaches exist for the straightening task, typically geometric algorithms are used whose outputs are characterized by jagged edges or fragments with discontinued banding patterns. To address the flaws in the geometric algorithms, we propose a novel framework based on image-to-image translation to learn a pertinent mapping dependence for synthesizing straightened chromosomes with uninterrupted banding patterns and preserved details. In addition, to avoid the pitfall of deficient input chromosomes, we construct an augmented dataset using only one single curved chromosome image for training models. Based on this framework, we apply two popular image-to-image translation architectures, U-shape networks and conditional generative adversarial networks, to assess its efficacy. Experiments on a dataset comprised of 642 real-world chromosomes demonstrate the superiority of our framework, as compared to the geometric method in straightening performance, by rendering realistic and continued chromosome details. Furthermore, our straightened results improve the chromosome classification by 0.98%-1.39% mean accuracy.