A Robust Framework of Chromosome Straightening with ViT-Patch GAN

TL;DR

This paper introduces ViT-Patch GAN, a novel framework for chromosome straightening that improves detail preservation and generalization using a transformer-based discriminator and a motion learning generator.

Contribution

The paper presents a new architecture combining a self-learned motion generator with a ViT-based discriminator for robust chromosome straightening.

Findings

Achieves better FID, LPIPS, and classification accuracy.

Demonstrates excellent generalization on large datasets.

Retains shape and banding details effectively.

Abstract

Chromosomes carry the genetic information of humans. They exhibit non-rigid and non-articulated nature with varying degrees of curvature. Chromosome straightening is an important step for subsequent karyotype construction, pathological diagnosis and cytogenetic map development. However, robust chromosome straightening remains challenging, due to the unavailability of training images, distorted chromosome details and shapes after straightening, as well as poor generalization capability. In this paper, we propose a novel architecture, ViT-Patch GAN, consisting of a self-learned motion transformation generator and a Vision Transformer-based patch (ViT-Patch) discriminator. The generator learns the motion representation of chromosomes for straightening. With the help of the ViT-Patch discriminator, the straightened chromosomes retain more shape and banding pattern details. The experimental results show that the proposed method achieves better performance on Fr\'echet Inception Distance (FID), Learned Perceptual Image Patch Similarity (LPIPS) and downstream chromosome classification accuracy, and shows excellent generalization capability on a large dataset.