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.

翻译：染色体承载着人类的遗传信息，具有非刚性、非关节化的特性，并呈现不同程度的弯曲。染色体拉直是后续核型构建、病理诊断和细胞遗传学图谱绘制的重要步骤。然而，由于训练图像的不可获取性、拉直后染色体细节和形状的畸变以及泛化能力的不足，稳健的染色体拉直仍然具有挑战性。本文提出了一种新颖的架构——ViT-Patch GAN，它由自学习运动变换生成器和基于Vision Transformer的补丁（ViT-Patch）判别器组成。该生成器学习染色体的运动表示以实现拉直。借助ViT-Patch判别器，拉直后的染色体保留了更多的形状和带型细节。实验结果表明，所提方法在Fr\'echet Inception Distance（FID）、Learned Perceptual Image Patch Similarity（LPIPS）和下游染色体分类准确率上均取得了更优性能，并且在大规模数据集上展现出卓越的泛化能力。