ChrSNet: Chromosome Straightening using Self-attention Guided Networks

TL;DR

This paper introduces ChrSNet, a self-attention based neural network framework that effectively straightens curved chromosomes in microscopic images, preserving details and length for improved karyotyping analysis.

Contribution

It proposes a novel self-attention guided network with geometric constraints and a synthetic dataset for chromosome straightening, advancing cytogenetic image processing.

Findings

Effectively straightens curved chromosomes in images.

Preserves banding patterns and chromosome length.

Performs well on both synthetic and real data.

Abstract

Karyotyping is an important procedure to assess the possible existence of chromosomal abnormalities. However, because of the non-rigid nature, chromosomes are usually heavily curved in microscopic images and such deformed shapes hinder the chromosome analysis for cytogeneticists. In this paper, we present a self-attention guided framework to erase the curvature of chromosomes. The proposed framework extracts spatial information and local textures to preserve banding patterns in a regression module. With complementary information from the bent chromosome, a refinement module is designed to further improve fine details. In addition, we propose two dedicated geometric constraints to maintain the length and restore the distortion of chromosomes. To train our framework, we create a synthetic dataset where curved chromosomes are generated from the real-world straight chromosomes by grid-deformation. Quantitative and qualitative experiments are conducted on synthetic and real-world data. Experimental results show that our proposed method can effectively straighten bent chromosomes while keeping banding details and length.