An algorithm to straighten the bent human chromosomes

Arora, Tanvi; Dhir, Renu; Mahajan, Manish

doi:10.1109/iciip.2017.8313772

Cited by 13 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there are two categories of geometric methods (medial axis extraction [10]- [12] and bending points localization [6], [15]), we find that the morphological and Stentiford thinning algorithms of medial axis extraction may cause many unexpected branches and irregular rings. Therefore, we investigate the performance of chromosome straightening using (a) the geometric method (bending points localization) whose main component is used by [6], [15], and our imageto-image translation model based framework with (b) U-Net and (c) pix2pix models.…”

Section: ) Comparison Of Straightening Performancementioning

confidence: 87%

“…For the first approach, Barrett et al [9] requires user interaction and manual labels. References [10]- [12] utilize thinning algorithms, such as morphological thinning [13] and Stentiford thinning algorithms [14]. However, such algorithms are not suitable for chromosomes with pronounced widths, resulting in many branches along their central axes when thinned [11], [12].…”

mentioning

confidence: 99%

“…3 illustrates that the morphological and Stentiford thinning algorithms may cause branches and irregular rings when the chromosome is with pronounced widths. Thus the previous chromosome straightening works [10]- [12] composed of these thinning algorithms cannot be utilized in this work. In contrast, our predicted 10-point central axis are approximately in accordance with the actual chromosome backbone.…”

mentioning

confidence: 99%

See 2 more Smart Citations

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

Song¹,

Huang²,

Hu³

et al. 2021

Preprint

View full text Add to dashboard Cite

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, they are mostly geometric algorithms 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 comprising 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, achieving 0.98%-1.39% in mean accuracy.

show abstract

Section: ) Comparison Of Straightening Performancementioning

confidence: 87%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

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

Song¹,

Huang²,

Hu³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The straightening method is inspired by similar techniques used to straighten images of human chromosomes (e.g., Jahani and Kamaledin Setarehdan (2012); Arora et al. (2017)). Like ARs, chromosomes may appear straight, bent and at various orientations in their microscope scans.…”

Section: Methodsmentioning

confidence: 99%

Improving the Understanding of Atmospheric River Water Vapor Transport Using a Three‐Dimensional Straightened Composite Analysis

Wang

Chang

et al. 2022

JGR Atmospheres

View full text Add to dashboard Cite

Irregular shapes of atmospheric rivers (ARs) hamper easy AR composite analyses and understandings of AR's moisture transport mechanisms. We develop a method to composite AR‐related variables from a reanalysis data set. By averaging a large number of samples, the three‐dimensional structure and some evolutionary features of a typical North Pacific AR are revealed. An AR is typically located along and in advance of the surface cold front of an extratropical cyclone. A mesoscale secondary circulation is observed in the cross sections of the AR corridor, where both geostrophic and ageostrophic winds make indispensable contributions to the moisture fluxes. Geostrophic moisture advection across the cold front within the Equatorward half of the AR is created by baroclinicity of the system and serves as the primary moisture source for the AR. Moisture fluxes from the warm sector of the cyclone are primarily due to boundary layer ageostrophic winds and are more important within the poleward half of the AR, particularly during the genesis stage. Faster AR movement compared with low‐level winds enables the AR to collect downwind moisture. In an AR‐relative view, this is represented as an easterly flow, consistent with the “feeder‐airstream” concept, and emphasizes the role of local moisture recycling. Moisture transport within the Equatorward half is mostly due to geostrophic advection of the propagating AR‐cyclone couple in an Earth‐relative view. Driven by intensifying geostrophic winds, ARs tend to reach peak moisture transport intensity about 2 days after genesis. Then, reduced moisture level and influxes from lateral boundaries prevent further intensification.

show abstract

“…(i) Printed images of bent chromosome are physically cut and rearranged for straightening [4], [5]. (ii) Geometric algorithms are extensively designed based on chromosome micrographs for automatic straightening, which consist of two main categories: extraction of the medial axis [6]- [9] and finding bending points [10]- [12]. However, these geometric methods may extract inaccurate medial axes when chromosomes have large widths.…”

Section: Introductionmentioning

confidence: 99%

A Robust Framework of Chromosome Straightening with ViT-Patch GAN

Song¹,

Wang²,

Cheng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Chromosomes exhibit non-rigid and non-articulated nature with varying degrees of curvature. Chromosome straightening is an essential 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. We propose a novel architecture, ViT-Patch GAN, consisting of a 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 proposed framework is trained on a small dataset and is able to straighten chromosome images with stateof-the-art performance for two large datasets.

show abstract

An algorithm to straighten the bent human chromosomes

Cited by 13 publications

References 12 publications

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

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

Improving the Understanding of Atmospheric River Water Vapor Transport Using a Three‐Dimensional Straightened Composite Analysis

A Robust Framework of Chromosome Straightening with ViT-Patch GAN

Contact Info

Product

Resources

About