Convolutional neural network-based regression analysis to predict subnuclear chromatin organization from two-dimensional optical scattering signals

Yazdan Al-Kurdi; Cem Direkoǧlu; Meryem Erbilek; Dizem Arifler

doi:10.1117/1.JBO.29.8.080502

28 August 2024 Convolutional neural network-based regression analysis to predict subnuclear chromatin organization from two-dimensional optical scattering signals

Yazdan Al-Kurdi, Cem Direkoǧlu, Meryem Erbilek, Dizem Arifler

Author Affiliations +

Journal of Biomedical Optics, Vol. 29, Issue 8, 080502 (August 2024). https://doi.org/10.1117/1.JBO.29.8.080502

Abstract

Significance

Azimuth-resolved optical scattering signals obtained from cell nuclei are sensitive to changes in their internal refractive index profile. These two-dimensional signals can therefore offer significant insights into chromatin organization.

Aim

We aim to determine whether two-dimensional scattering signals can be used in an inverse scheme to extract the spatial correlation length ℓc and extent δn of subnuclear refractive index fluctuations to provide quantitative information on chromatin distribution.

Approach

Since an analytical formulation that links azimuth-resolved signals to ℓc and δn is not feasible, we set out to assess the potential of machine learning to predict these parameters via a data-driven approach. We carry out a convolutional neural network (CNN)-based regression analysis on 198 numerically computed signals for nuclear models constructed with ℓc varying in steps of 0.1 μm between 0.4 and 1.0 μm, and δn varying in steps of 0.005 between 0.005 and 0.035. We quantify the performance of our analysis using a five-fold cross-validation technique.

Results

The results show agreement between the true and predicted values for both ℓc and δn, with mean absolute percent errors of 8.5% and 13.5%, respectively. These errors are smaller than the minimum percent increment between successive values for respective parameters characterizing the constructed models and thus signify an extremely good prediction performance over the range of interest.

Conclusions

Our results reveal that CNN-based regression can be a powerful approach for exploiting the information content of two-dimensional optical scattering signals and hence monitoring chromatin organization in a quantitative manner.

CC BY: © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Citation Download Citation

Yazdan Al-Kurdi, Cem Direkoǧlu, Meryem Erbilek, and Dizem Arifler "Convolutional neural network-based regression analysis to predict subnuclear chromatin organization from two-dimensional optical scattering signals," Journal of Biomedical Optics 29(8), 080502 (28 August 2024). https://doi.org/10.1117/1.JBO.29.8.080502

Received: 12 April 2024; Accepted: 6 August 2024; Published: 28 August 2024

ACCESS THE FULL ARTICLE

JOURNAL ARTICLE
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Refractive index

Scattering

Convolutional neural networks

Finite-difference time-domain method

Interference (communication)

Signal to noise ratio

Cross validation

Significance

Aim

Approach

Results

Conclusions

Show All Keywords

Keywords/Phrases

Search In:

Publication Years