We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us
LGC Clinical Diagnostics

Download Mobile App




New Computational Model Significantly Improves Quality of Microscopy Images

By LabMedica International staff writers
Posted on 25 Dec 2024
Print article
Image: Illustration of an m-rBCR model for light microscopy (Photo courtesy of HZDR/A. Yakimovich)
Image: Illustration of an m-rBCR model for light microscopy (Photo courtesy of HZDR/A. Yakimovich)

The computational processing of images allows for the detailed examination of samples using various light microscopes. While there has been significant progress in this field, there remains potential to enhance aspects such as image contrast and resolution. Now, a new computational model, based on an advanced deep learning architecture, offers faster processing times while achieving or surpassing the image quality of traditional methods.

The model, called Multi-Stage Residual-BCR Net (m-rBCR), was specifically developed for microscopy images by researchers at Helmholtz-Zentrum Dresden-Rossendorf (HZDR, Dresden, German) and the Max Delbrück Center for Molecular Medicine (Berlin, Germany). It introduces a novel approach to image processing using deconvolution, a method aimed at improving the contrast and resolution of digital images captured by optical microscopes, including widefield, confocal, or transmission types. Deconvolution addresses image blur, which is a type of distortion caused by the optical system, and it can be performed in two main ways: explicit deconvolution and deep learning-based deconvolution.

Explicit deconvolution techniques rely on the concept of the point spread function (PSF), which describes how light from a point source is scattered by the optical system, creating a three-dimensional diffraction pattern. This spreading causes out-of-focus light to contribute to blur in a recorded image. By knowing the PSF of a system, the blur can be mathematically removed, producing a clearer representation of the original image. However, PSF-based deconvolution is limited by the difficulty in obtaining accurate or precise PSF data for certain systems. Blind deconvolution methods, where the PSF is estimated from the image itself, have been developed but still present significant challenges and have made limited progress.

To address this issue, the research team has applied "inverse problem-solving" techniques, which have proven effective in microscopy. Inverse problems involve determining the underlying factors that lead to certain observed results. Solving such problems typically requires large amounts of data and advanced deep learning algorithms. Like explicit deconvolution, the goal is to achieve higher-resolution or better-quality images. For their approach, presented at the ECCV, the team used a physics-informed neural network called m-rBCR. In image processing, there are two basic approaches: working with the spatial representation of an image or its frequency representation, the latter of which requires transforming the spatial data. Each method has its advantages, and the majority of deep learning models operate on the spatial domain, which works well for general photographs. However, microscopy images, particularly those from fluorescence microscopy, are often monochromatic and typically feature specific light sources against a dark background.

To address the unique challenges of microscopy images, m-rBCR begins with the frequency representation. This approach enables more meaningful optical data representations and allows the model to solve the deconvolution task with far fewer parameters compared to other deep learning models. The team validated the m-rBCR model across four different datasets—two simulated and two real microscopy datasets. It demonstrated high performance with significantly fewer training parameters and faster processing times than current deep learning models, while also outperforming explicit deconvolution methods.

“This new architecture is leveraging a neglected way to learn representations beyond the classic convolutional neural network approaches,” said co-author Prof. Misha Kudryashev, Leader of the “In situ Structural Biology” group of the Max Delbrück Center for Molecular Medicine. “Our model significantly reduces potentially redundant parameters. As the results show, this is not accompanied by a loss of performance. The model is explicitly suitable for microscopy images and, having a lightweight architecture, it is challenging the trend of ever-bigger models that require ever more computing power.”

Gold Member
Pharmacogenetics Panel
VeriDose Core Panel v2.0
Verification Panels for Assay Development & QC
Seroconversion Panels
New
Aspergillus Test
REALQUALITY Aspergillus
New
Auto Clinical Chemistry Analyzer
cobas c 703

Print article

Channels

Clinical Chemistry

view channel
Image: The tiny clay-based materials can be customized for a range of medical applications (Photo courtesy of Angira Roy and Sam O’Keefe)

‘Brilliantly Luminous’ Nanoscale Chemical Tool to Improve Disease Detection

Thousands of commercially available glowing molecules known as fluorophores are commonly used in medical imaging, disease detection, biomarker tagging, and chemical analysis. They are also integral in... Read more

Immunology

view channel
Image: The cancer stem cell test can accurately choose more effective treatments (Photo courtesy of University of Cincinnati)

Stem Cell Test Predicts Treatment Outcome for Patients with Platinum-Resistant Ovarian Cancer

Epithelial ovarian cancer frequently responds to chemotherapy initially, but eventually, the tumor develops resistance to the therapy, leading to regrowth. This resistance is partially due to the activation... Read more

Microbiology

view channel
Image: The lab-in-tube assay could improve TB diagnoses in rural or resource-limited areas (Photo courtesy of Kenny Lass/Tulane University)

Handheld Device Delivers Low-Cost TB Results in Less Than One Hour

Tuberculosis (TB) remains the deadliest infectious disease globally, affecting an estimated 10 million people annually. In 2021, about 4.2 million TB cases went undiagnosed or unreported, mainly due to... Read more

Technology

view channel
Image: The HIV-1 self-testing chip will be capable of selectively detecting HIV in whole blood samples (Photo courtesy of Shutterstock)

Disposable Microchip Technology Could Selectively Detect HIV in Whole Blood Samples

As of the end of 2023, approximately 40 million people globally were living with HIV, and around 630,000 individuals died from AIDS-related illnesses that same year. Despite a substantial decline in deaths... Read more

Industry

view channel
Image: The collaboration aims to leverage Oxford Nanopore\'s sequencing platform and Cepheid\'s GeneXpert system to advance the field of sequencing for infectious diseases (Photo courtesy of Cepheid)

Cepheid and Oxford Nanopore Technologies Partner on Advancing Automated Sequencing-Based Solutions

Cepheid (Sunnyvale, CA, USA), a leading molecular diagnostics company, and Oxford Nanopore Technologies (Oxford, UK), the company behind a new generation of sequencing-based molecular analysis technologies,... Read more
Copyright © 2000-2025 Globetech Media. All rights reserved.