Microscopy Imaging Enhancement

My research on microscopy image enhancement focuses on addressing challenges like noise, blur, and low contrast, which often limit the interpretability of microscopy data. Enhancing microscopy images requires addressing challenges like noise, blur, and limited contrast, which often obscure important details. My work involves designing and evaluating both traditional methods, such as deconvolution and denoising, and modern machine learning techniques to improve image quality. I experiment with approaches like Wiener filtering, Richardson-Lucy deconvolution, and wavelet transformations alongside deep-learning-based denoising and reconstruction methods. By quantitatively assessing improvements using metrics such as PSNR, SSIM, and SNR, I aim to develop robust tools that support researchers in extracting meaningful insights from noisy or degraded data. This research bridges the gap between computational imaging and practical applications, empowering advancements in microscopy-based scientific discovery.

Research Highlights

Investigating traditional methods, including Wiener deconvolution, Richardson-Lucy deconvolution, and wavelet-based denoising, to restore degraded images. (Dutta et al., 2024).
Developing deep learning-based pipelines for denoising, deblurring, and contrast enhancement, tailored to microscopy data.
Degrading images with controlled noise and blur to simulate real-world conditions, allowing for rigorous evaluation of enhancement methods.
Quantifying enhancements using metrics such as SNR, SSIM, and PSNR to assess their scientific value and practical relevance.

References

2024

IEEE
Recent Advancements in Microscopy Image Enhancement using Deep Learning: A Survey

Debasish Dutta, Neeharika Sonowal, Risheraj Barauh, and 2 more authors

In 2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI), 2024

10.1109/CVMI61877.2024.10782829
IEEE Explore

Abs Bib HTML PDF

Microscopy image enhancement plays a pivotal role in understanding the details of biological cells and materials at microscopic scales. In recent years, there has been a significant rise in the advancement of microscopy image enhancement, specifically with the help of deep learning methods. This survey paper aims to provide a snapshot of this rapidly growing state-of-the-art method, focusing on its evolution, applications, challenges, and future directions. The core discussions take place around the key domains of microscopy image enhancement of super-resolution, reconstruction, and denoising, with each domain explored in terms of its current trends and their practical utility of deep learning.
@inproceedings{ddcvmi2024, author = {Dutta, Debasish and Sonowal, Neeharika and Barauh, Risheraj and Chetia, Deepjyoti and Kalita, Sanjib Kr}, booktitle = {2024 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)}, title = {Recent Advancements in Microscopy Image Enhancement using Deep Learning: A Survey}, year = {2024}, volume = {}, number = {}, pages = {1-7}, ieee = {10782829}, dimensions = {true}, keywords = {Surveys;Deep learning;Evolution (biology);Microscopy;Biological system modeling;Noise reduction;Superresolution;Spatial resolution;Image enhancement;Image reconstruction;microscopy;deep learning;image restoration;image enhancement;super-resolution;deconvolution}, doi = {10.1109/CVMI61877.2024.10782829}, }