Towards scanning electron microscopy image denoising: a state-of-the-art overview, benchmark, taxonomies, and future direction

SSMM Rahman, M Salomon, S Dembélé - Machine Vision and …, 2024 - Springer
Scanning electron microscope (SEM) enables imaging of micro-nano scale objects. It is an
analytical tool widely used in the material, earth and life sciences. However, SEM images …

Denoising of Optical Coherence Tomography Images in Ophthalmology Using Deep Learning: A Systematic Review

H Ahmed, Q Zhang, R Donnan, A Alomainy - Journal of Imaging, 2024 - mdpi.com
Background: Open Access Systematic Review Denoising of Optical Coherence Tomography
Images in Ophthalmology Using Deep Learning: A Systematic Review by Hanya Ahmed …

A retinex based non-local total generalized variation framework for OCT image restoration

A Smitha, IP Febin, P Jidesh - Biomedical Signal Processing and Control, 2022 - Elsevier
A retinex driven non-local total generalized variational (TGV) model is proposed in this
paper to restore and enhance speckled images. The combined first and second-order TGV …

A nonlocal deep image prior model to restore optical coherence tomographic images from gamma distributed speckle noise

A Smitha, P Jidesh - Journal of Modern Optics, 2021 - Taylor & Francis
Optical Coherence Tomography (OCT) is often employed to observe the retinal layers in the
human eyes. The retinal scans are susceptible to artefacts such as head movements or eye …

Radiomics, deep learning, and breast cancer detection

YJ Gaona, MJ Rodríguez-Álvarez… - … in Cancer Diagnosis …, 2022 - iopscience.iop.org
This chapter gives an overview of deep learning use in multiple-imaging-modality radiomics
data. Specifically, we deal with the characterization of breast cancer using medical images …

Mimic Deep Learning Technique for Retinal Images Denoising in IoT based Medical Devices

A Rana, VK Srivastava - 2022 IEEE 2nd Mysore Sub Section …, 2022 - ieeexplore.ieee.org
Retinal images are careful, non-invasive, as well as non-radioactive imaging tool in the
development of medical imaging. Yet, the large volume of image datasets and lengthy times …