Deep learning models for digital image processing: a review

Archana, R.; Jeevaraj, P. S. Eliahim

doi:10.1007/s10462-023-10631-z

Cited by 49 publications

(1 citation statement)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…High resolution of expanded large-scale tissues results in a huge amount of data, rendering whole-tissue 3D reconstruction and feature extraction tedious. Currently, machine learning is making efforts to partition regions of interest and data mining 103 and 3D volume stitching. 104 Lastly, currently established ExM variants are successful for cells and soft tissues, but few ExM variants for hard tissues like bones are developed.…”

Section: Discussionmentioning

confidence: 99%

Subdiffraction Imaging of Cleared and Expanded Large-Scale Tissues

Zhang,

Wu,

Shen

et al. 2024

Chemical & Biomedical Imaging

View full text Add to dashboard Cite

The quest for high spatial resolution in molecular identification is critical across various domains, including physiology, pathology, and pharmaceutical research. Super-resolution microscopy has made strides by surpassing the Abbe diffraction limit, but it relies on sophisticated equipment and is limited by the sample size to handle. Expansion microscopy, an emerging technique, has broadened the scope of subdiffraction imaging. It chemically preserves tissues at a large scale and physically enlarges them 4−20 times linearly, enabling superresolution observation. This review begins by exploring the foundational concepts of tissue clearing and the latest methodologies in the field. It then delves into the core tenets of expansion microscopy, covering a range of protocols. The review spotlights advancements in enhancing resolution, improving labeling efficiency, and ensuring isotropic tissue expansion. Finally, the review offers insights into the prospective evolution of expansion microscopy. It emphasizes the potential role of machine learning in refining image quality and in the autonomous extraction of data, which could revolutionize the way we visualize and understand biological tissues.

show abstract

Section: Discussionmentioning

confidence: 99%