Related Experiment Video
Updated: Aug 23, 2025
06:25
Using Computer Vision Libraries to Streamline Nuclei Quantification
Published on: June 6, 2025
393
A Review of Nuclei Detection and Segmentation on Microscopy Images Using Deep Learning With Applications to Unbiased
IEEE Transactions on Neural Networks and Learning Systems
|November 3, 2022
Summary
Deep learning models accurately detect and segment cells and nuclei in stained tissue images, crucial for disease research. This review highlights advancements combining deep learning with stereology for improved medical image analysis.
Area of Science:
- Medical Image Analysis
- Computational Pathology
- Digital Pathology
Background:
- Accurate cell and nuclei detection/segmentation is vital for disease research.
- Deep learning (DL) shows promise in medical image analysis.
- Stereology is essential for quantitative microscopic analysis.
Purpose of the Study:
- Review recent DL approaches for cell/nuclei detection and segmentation.
- Focus on applications in cancer and Alzheimer's disease.
- Emphasize DL combined with unbiased stereology.
Main Methods:
- Literature review of DL techniques in cell detection/segmentation.
- Analysis of DL applications in cancer and Alzheimer's disease pathology.
- Integration of DL with stereological principles.
Main Results:
- DL significantly enhances cell and nuclei detection and segmentation accuracy.
- Combined DL and stereology offer robust quantitative analysis.
- Identified key challenges in reproducible microscopic image analysis.
Conclusions:
- DL is a powerful tool for cell detection and segmentation in pathology.
- Future trends point towards improved DL algorithms and integration with stereology.
- Advancements promise more accurate disease diagnosis and treatment development.
