High-throughput microscopy enables researchers to acquire thousands of images automatically over a short time, making it possible to conduct large-scale, image-based experiments for biological or biomedical discovery. However, visual analysis of large-scale image data is a daunting task. The post-acquisition component of high-throughput microscopy experiments calls for effective and efficient computer vision techniques.
Computer Vision for Microscopy Image Analysis provides a comprehensive and in-depth introduction to state-of-the-art computer vision techniques for microscopy image analysis, demonstrating how they can be effectively applied to biological and medical data.
The reader of the book will learn:
- How computer vision analysis can automate and enhance human assessment of microscopy images for discovery
- The important steps in microscopy image analysis
- State-of-the-art methods for microscopy image analysis including machine learning and deep neural network approaches
This reference on the state-of-the-art computer vision methods in microscopy image analysis is suitable for researchers and graduate students interested in analyzing microscopy images or for developing toolsets for general biomedical image analysis applications.
- Each topic contains a comprehensive overview of the field, followed by in-depth presentation of a state-of-the-art approach
- Perspectives and content contributed by both technologists and biologists
- Tackles specific problems of detection, segmentation, classification, tracking, cellular event detection
- Contains the fundamentals of object measurement in microscopy images
- Contains open source data and toolsets for microscopy image analysis on an accompanying website
1. A biologists perspective on computer vision
2. Microscopy image formation, restoration and segmentation
3. Detection and segmentation in microscopy images
4. Visual feature representation in microscopy image classification
5. Cell tracking in time-lapse microscopy image sequences
6. Mitosis detection in biomedical images
7. Object measurements from 2D microscopy images
8. Deep learning-based nuclei segmentation and classification in
histopathology images with application to imaging genomics
9. Open data and software for microscopy image analysis
Mei Chen is a principal research manager at Microsoft. She was an associate professor in the Electrical and Computer Engineering Department and director for the Information Science PhD Program at the State University of New York, Albany. She was the founding chair for the Workshop on Computer Vision for Microscopy Image Analysis that has been held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition since 2016. Mei has published extensively in computer vision and biomedical image analysis. Her work was nominated as a finalist for six Best Paper Awards, for which she won three. She earned a PhD in robotics from the School of Computer Science, Carnegie Mellon University, and an MS and BS from Tsinghua University, Beijing, China.
Lisainfo e-raamatute kohta