Related Experiment Video
Updated: Jan 24, 2026

Author Spotlight: Efficient Retinal Ganglion Cell Counting in Mouse Models of Glaucoma for Treatment Evaluation
Published on: October 4, 2024
Automatic colony cell counting method of phytoplankton in microscopic images with multi-task learning
Renqing Jia1, Gaofang Yin2, Nanjing Zhao3
1Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China; Key Laboratory of Optical Monitoring Technology for Environment of Anhui Province, Hefei 230031, China; Wanjiang Emerging Industry Technology Development Center, Tongling 244002, China.
This study introduces a new AI method for identifying and counting colonial phytoplankton, improving aquatic ecosystem monitoring. The approach achieves high accuracy in both recognition and cell enumeration, addressing a key challenge in algal analysis.
Area of Science:
- Environmental Science
- Marine Biology
- Computational Biology
Background:
- Phytoplankton are crucial bioindicators for assessing aquatic ecosystem health.
- Automated image-based phytoplankton identification is advancing but struggles with colonial cell counting.
- Accurate species distribution and cell abundance are vital environmental assessment metrics.
Purpose of the Study:
- To develop a novel method for simultaneous phytoplankton recognition and cell counting.
- To overcome the challenges in accurately counting colonial phytoplankton cells.
- To provide a robust tool for automated aquatic algal monitoring.
Main Methods:
- Utilized ResNet50 for deep feature extraction from microscopic images of algal colonies.
- Implemented two parallel branches for classification and counting, with alternating training for parameter updates.
- Evaluated the method on 16 common colonial algae species from Lake Chaohu.
Main Results:
- Achieved 99.2% accuracy in phytoplankton identification.
- Reached 93.9% average accuracy in cell counting.
- Reported mean absolute error of 1.290 and mean squared error of 2.263.
Conclusions:
- The proposed method effectively integrates identification and counting for colonial phytoplankton.
- This unified framework addresses limitations in current automated monitoring tools.
- The approach offers a robust solution for precise aquatic algal assessment.
Related Concept Videos
Automatic Processing and Automatic Social Behavior
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Learning Disabilities
Dyslexia
Dyslexia is a...
Associative Learning
Classical conditioning, also known...
Purposive Learning
Observational Learning

