Related Experiment Video
Updated: Dec 12, 2025
Using Computer Vision Libraries to Streamline Nuclei Quantification
Published on: June 6, 2025
Automatic Detection Method for Cancer Cell Nucleus Image Based on Deep-Learning Analysis and Color Layer Signature
Hsing-Hao Su1,2, Hung-Wei Pan3, Chuan-Pin Lu4
1Department of Otorhinolaryngology-Head and Neck Surgery, Kaohsiung Veterans General Hospital, Kaohsiung 81362, Taiwan.
Abstract:
Exploring strategies to treat cancer has always been an aim of medical researchers. One of the available strategies is to use targeted therapy drugs to make the chromosomes in cancer cells unstable such that cell death can be induced, and the elimination of highly proliferative cancer cells can be achieved. Studies have reported that the mitotic defects and micronuclei in cancer cells can be used as biomarkers to evaluate the instability of the chromosomes. Researchers use these two biomarkers to assess the effects of drugs on eliminating cancer cells. However, manual work is required to count the number of cells exhibiting mitotic defects and micronuclei either directly from the viewing window of a microscope or from an image, which is tedious and creates errors. Therefore, this study aims to detect cells with mitotic defects and micronuclei by applying an approach that can automatically count the targets. This approach integrates the application of a convolutional neural network for normal cell identification and the proposed color layer signature analysis (CLSA) to spot cells with mitotic defects and micronuclei. This approach provides a method for researchers to detect colon cancer cells in an accurate and time-efficient manner, thereby decreasing errors and the processing time. The following sections will illustrate the methodology and workflow design of this study, as well as explain the practicality of the experimental comparisons and the results that were used to validate the practicality of this algorithm.
Insights
Researchers developed an automated method using AI and color analysis to detect cancer cells with chromosomal instability, improving accuracy and efficiency in drug development for cancer treatment.
Area of Science:
- Oncology
- Biotechnology
- Computational Biology
Background:
- Targeted cancer therapies aim to induce cancer cell death by destabilizing chromosomes.
- Mitotic defects and micronuclei serve as biomarkers for chromosomal instability and drug efficacy.
- Manual counting of these biomarkers is time-consuming and prone to errors.
Purpose of the Study:
- To develop an automated approach for detecting mitotic defects and micronuclei in cancer cells.
- To improve the accuracy and efficiency of assessing drug effects on cancer cell elimination.
- To provide a tool for accurate and time-efficient detection of colon cancer cells.
Main Methods:
- Integration of a convolutional neural network for normal cell identification.
- Application of Color Layer Signature Analysis (CLSA) to identify cells with mitotic defects and micronuclei.
- Development of an automated counting approach for these cellular biomarkers.
Main Results:
- The proposed approach enables accurate and automated detection of cells with mitotic defects and micronuclei.
- The method significantly reduces the time and potential for errors associated with manual counting.
- Validated algorithm demonstrates practicality for assessing cancer drug efficacy.
Conclusions:
- Automated detection of chromosomal instability biomarkers enhances cancer research efficiency.
- The developed AI-driven method offers a reliable tool for drug discovery and development.
- This approach facilitates faster and more accurate evaluation of targeted cancer therapies.
