Deep Learning-Assisted Assessing of Single Circulating Tumor Cell Viability via Cellular Morphology
Yiyao Yang1, Zhaoliang Wang2,3, Tingting Hao1
1State Key Laboratory for Managing Biotic and Chemical Threats to the Quality and Safety of Agro-products, School of Material Science and Chemical Engineering, Ningbo University, Ningbo 315211, PR China.
Analytical Chemistry
|October 9, 2024
Summary
This study introduces a deep learning model to assess the viability of circulating tumor cells (CTCs) in blood. The AI model accurately identifies and analyzes single CTCs, aiding cancer diagnosis and treatment monitoring.
Area of Science:
- Oncology
- Biomedical Engineering
- Artificial Intelligence in Medicine
Background:
- Circulating tumor cells (CTCs) are vital indicators of cancer metastasis and recurrence.
- Assessing CTC viability is critical for cancer diagnosis, prognosis, and treatment efficacy.
- The scarcity of CTCs in blood poses challenges for accurate single-cell viability assessment.
Purpose of the Study:
- To develop and validate a deep learning model for accurate identification and viability assessment of single CTCs.
- To overcome the limitations of traditional methods in analyzing rare CTCs.
- To provide a noninvasive tool for evaluating CTC viability in clinical settings.
Main Methods:
- A convolutional neural network (CNN)-based deep learning model was constructed and trained.
- The model was trained to extract morphological features of CTCs with varying viabilities.
- Cell viability was defined using the cell counting kit-8 assay.
Main Results:
- The deep learning model achieved accurate identification of CTCs.
- The model successfully assessed the viability of individual CTCs based on morphological features.
- The developed method demonstrated efficiency and accuracy in CTC viability analysis.
Conclusions:
- Deep learning offers a powerful, noninvasive approach for single CTC viability assessment.
- This technology has significant potential for improving cancer diagnosis, prognosis, and treatment monitoring.
- The AI-driven method addresses the challenge of analyzing rare CTCs in blood samples.
