Related Experiment Video
Updated: Jun 27, 2025
08:56
Simultaneous Imaging and Flow-Cytometry-based Detection of Multiple Fluorescent Senescence Markers in Therapy-Induced Senescent Cancer Cells
Published on: July 12, 2022
2.9K
Detection of bladder cancer cells using quantitative interferometric label-free imaging flow cytometry
Matan Dudaie1, Eden Dotan1, Itay Barnea1
1Faculty of Engineering, Department of Biomedical Engineering, Tel Aviv University, Tel Aviv, Israel.
Summary
A new non-invasive method uses interferometric imaging flow cytometry to detect bladder cancer cells in urine. This technique offers high accuracy for diagnosing bladder cancer, potentially replacing traditional cystoscopies.
Area of Science:
- Biomedical Engineering
- Medical Diagnostics
- Optical Imaging
Background:
- Bladder cancer is a common malignancy with a high recurrence rate, necessitating frequent, invasive, and costly surveillance methods like cystoscopies.
- Current diagnostic and surveillance methods for bladder cancer are invasive and burdensome for patients.
Purpose of the Study:
- To develop a non-invasive, label-free method for detecting bladder cancer cells in urine samples.
- To evaluate the efficacy of interferometric imaging flow cytometry combined with machine learning for bladder cancer cell classification.
Main Methods:
- Utilized interferometric imaging flow cytometry to quantitatively image unstained urothelial carcinoma cell lines and normal cells in a microfluidic chip.
- Employed deep-learning semantic segmentation convolutional neural network and extreme gradient boosting algorithms for cell classification.
- Applied the developed system to urine samples from bladder cancer patients and healthy volunteers.
Main Results:
- Achieved high accuracy (99%) and area under the curve (AUC) (97%) for cell line classification using both machine learning algorithms.
- Demonstrated strong performance on real urine samples with the deep-learning algorithm (96% accuracy, 96% AUC) and gradient-boosting algorithm (95% accuracy, 93% AUC).
- Successfully differentiated between healthy and malignant cells with high precision.
Conclusions:
- Label-free interferometric imaging flow cytometry coupled with advanced machine learning algorithms provides a highly effective method for bladder cancer detection.
- The proposed technique shows significant potential to serve as a non-invasive alternative to cystoscopy for bladder cancer surveillance and diagnosis.
