Related Experiment Video
Updated: Jun 22, 2025
12:41
Multiparametric Tumor Organoid Drug Screening Using Widefield Live-Cell Imaging for Bulk and Single-Organoid Analysis
Published on: December 23, 2022
4.8K
Segmentation and Multi-Timepoint Tracking of 3D Cancer Organoids from Optical Coherence Tomography Images Using Deep
Francesco Branciforti1, Massimo Salvi1, Filippo D'Agostino1
1Biolab, PolitoBIOMed Lab, Department of Electronics and Telecommunications, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Turin, Italy.
Diagnostics (Basel, Switzerland)
|June 27, 2024
Summary
This study introduces an automated deep learning pipeline for tracking organoid growth using optical coherence tomography (OCT) imaging. The method accurately monitors organoid development and morphological changes over 13 days, advancing in vitro modeling.
Area of Science:
- Biomedical Engineering
- Biotechnology
- Medical Imaging
Background:
- Organoids are advanced 3D in vitro models derived from stem cells or tumor cells.
- Quantitative monitoring of organoid growth is crucial but challenging.
- Optical coherence tomography (OCT) offers label-free, high-resolution 3D imaging for organoid analysis.
Purpose of the Study:
- To develop an automated deep learning pipeline for accurate organoid identification and quantification in OCT images.
- To enable long-term tracking and analysis of organoid growth and morphological changes.
- To provide a foundation for drug screening and tumor drug sensitivity detection using organoids.
Main Methods:
- A deep learning pipeline utilizing convolutional neural networks (CNNs).
- Optimized preprocessing and ad-hoc postprocessing steps for image analysis.
- A tracking algorithm incorporating reference volumes, dual branch analysis, and probability scoring.
Main Results:
- Demonstrated good generalizability and tracking capabilities over 13 days.
- Enabled accurate tracking of organoid growth and morphological evolution.
- The pipeline effectively identifies and quantifies organoids in OCT images.
Conclusions:
- The proposed deep learning pipeline significantly advances organoid analysis using OCT.
- This approach provides a robust method for monitoring organoid development over time.
- It lays the groundwork for future applications in drug screening and personalized medicine.
