Related Experiment Video
Updated: Mar 27, 2026
10:37
A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells
Published on: August 22, 2025
1.4K
Label-Free Intraoperative Diagnosis of Breast Cancer Based on Multi-Angle Orthogonal Polarization Microscopy and
Jianbo Zhu1, Wenhui Sun1, Jinjin Wu1
1Department of Biomedical Engineering, College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China.
Journal of Biophotonics
|March 24, 2026
Summary
This study introduces a new label-free imaging method for rapid breast cancer diagnosis during surgery. The technique enhances collagen visualization, improving diagnostic accuracy and supporting timely surgical decisions.
Area of Science:
- Biomedical Imaging
- Oncology
- Pathology
Background:
- Intraoperative breast cancer diagnosis relies on time-consuming frozen-section pathology, delaying surgical decisions.
- Existing label-free imaging lacks comprehensive pathological information and diagnostic power.
Purpose of the Study:
- To develop a rapid, objective, label-free intraoperative diagnostic strategy for breast cancer.
- To overcome limitations of current imaging techniques by integrating multimodal data.
Main Methods:
- A multimodal fusion framework combining unstained multi-angle orthogonal polarization micro-imaging (OPMI) and bright-field micro-imaging (BFMI).
- Enhanced visualization of collagen fibers via image superposition and differencing.
- A dual-encoder fusion network for integrated global and local feature representation.
Main Results:
- Significantly enhanced optical contrast of anisotropic collagen fibers without staining.
- Identified local radial alignment and increased density of collagen fibers indicative of invasive progression.
- Achieved 91.83% accuracy and an AUC of 0.9295, outperforming unimodal and bimodal methods.
Conclusions:
- The proposed multimodal fusion framework offers a promising label-free intraoperative decision-support strategy for breast cancer.
- This approach enables objective visualization of malignancy-associated collagen alterations.
- The method improves lesion structure and boundary delineation for more accurate diagnosis.
