Multimodal endoscopic system based on multispectral and photometric stereo imaging and analysis

Area of Science:

• Medical Imaging
• Gastroenterology
• Oncology

Background:

• Current colonoscopy methods face challenges in accurately diagnosing diverse colorectal cancer (CRC) lesion types.
• Enhancements in diagnostic accuracy for CRC via colonoscopy have been reported, yet limitations persist.

Purpose of the Study:

• To develop and evaluate a multimodal endoscopic system for improved colorectal cancer examination.
• To simultaneously discriminate tumor distributions and provide 3D morphological information of the colon surface.

Main Methods:

• Integration of white light (WL), multispectral (MS), and photometric stereo (PS) imaging modalities into a single endoscopic system.
• Utilizing combined imaging data for enhanced visualization and analysis of colon tissues.

Main Results:

• The multimodal system successfully discriminated tumor distributions on the colon surface.
• The system provided accurate three-dimensional (3D) morphological information, aiding in lesion characterization.
• Demonstrated capability to analyze diverse lesion types beyond current endoscopic limitations.

Conclusions:

• The proposed multimodal endoscopic system shows significant potential for advancing colorectal cancer diagnosis.
• Combining WL, MS, and PS imaging offers a powerful approach for enhanced CRC detection and characterization.
• Further development and clinical validation could lead to improved patient outcomes in CRC screening.