โก Quick Summary
This study explored the use of Depth-in-Color En Face Optical Coherence Tomography (OCT) for classifying colorectal polyps, achieving an impressive AUC of 0.90 for detecting malignant potential. The findings suggest that this innovative approach could significantly enhance colorectal cancer screening strategies.
๐ Key Details
- ๐ Dataset: 300 subjects with colorectal polyps
- ๐งฉ Imaging Technique: Depth-sensitive OCT with color encoding
- โ๏ธ Methodology: Ensemble learning and score-level fusion
- ๐ Performance: AUC of 0.90 for all polyps, 0.88 for diminutive polyps (โค 5 mm)
๐ Key Takeaways
- ๐ฌ Depth-sensitive OCT enhances the visualization of polyp structures.
- ๐ก Ensemble learning improves classification accuracy for malignant potential.
- ๐ High AUC values indicate strong diagnostic performance.
- ๐ฉบ Potential clinical applications include ‘diagnose and leave’ and ‘resect and discard’ strategies.
- ๐ Results may meet ASGE’s PIVI criteria for negative predictive value (NPV).
- ๐ง Future research is needed to validate findings in vivo.
๐ Background
Colorectal cancer remains a leading cause of cancer-related deaths globally, primarily due to challenges in accurately detecting precursor lesions such as polyps. Traditional imaging techniques often struggle with the ambiguous surface appearances of these lesions, necessitating innovative approaches to improve diagnostic accuracy and patient outcomes.
๐๏ธ Study
The study involved imaging colorectal polyps from 300 subjects using a novel Depth-in-Color En Face OCT technique. By encoding depth information in color, researchers aimed to enhance the visualization of polyp structures, facilitating better classification of their malignant potential. The resulting en face projections were meticulously annotated and utilized to train an ensemble learning network.
๐ Results
The results were promising, with the ensemble network achieving an AUC of 0.90 for all polyps and 0.88 for diminutive polyps (โค 5 mm). These metrics indicate a high degree of accuracy in classifying the malignant potential of polyps ex vivo, suggesting that this method could significantly improve colorectal cancer screening practices.
๐ Impact and Implications
If validated in vivo, this study’s findings could revolutionize colorectal cancer screening by enabling more accurate and efficient classification of polyps. The potential to implement ‘diagnose and leave’ or ‘resect and discard’ strategies could lead to reduced patient burden and healthcare costs, ultimately improving patient outcomes in colorectal cancer management.
๐ฎ Conclusion
This study highlights the transformative potential of Depth-in-Color En Face OCT in colorectal polyp classification. With high accuracy rates demonstrated through ensemble learning, this technology could pave the way for enhanced screening protocols in clinical practice. Continued research is essential to confirm these findings and explore broader applications in gastrointestinal diagnostics.
๐ฌ Your comments
What are your thoughts on this innovative approach to colorectal cancer screening? We would love to hear your insights! ๐ฌ Join the conversation in the comments below or connect with us on social media:
Feasibility of Depth-in-Color En Face Optical Coherence Tomography for Colorectal Polyp Classification Using Ensemble Learning and Score-Level Fusion.
Abstract
In colorectal cancer screening, accurate detection of precursor lesions is challenging due to their ambiguous surface appearance. Depth-sensitive optical coherence tomography (OCT) with deep learning may improve accuracy. OCT imaging was performed on polyps from 300 subjects. Depth was encoded (surface, mid, deep) in color to generate en face OCT projections. En face projections were then annotated. The projections were then used to train an ensemble network based on the malignant potential of polyps. The area under the curve (AUC) for detecting malignant potential of all polyps was 0.90, and for diminutive polyps (โคโ5โmm), it was 0.88. These results demonstrate a high degree of accuracy in classifying malignant potential exย vivo. Should these results hold inย vivo, this algorithm would meet the ASGE’s PIVI criteria for NPV, supporting clinical use of OCT for either a lower colon ‘diagnose and leave’ strategy and/or ‘resect and discard’ strategy for diminutive polyps.
Author: [‘Thrapp AD’, “D’Mello S”, ‘Pitris C’, ‘Photiou C’, ‘Lamphier G’, ‘Villareyna-Lopez E’, ‘Chung A’, ‘Grant C’, ‘Schulz-Hildenbrandt H’, ‘Caravaca-Mora O’, ‘Miller T’, ‘Song DR’, ‘Khalili H’, ‘Nishioka NS’, ‘Tearney G’]
Journal: J Biophotonics
Citation: Thrapp AD, et al. Feasibility of Depth-in-Color En Face Optical Coherence Tomography for Colorectal Polyp Classification Using Ensemble Learning and Score-Level Fusion. Feasibility of Depth-in-Color En Face Optical Coherence Tomography for Colorectal Polyp Classification Using Ensemble Learning and Score-Level Fusion. 2026; 19:e202500292. doi: 10.1002/jbio.202500292