โก Quick Summary
This study explored the integration of optical coherence tomography (OCT) and peripheral blood immune indicators to predict oral cancer prognosis using artificial intelligence. The developed model achieved an impressive AUC of 0.886, highlighting the significance of the systemic immune-inflammation index (SII) as a key prognostic indicator.
๐ Key Details
- ๐ Dataset: 68 patients, 289 oral mucosal samples, 1,445 OCT images
- ๐งฉ Features used: OCT images and peripheral blood immune indicators
- โ๏ธ Technology: Deep learning and multi-view radiomics model
- ๐ Performance: AUC 0.886, Accuracy 85.26%
๐ Key Takeaways
- ๐ Integration of imaging and blood indicators enhances oral cancer prognosis prediction.
- ๐ก The study developed a deep learning model that effectively utilizes OCT features.
- ๐ฉโ๐ฌ SII emerged as the most informative feature for prognosis prediction.
- ๐ The model achieved an AUC of 0.886, indicating excellent discrimination capability.
- ๐ค Deep learning model classified SII risk with an accuracy of 85.26%.
- ๐ Study conducted in a clinical setting, emphasizing real-world applicability.
- ๐ Clinical trial registered under ChiCTR2200064861.
๐ Background
Oral cancer remains a significant health concern, often diagnosed at advanced stages, leading to poor patient outcomes. Traditional prognostic methods can be limited in their predictive capabilities. The integration of advanced imaging techniques like optical coherence tomography (OCT) with peripheral blood immune indicators presents a promising avenue for enhancing prognostic accuracy and improving clinical decision-making.
๐๏ธ Study
This study involved patients undergoing radical oral cancer resection, where researchers aimed to explore the relationships among clinical data, OCT images, and peripheral immune indicators. A novel peripheral blood immune indicator-guided deep learning feature representation method was developed, leading to the creation of a comprehensive multi-view prognostic radiomics model.
๐ Results
The results were promising, with the deep radiomics-based prognosis model achieving an AUC of 0.886. The model identified the systemic immune-inflammation index (SII) as the most informative feature for predicting oral cancer prognosis. Additionally, the deep learning model demonstrated an accuracy of 85.26% in classifying SII risk, showcasing its potential for clinical application.
๐ Impact and Implications
The findings of this study underscore the potential of combining imaging and blood indicators in clinical practice. By leveraging advanced technologies like deep learning, healthcare professionals can enhance prognostic predictions for oral cancer, ultimately leading to better patient management and outcomes. This integration could pave the way for more personalized treatment strategies in oncology.
๐ฎ Conclusion
This study highlights the transformative potential of deep learning in the field of oral cancer prognosis. By merging OCT imaging with peripheral blood immune indicators, researchers have developed a robust model that can significantly improve prognostic accuracy. Continued exploration in this area could lead to groundbreaking advancements in cancer care and patient outcomes.
๐ฌ Your comments
What are your thoughts on the integration of imaging and blood indicators for cancer prognosis? We invite you to share your insights and engage in a discussion! ๐ฌ Leave your comments below or connect with us on social media:
Deep radiomics-based prognostic prediction of oral cancer using optical coherence tomography.
Abstract
BACKGROUND: This study aims to evaluate the integration of optical coherence tomography (OCT) and peripheral blood immune indicators for predicting oral cancer prognosis by artificial intelligence.
METHODS: In this study, we examined patients undergoing radical oral cancer resection and explored inherent relationships among clinical data, OCT images, and peripheral immune indicators for oral cancer prognosis. We firstly built a peripheral blood immune indicator-guided deep learning feature representation method for OCT images, and further integrated a multi-view prognostic radiomics model incorporating feature selection and logistic modeling. Thus, we can assess the prognostic impact of each indicator on oral cancer by quantifying OCT features.
RESULTS: We collected 289 oral mucosal samples from 68 patients, yielding 1,445 OCT images. Using our deep radiomics-based prognosis model, it achieved excellent discrimination for oral cancer prognosis with the area under the receiver operating characteristic curve (AUC) of 0.886, identifying systemic immune-inflammation index (SII) as the most informative feature for prognosis prediction. Additionally, the deep learning model also performed excellent results with 85.26% accuracy and 0.86 AUC in classifying the SII risk.
CONCLUSIONS: Our study effectively merged OCT imaging with peripheral blood immune indicators to create a deep learning-based model for inflammatory risk prediction in oral cancer. Additionally, we constructed a comprehensive multi-view radiomics model that utilizes deep learning features for accurate prognosis prediction. The study highlighted the significance of the SII as a crucial indicator for evaluating patient outcomes, corroborating our clinical statistical analyses. This integration underscores the potential of combining imaging and blood indicators in clinical decision-making.
TRIAL REGISTRATION: The clinical trial associated with this study was prospectively registered in the Chinese Clinical Trial Registry with the trial registration number (TRN) ChiCTR2200064861. The registration was completed on 2021.
Author: [‘Yuan W’, ‘Rao J’, ‘Liu Y’, ‘Li S’, ‘Qin L’, ‘Huang X’]
Journal: BMC Oral Health
Citation: Yuan W, et al. Deep radiomics-based prognostic prediction of oral cancer using optical coherence tomography. Deep radiomics-based prognostic prediction of oral cancer using optical coherence tomography. 2024; 24:1117. doi: 10.1186/s12903-024-04849-8