Objective: To develop and evaluate the clinical application of a multimodal colposcopy combining multispectral reflectance, autofluorescence and RGB imaging for early screening of cervical intraepithelial neoplasia (CIN).
Methods: We developed a multimodal colposcopy system that combined multispectral reflectance, autofluorescence, and RGB imaging for early screening of CIN. We studied the optical properties of cervical tissue first, then the imaging system was designed and tested in clinical trial where comprehensive datasets were acquired and analyzed to differentiate between squamous normal and high grade types of cervical tissue.
Results: The specially designed multimodal colposcopy is capable of acquiring multispectral reflectance images, autofluorescence images, and RGB images of cervical tissue consecutively. The classification algorithm was employed on both normal and abnormal cases for image segmentation. The sensitivity and specificity performance of this system related to gold standard of histopathology show statistical significance.
Conclusions: Our pilot study demonstrated the clinical potential of this multimodal colposcopic system for early screening of CIN. The low-cost portable characteristics, the simple operating process, and the simple image segmentation algorithm of this system make it possibility to address the needs for CIN early screening in a rapid, cost-effective, and non-invasive fashion in the developing countries.