Identification of cervical neoplasia using a simulation of human vision

Objective. To determine whether a computer simulation of human vision could detect and discriminate cervical cancer precursors and cancer from normal epithelium. Methods. The Georgia Tech Vision (TGV) system was trained to recognize normal and abnormal cervical features. GTV then assessed a new series of images to determine whether it could detect and diagnose cervical neoplasia without any a priori information about the images. Results. After training on one set and testing on another set of images. GTV demonstrated 100% sensitivity and 98% specificity to detect cervical intraepithelial neoplasia 3 (CIN3). GTV also had 88% sensitivity and 93% specificity to detect cervical cancer following training on one set and testing on another set of digitized cervical colposcopic images. Conclusion: This study demonstrated that GTV can detect CIN3 and cancer from digitized cervical colposcopic images. Furthermore, GTV could discriminate cervical cancer precursors and cancer from normal cervical epithelim, including immature metaplasia.