Initial neural net construction for the detection of cervical intraepithelial neoplasia by fluorescence imaging
| Autor: | Gordon S. Okimoto, Steven J. Saggese, Gregory C. Mooradian, Kunio Miyazawa, Dennis M. O'Connor, Mary F. Parker |
|---|---|
| Rok vydání: | 2002 |
| Předmět: |
medicine.medical_specialty
Fluorescence-lifetime imaging microscopy Fluorescence spectrometry Uterine Cervical Neoplasms Cervical intraepithelial neoplasia Sensitivity and Specificity Predictive Value of Tests Positive predicative value Image Processing Computer-Assisted medicine Humans Spectral data Colposcopy Gynecology Intraepithelial neoplasia medicine.diagnostic_test business.industry Obstetrics and Gynecology Uterine Cervical Dysplasia medicine.disease Spectrometry Fluorescence Predictive value of tests Female Neural Networks Computer Radiology business |
| Zdroj: | American Journal of Obstetrics and Gynecology. 187:398-402 |
| ISSN: | 0002-9378 |
| DOI: | 10.1067/mob.2002.123940 |
| Popis: | Objective: The aim of this study was to initiate neural net construction for the detection of cervical intraepithelial neoplasia by fluorescence imaging. Study Design: Thirty-three women with abnormal Papanicolaou smears underwent fluorescence imaging during colposcopy. With the use of >4000 training pixels and >1000 test pixels, intrapatient nets were constructed from the spectral data of 17 women. An interpatient net that discriminated between cervical intraepithelial neoplasia 1 and normal tissue classes among patients was constructed with the use of >2300 training pixels and >2000 test pixels from 12 women. Average correct classification rates were determined. Sensitivities, specificities, and positive and negative predictive values for cervical intraepithelial neoplasia grade 1 and normal tissue classes were calculated. Extrapolated false-color cervical images were generated. Results: Average correct classification rates were 96.5% for the intrapatient nets and 97.5% for the interpatient net. The sensitivity, specificity, and positive and negative predictive values for cervical intraepithelial neoplasia grade 1 were 98.2%, 98.9%, 71.4%, and 99.9%, respectively. Conclusion: Initial results suggest that neural nets that are constructed from fluorescence imaging spectra may offer a potential method for the detection of cervical intraepithelial neoplasia. (Am J Obstet Gynecol 2002;187:398-402.) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect