Emerging Technologies, Signal Processing and Statistical Methods for Screening of Cervical Cancer In Vivo: Are They Good Candidates for Cervical Screening?

摘要

The current cervical cancer screening test (the Pap smear) is a manual cytological procedure. This cytology test has various limitations and many errors. Excellent candidates for improving the performance of the cervical cancer screening procedure are electro-optical systems (EOSs), used for assessment of the cervical cancer precursors in vivo, such as digital spectroscopy, digital colposcopy and bioelectrical phenomena-based systems. These EOSs use the advantages of signal processing methods and can replace the qualitative assessments, with objective metrics. The EOSs can be used as an adjunct to the current screener or as a primary screener. We analyse and discuss the effectiveness of the signal processing and statistical methods for diagnosis of cervical cancer in vivo. This analysis is reinforced by the presentation of the scientific and clinical contributions of these methods in clinical practice. As a result of this analysis, we outline and discuss the well-established estimates of the signal processing features and the ambiguous features, that are used for classification of the cervical pre-cancer in vivo.