Multimodal Hyperspectroscopy - The Use Of Digital Technology In Cervical Cancer Screening

ORVOSI HETILAP(2021)

Cited 0|Views9
No score
Abstract
Introduction: Despite the use of human papillomavirus (HPV) testing, the management of the transitional categories of cytology-based screening still remains a challenge. The modern multimodal hyperspectroscopy (MHS) of the cervix is a novel digital technology based on artificial intelligence, providing an instant result in the assessment of cytology-based screening abnormalities.Patients and methods: 208 women (age 18-75) were enrolled. The patients already had cytology results and an operation on the cervix indicated at the time of inclusion. HPV and the hyperspectroscopy examination was performed pre-operatively. The pre-indicated operation was performed on 166 patients.Results: Cytology-based screening alone (in the category of all patients) resulted in a high false-positive rate (69.28%). In this category, the MHS had an outstanding false-negative rate (3/166 = 1.80%) compared to the HPV (11/165 = 6.66%). The false-positive rate of the spectroscopy examination (91/166 = 54.81%) was higher than that of the HPV testing (40/165 = 24.24%). In the atypical squamous cell (ASC-US/ASC-H) category, the false-negative rate of the spectroscopy (3/126 = 2.38%) was also lower than that of the HPV test (9/126 = 7.14%). In the detection of high-grade abnormalities (cervical intraepithelial neoplasia 2 and worse), the spectroscopy had a 94% sensitivity (95% CI = 0.84-0.99), with a 22% specificity (95% CI = 0.15-0.31), an 90% negative predictive value (95% CI = 0.73- 0.98), and a 34% positive predictive value (95% CI = 0.26-0.43) (p = 0.00130).Conclusion: In the case of cytological abnormality, the MHS provides an immediate result based on advanced digital technology, and because of its outstanding false negative rate it is a great aid and should be considered in the triage of such patients.
More
Translated text
Key words
ASC-US, human papillomavirus, artificial intelligence, cervical intraepithelial neoplasia, spectroscopy
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined