Affiliations: [a] Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang, Jiangxi, China | [b] Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA | [c] Department of Gynecologic Oncology, Jiangxi Maternal and Child Health Hospital, Nanchang, Jiangxi, China | [d] Department of Biomedical Engineering, University of Houston, Houston, TX, USA
Correspondence:
[*]
Correspondence author: Ling Li, Department of Gynecologic Oncology, Jiangxi Maternal and Child Health Hospital, Nanchang, Jiangxi, China. Tel.: +86 13576947029; E-mail: [email protected].
Abstract: BACKGROUND: Screening tools are critical in the early prevention of cervical cancers. Acetic-acid based colposcopy test provides an affordable solution but is often challenged by the lack of experienced doctors in under-developed districts. OBJECTIVE: To evaluate the feasibility of an internet-based expert system to better utilize the expert knowledge. METHODS: A centralized internet-based expert system was developed to upload acetowhite images acquired by an integrated colposcopy device at remote healthcare centers. The detection rates of high grade cervical intraepithelial neoplasia (CIN) during two consecutive years (installed in the second year) were collected at two study sites and twelve control sites. RESULTS: No difference in the detection rate was observed between study and control sites at baseline (year 1); however, greater detection rates were found at study sites after introducing the internet-based expert system (year 2). Comparing the detection rates at each site between year 1 and year 2, the study site exhibited improved detection rates. User feedbacks suggested “great learning experience from expert feedback” as the most recognized benefits. CONCLUSIONS: This study shows the feasibility of an internet-based expert system in screening cervical cancers and lays the foundation to future population-level application in under-developed districts.
