Browsing by Author "Verhoeven, Veronique M."

Now showing 1 - 2 of 2

Knowledge and perceptions about cervical cancer and HPV screening in women in rural areas of Ecuador: a qualitative research study
(2022) Vega Crespo, Bernardo José; Maldonado Rengel, Ruth; Espinosa González, María Elena; Neira Molina, Vivian Alejandra; Verhoeven, Veronique M.; Bautista Valarezo, Estefanía
Background: Cervical cancer continues to be a major health problem in developing countries. Educational programs, as well as Pap and HPV screening and vaccination, are important tools to reduce the morbidity and mortality rates associated with this disease. The objective of this study is to explore the diverse knowledge and perceptions about cervical cancer and the different diagnostic tests for HPV of populations living in the rural parish “El Valle”. Method: A qualitative study was conducted through eight focus groups, which included 46 participants from mixed ethnic groups. A phenomenological analysis was performed. Results: Four topics and seven sub-topics were identified. By analyzing all the narratives, it was possible to identify that the perception of cervical cancer was focused on its severity, secondary to its infectious process and screening periodicity. However, despite the diverse knowledge, indigenous people do not relate it to the human papilloma virus; in addition, there is also certain resistance to undergo the Pap smear test, for reasons such as inaccessibility and its sampling process. Conclusions: It is necessary to develop educational programs for the prevention of cervical cancer and to implement diagnostic alternatives to reach populations with precarious accessibility, as well as women who refuse to undergo the Pap smear test.
Radiomics Diagnostic Tool Based on Deep Learning for Colposcopy Image Classification
(2022) Dávila Sacoto, Santiago Arturo; Jiménez Gaona, Yuliana; Vicuña, María José; Verhoeven, Veronique M.; Neira Molina, Vivian Alejandra; Castillo Malla, Darwin Patricio; Vega Crespo, Bernardo José
Background: Colposcopy imaging is widely used to diagnose, treat and follow-up on premalignant and malignant lesions in the vulva, vagina, and cervix. Thus, deep learning algorithms are being used widely in cervical cancer diagnosis tools. In this study, we developed and preliminarily validated a model based on the Unet network plus SVM to classify cervical lesions on colposcopy images. Methodology: Two sets of images were used: the Intel & Mobile ODT Cervical Cancer Screening public dataset, and a private dataset from a public hospital in Ecuador during a routine colposcopy, after the application of acetic acid and lugol. For the latter, the corresponding clinical information was collected, specifically cytology on the PAP smear and the screening of human papillomavirus testing, prior to colposcopy. The lesions of the cervix or regions of interest were segmented and classified by the Unet and the SVM model, respectively. Results: The CAD system was evaluated for the ability to predict the risk of cervical cancer. The lesion segmentation metric results indicate a DICE of 50%, a precision of 65%, and an accuracy of 80%. The classification results’ sensitivity, specificity, and accuracy were 70%, 48.8%, and 58%, respectively. Randomly, 20 images were selected and sent to 13 expert colposcopists for a statistical comparison between visual evaluation experts and the CAD tool (p-value of 0.597). Conclusion: The CAD system needs to improve but could be acceptable in an environment where women have limited access to clinicians for the diagnosis, follow-up, and treatment of cervical cancer; better performance is possible through the exploration of other deep learning methods with larger datasets.