Design and Evaluation of Cervical Pap Smear E-learning System for the Education of Cytopathology
Po-Chi Huang, Jen‐Yung Lin, Li-En Wang, Yung‐Fa Huang, Shou-Wei Chien, Yung-Fu Chen · 2013
Cytology evaluation is a safe, efficient, and well-establis hed technique for the diagnoses of many diseases. Its abilit y to reduce the mortality and morbidity of cervical cancer is through mass screening to early detect dysplasia or pre-invasive cancer cells. Classical cytological diagnosis is based on microscopic observation of specialized cells and qualitative assessment using descriptive criteria, which may be inconsistent because of subjective variability of different observers. Recently, web-based le arning is becoming prevalent in schools and enterprises around the world for its advantages of providing easy access to information and knowledge, supporting ubiquitous learning environment, and increasing cost-effectiveness for both educational institution an d students. The objectives of this study were to design automatic classifier s based on integrated genetic algorithm (GA) and support vector machine (SVM) to cluster four different types of cervical cells and t o discriminate dysplasia from normal cells, as well as to implement a web-based cytopathology training and testing system to increase learning efficiency of cytopathologic education. A p rototypic system composed of a microscope, digital camera, personal computer, cellular processing and analyzing program, and cell classifier was designed to facilitate acquisition, image processing a nd analysis, and classification of cell images. Furthermore , a web-based cytopathology training and testing (WBCTT) systems were developed based on the classified cell images to train students , resident physicians, and novice pathologists to discriminate vario us types of cervical cells. The experimental results demonstrate that the classification and diagnostic accuracy achieves 96.82% and 99.6% , respectively. System evaluation based on questionnaire survey of extended technology acceptance model (TAM) shows that the proposed system embedded with cell classifier and WBCTT is u seful in cytopathology diagnosis and training. Most of the users agreed the operation interface is friendly and easy to use. They also expressed strong behaviour intention to further adopt the system. It i s expected to have significant contributions in increasing d iagnostic efficiency and promoting learning efficiency.