Research Output
Pap smear images classification based on surrounding tissues: A comparative study
Analysis of Cytology Pap Smear Images Based on Ensemble Deep Learning Approach
1 - 2 of 2
Publication
Cervical cancer is one of the most known health problems faced by women around the world. Early detection of cervical cancer may reduce the mortality rate. Pap smear images are new techniques used for screening cervical cancer. This paper excludes the nucleus of pap smear images, and the resultant images are classified into seven classes based on the surrounding region nucleus. Automated features are extracted using three pre-trained convolutional neural networks (CNN). The resultant features are twenty-one. The principal component analysis reduces the dimensionality and selects the most significant features into ten features. These features are fed to two types of machine learning algorithms: support vector machine (SVM) classifier and random forest classifier. The support vector machine classifier achieved the highest accuracy for seven classes, reaching 93.1%. This method will help the physicians in the diagnosis of cervical cancer depending on the tissues, not the nucleus. Furthermore, the result can be enhanced using a huge amount of data.
Publication
The fourth most prevalent cancer in women is cervical cancer, and early detection is crucial for effective treatment and prognostic prediction. Conventional cervical cancer screening and classifying methods are less reliable and accurate as they heavily rely on the expertise of a pathologist. As such, colposcopy is an essential part of preventing cervical cancer. Computer-assisted diagnosis is essential for expanding cervical cancer screening because visual screening results in misdiagnosis and low diagnostic effectiveness due to doctors’ increased workloads. Classifying a single cervical cell will overwhelm the physicians, in addition to the existence of overlap between cervical cells, which needs efficient algorithms to separate each cell individually. Focusing on the whole image is the best way and an easy task for the diagnosis. Therefore, looking for new methods to diagnose the whole image is necessary and more accurate. However, existing recognition algorithms do not work well for whole-slide image (WSI) analysis, failing to generalize for different stains and imaging, and displaying subpar clinical-level verification. This paper describes the design of a full ensemble deep learning model for the automatic diagnosis of the WSI. The proposed network discriminates between four classes with high accuracy, reaching up to 99.6%. This work is distinct from existing research in terms of simplicity, accuracy, and speed. It focuses on the whole staining slice image, not on a single cell. The designed deep learning structure considers the slice image with overlapping and non-overlapping cervical cells.