Image processing and machine learning approaches for the automatic diagnosis of endometrial cancer

Abstract

In many medical imaging based diagnosis, Deep Learning (DL) algorithms play an essential role. A DL algorithm can be used to identify abnormal and normal cells in the uterus's endometrium in order to discover Endometrial Cancer (EC) cells. EC is difficult to diagnose since it develops without causing any symptoms. DL algorithm can distinguish between normal, abnormal, and malignant cells, producing more accurate findings than screening by hand procedures such as liquid cytology and Pap smear test. For the accurate and easier detection of EC cells, DL employs multiple architectures. The findings of an analysis and survey of the many forms of DL architecture, as well as their accuracy and performance, are addressed in this work. Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are the most modalities of advanced imaging used for the non-invasive diagnosis of EC. EC is considered as the fourth most prevalent malignancy in women and one of the common most gynaecological cancers. Diagnostic imaging in clinical evaluation with has not been proven yet to be precise enough to substitute surgical staging in determining the spread of cancer. It may allow for improved surgical process optimization and a more customised therapeutic plan.