An Endometrial Tumor (ET) is a common uterine disease that continues to play a significant role in the mortality linked to a tumor. Advanced ET diagnosis exhibits worse diagnostic accuracy. The medically used ET screening methods require a significant amount of time and money, and not all patients can easily access them. So, oncologists have focused huge attention on molecular modeling as it has grown quickly, which has sped up the invention of computer-aided tumor detection systems. Artificial Intelligence (AI) models offer possibilities for molecular diagnostics, early tumor classification, efficient diagnosis, and diagnosis modality selection. It may be especially pertinent to use AI models in ET detection, classification, and diagnosis. From this perspective, researchers have been actively developing and implementing AI models to create effective ET diagnostic systems. This article studies the background of ET characteristics and earlier diagnosis techniques to stimulate further research in this field. The review is planned to investigate AI models, such as Machine Learning (ML) and Deep Learning (DL) algorithms, for ET detection, classification, and diagnosis. After that, the positives and negatives of each classification model, such as Logistic Regression (LR), Support Vector Machine (SVM), Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) networks, are compared. Amongst them, a multi-modal CNN-LSTM model achieves 93% accuracy on the TCGA-UCEC dataset, compared to the other models. At last, promising prospects are emphasized to achieve greater efficiency in classifying and diagnosing ET.