CeLaTis: A Large Scale Multimodal Dataset with Deep Region Network to Diagnose Cervical Cancer

Cervical cancer is a leading cause of mortality in third world countries. Although there are multiple ways of screening cervical cancer, colposcope image analysis is considered to be standard routine method of diagnosis. Due to factors like lack of skilled personnel and interobserver variability, there is a need for automated diagnostic support for cervical cancer. However, artificial intelligence solutions for medical image analysis done through deep and machine learning models require high quality, non-erroneous and sufficient amount of data. Owing to the lack of such established benchmark datasets for the colposcope images, this work aims at establishing a standard benchmark multi state colposcope image dataset that also contains clinical findings pertaining to each case. In order to establish the quality of the images, mask R-CNN method is used for segmenting the images. Subsequently, a series of IMAGENet pretrained deep learning models are deployed on the dataset to evaluate the performance. The dataset will be made available upon request for strictly research purposes.