Applied Deep Learning to Identify and Localize Polyps from Endoscopic Images

TL;DR

This paper introduces a new publicly available dataset of endoscopic images from India with annotations for polyps and ulcers, and evaluates deep learning models for detection and classification tasks in biomedical imaging.

Contribution

It provides the first Indian dataset of endoscopic images with annotations and assesses the transferability of deep learning models across different datasets.

Findings

Models trained on large datasets perform well on the new Indian dataset.

The dataset enables detection and classification of polyps and ulcers.

Open sourcing the dataset supports further research in biomedical imaging.

Abstract

Deep learning based neural networks have gained popularity for a variety of biomedical imaging applications. In the last few years several works have shown the use of these methods for colon cancer detection and the early results have been promising. These methods can potentially be utilized to assist doctor's and may help in identifying the number of lesions or abnormalities in a diagnosis session. From our literature survey we found out that there is a lack of publicly available labeled data. Thus, as part of this work, we have aimed at open sourcing a dataset which contains annotations of polyps and ulcers. This is the first dataset that's coming from India containing polyp and ulcer images. The dataset can be used for detection and classification tasks. We also evaluated our dataset with several popular deep learning object detection models that's trained on large publicly available datasets and found out empirically that the model trained on one dataset works well on our dataset that has data being captured in a different acquisition device.