RUPNet: Residual upsampling network for real-time polyp segmentation

TL;DR

RUPNet is a novel real-time deep learning architecture for colon polyp segmentation that achieves high accuracy and speed, potentially improving early detection and clinical outcomes.

Contribution

The paper introduces RUPNet, a new encoder-decoder network with residual upsampling blocks designed for fast and accurate polyp segmentation in real-time.

Findings

Achieves 152.60 fps processing speed at 512x512 image size

Attains an average dice coefficient of 0.7658

Demonstrates high sensitivity and precision in polyp detection

Abstract

Colorectal cancer is among the most prevalent cause of cancer-related mortality worldwide. Detection and removal of polyps at an early stage can help reduce mortality and even help in spreading over adjacent organs. Early polyp detection could save the lives of millions of patients over the world as well as reduce the clinical burden. However, the detection polyp rate varies significantly among endoscopists. There is numerous deep learning-based method proposed, however, most of the studies improve accuracy. Here, we propose a novel architecture, Residual Upsampling Network (RUPNet) for colon polyp segmentation that can process in real-time and show high recall and precision. The proposed architecture, RUPNet, is an encoder-decoder network that consists of three encoders, three decoder blocks, and some additional upsampling blocks at the end of the network. With an image size of $512 \times 512$, the proposed method achieves an excellent real-time operation speed of 152.60 frames per second with an average dice coefficient of 0.7658, mean intersection of union of 0.6553, sensitivity of 0.8049, precision of 0.7995, and F2-score of 0.9361. The results suggest that RUPNet can give real-time feedback while retaining high accuracy indicating a good benchmark for early polyp detection.