Self-Supervised U-Net for Segmenting Flat and Sessile Polyps

TL;DR

This paper introduces a self-supervised U-Net approach for segmenting flat and sessile polyps in colonoscopy images, improving accuracy with limited labeled data by leveraging unlabeled data for pre-training.

Contribution

The paper proposes a novel self-supervised training method for U-Net that enhances polyp segmentation accuracy using limited labeled data and large unlabeled datasets.

Findings

Self-supervised U-Net outperforms five supervised models on the Kvasir-Sessile dataset.

Pre-training with unlabeled data improves segmentation accuracy in limited data scenarios.

The approach reduces the need for extensive annotated datasets in polyp segmentation.

Abstract

Colorectal Cancer(CRC) poses a great risk to public health. It is the third most common cause of cancer in the US. Development of colorectal polyps is one of the earliest signs of cancer. Early detection and resection of polyps can greatly increase survival rate to 90%. Manual inspection can cause misdetections because polyps vary in color, shape, size and appearance. To this end, Computer-Aided Diagnosis systems(CADx) has been proposed that detect polyps by processing the colonoscopic videos. The system acts a secondary check to help clinicians reduce misdetections so that polyps may be resected before they transform to cancer. Polyps vary in color, shape, size, texture and appearance. As a result, the miss rate of polyps is between 6% and 27% despite the prominence of CADx solutions. Furthermore, sessile and flat polyps which have diameter less than 10 mm are more likely to be undetected. Convolutional Neural Networks(CNN) have shown promising results in polyp segmentation. However, all of these works have a supervised approach and are limited by the size of the dataset. It was observed that smaller datasets reduce the segmentation accuracy of ResUNet++. We train a U-Net to inpaint randomly dropped out pixels in the image as a proxy task. The dataset we use for pre-training is Kvasir-SEG dataset. This is followed by a supervised training on the limited Kvasir-Sessile dataset. Our experimental results demonstrate that with limited annotated dataset and a larger unlabeled dataset, self-supervised approach is a better alternative than fully supervised approach. Specifically, our self-supervised U-Net performs better than five segmentation models which were trained in supervised manner on the Kvasir-Sessile dataset.