Learning from Pseudo Lesion: A Self-supervised Framework for COVID-19 Diagnosis

TL;DR

This paper introduces a self-supervised learning framework for COVID-19 diagnosis from CT scans, using pseudo lesion generation to improve feature extraction without requiring labeled data, leading to higher diagnostic accuracy.

Contribution

A novel self-supervised pretraining method using pseudo lesion generation with Perlin noise for COVID-19 CT diagnosis, reducing dependence on labeled data.

Findings

Outperforms supervised models pretrained on large datasets.

Achieves 6.57% and 3.03% higher accuracy on two datasets.

Effective feature extraction for COVID-19 diagnosis.

Abstract

The Coronavirus disease 2019 (COVID-19) has rapidly spread all over the world since its first report in December 2019 and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based approaches have shown impressive performance in myriad image recognition tasks. However, they usually require a large number of annotated data for training. Inspired by Ground Glass Opacity (GGO), a common finding in COIVD-19 patient's CT scans, we proposed in this paper a novel self-supervised pretraining method based on pseudo lesions generation and restoration for COVID-19 diagnosis. We used Perlin noise, a gradient noise based mathematical model, to generate lesion-like patterns, which were then randomly pasted to the lung regions of normal CT images to generate pseudo COVID-19 images. The pairs of normal and pseudo COVID-19 images were then used to train an encoder-decoder architecture based U-Net for image restoration, which does not require any labelled data. The pretrained encoder was then fine-tuned using labelled data for COVID-19 diagnosis task. Two public COVID-19 diagnosis datasets made up of CT images were employed for evaluation. Comprehensive experimental results demonstrated that the proposed self-supervised learning approach could extract better feature representation for COVID-19 diagnosis and the accuracy of the proposed method outperformed the supervised model pretrained on large scale images by 6.57% and 3.03% on SARS-CoV-2 dataset and Jinan COVID-19 dataset, respectively.