Dense Pixel-Labeling for Reverse-Transfer and Diagnostic Learning on Lung Ultrasound for COVID-19 and Pneumonia Detection

TL;DR

This paper introduces a reverse-transfer learning approach using pre-trained segmentation models for lung ultrasound classification, demonstrating improved accuracy and interpretability in detecting COVID-19 and Pneumonia.

Contribution

It presents a novel architecture to convert segmentation models into classifiers and compares dense versus sparse labeling impacts on diagnostic accuracy.

Findings

Dense labels reduce false positives in segmentation.

Pre-trained segmentation models outperform non-pretrained models.

Dense-label pretraining yields the best classification results.

Abstract

We propose using a pre-trained segmentation model to perform diagnostic classification in order to achieve better generalization and interpretability, terming the technique reverse-transfer learning. We present an architecture to convert segmentation models to classification models. We compare and contrast dense vs sparse segmentation labeling and study its impact on diagnostic classification. We compare the performance of U-Net trained with dense and sparse labels to segment A-lines, B-lines, and Pleural lines on a custom dataset of lung ultrasound scans from 4 patients. Our experiments show that dense labels help reduce false positive detection. We study the classification capability of the dense and sparse trained U-Net and contrast it with a non-pretrained U-Net, to detect and differentiate COVID-19 and Pneumonia on a large ultrasound dataset of about 40k curvilinear and linear probe images. Our segmentation-based models perform better classification when using pretrained segmentation weights, with the dense-label pretrained U-Net performing the best.