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.
@article{arxiv.2201.10166,
title = {Dense Pixel-Labeling for Reverse-Transfer and Diagnostic Learning on Lung Ultrasound for COVID-19 and Pneumonia Detection},
author = {Gautam Rajendrakumar Gare and Andrew Schoenling and Vipin Philip and Hai V Tran and Bennett P deBoisblanc and Ricardo Luis Rodriguez and John Michael Galeotti},
journal= {arXiv preprint arXiv:2201.10166},
year = {2022}
}
Comments
Published in 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) \copyright 2021 IEEE