Explainability Guided Multi-Site COVID-19 CT Classification
arXiv:2103.13677
Abstract
Radiologist examination of chest CT is an effective way for screening COVID-19 cases. In this work, we overcome three challenges in the automation of this process: (i) the limited number of supervised positive cases, (ii) the lack of region-based supervision, and (iii) the variability across acquisition sites. These challenges are met by incorporating a recent augmentation solution called SnapMix, by a new patch embedding technique, and by performing a test-time stability analysis. The three techniques are complementary and are all based on utilizing the heatmaps produced by the Class Activation Mapping (CAM) explainability method. Compared to the current state of the art, we obtain an increase of five percent in the F1 score on a site with a relatively high number of cases, and a gap twice as large for a site with much fewer training images.
References in corpus (4)
- Extracting possibly representative COVID-19 Biomarkers from X-Ray images with Deep Learning approach and image data related to Pulmonary Diseases
- Deep Image: Scaling up Image Recognition
- Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification
- Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization