Explainability Guided Multi-Site COVID-19 CT Classification
This work improves COVID-19 screening efficiency for radiologists, but it is incremental as it builds on existing explainability methods.
The paper tackled automating COVID-19 CT classification by addressing challenges like limited supervised cases, lack of region-based supervision, and site variability, resulting in a 5% F1 score increase on a high-case site and a larger gap on a low-case site.
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.