A coarse-to-fine approach for pericardial effusion localization and segmentation in chest CT scans

Pericardial effusion on CT scans demonstrates very high shape and volume variability and very low contrast to adjacent structures. This inhibits traditional automated segmentation methods from achieving high accuracies. Deep neural networks have been widely used for image segmentation in CT scans. In this work, we present a two-stage method for pericardial effusion localization and segmentation. For the first step, we localize the pericardial area from the entire CT volume, providing a reliable bounding box for the more refined segmentation step. A coarse-scaled holistically-nested convolutional networks (HNN) model is trained on the entire CT volume. The resulting FINN per-pixel probability maps are then thresholded to produce a bounding box covering the pericardial area. For the second step, a fine-scaled HNN model is trained only on the bounding box region for effusion segmentation to reduce the background distraction. Quantitative evaluation is performed on a dataset of 25 CT scans of patients (1206 images) with pericardial effusions. The segmentation accuracy of our two-stage method, measured by Dice Similarity Coefficient (DSC), is 75.59 +/- 12.04%, which is significantly better than the segmentation accuracy (62.74 +/- 15.20%) of only using the coarse-scaled FINN model.