Spatial Aggregation of Holistically-Nested Networks for Automated Pancreas Segmentation

TL;DR

This paper introduces a holistic learning method that combines deep interior and boundary cues with spatial aggregation to improve pancreas segmentation accuracy in CT scans, outperforming previous methods.

Contribution

The paper presents a novel spatial aggregation approach integrating deep mid-level cues for improved pancreas segmentation accuracy.

Findings

Achieved a Dice coefficient of 78.01%, surpassing the previous state-of-the-art of 71.8%.

Demonstrated robustness across 82 patient CT scans with 4-fold cross-validation.

Significantly improved segmentation performance over existing methods.

Abstract

Accurate automatic organ segmentation is an important yet challenging problem for medical image analysis. The pancreas is an abdominal organ with very high anatomical variability. This inhibits traditional segmentation methods from achieving high accuracies, especially compared to other organs such as the liver, heart or kidneys. In this paper, we present a holistic learning approach that integrates semantic mid-level cues of deeply-learned organ interior and boundary maps via robust spatial aggregation using random forest. Our method generates boundary preserving pixel-wise class labels for pancreas segmentation. Quantitative evaluation is performed on CT scans of 82 patients in 4-fold cross-validation. We achieve a (mean $\pm$ std. dev.) Dice Similarity Coefficient of 78.01% $\pm$ 8.2% in testing which significantly outperforms the previous state-of-the-art approach of 71.8% $\pm$ 10.7% under the same evaluation criterion.