SpatialAggregationof.PDFVIP

Spatial Aggregation of Holistically-Nested Networks for Automated Pancreas Segmentation Holger R. Roth, Le Lu, Amal Farag, B Andrew Sohn, and Ronald M. Summers( ) Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, National Institutes of Health, Bethesda, MD 20892-1182, USA rms@ 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 tra- ditional 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 ± std. dev.) Dice Similarity Coe?cient of 78.01 %±8.2 % in testing which signi?cantly outperforms the previous state-of-the-art approach of 71.8 %±10.7 % under the same evaluation criterion. 1 Introduction Pancreas segmentation in computed tomography (CT) is challenging for cur- rent computer-aided diagnosis (CAD) systems. While automatic segmentation of numerous other organs in CT scans such as liver, heart or kidneys achieves good performance with Dice Similarity Coe?cients (DSC) of 90 % [1–3], the pancreas’ variable shape, size and location in the abdomen limits segmentation accuracy to 73 % DSC be