Morphology-guided deep learning framework for segmentation of pancreas in computed tomography images

Abstract

Purpose: Accurate segmentation of the pancreas using abdominal computed tomography (CT) scans is a prerequisite for a computer-aided diagnosis system to detect pathologies and perform quantitative assessment of pancreatic disorders. Manual outlining of the pancreas is tedious, time-consuming, and prone to subjective errors, and thus clearly not a viable solution for large datasets. Approach: We introduce a multiphase morphology-guided deep learning framework for efficient three-dimensional segmentation of the pancreas in CT images. The methodology works by localizing the pancreas using a modified visual geometry group-19 architecture, which is a 19-layer convolutional neural network model that helped reduce the region of interest for more efficient computation and removed most of the peripheral structures from consideration during the segmentation process. Subsequently, soft labels for segmentation of the pancreas in the localized region were generated using the U-net model. Finally, the model integrates the morphology prior of the pancreas to update soft labels and perform segmentation. The morphology prior is a single three-dimensional matrix, defined over the general shape and size of the pancreases from multiple CT abdominal images, that helps improve segmentation of the pancreas. Results: The system was trained and tested on the National Institutes of Health dataset (82 CT scans of the healthy pancreas). In fourfold cross-validation, the system produced an average Dice–SØrensen coefficient of 88.53% and outperformed state-of-the-art techniques. Conclusions: Localizing the pancreas assists in reducing segmentation errors and eliminating peripheral structures from consideration. Additionally, the morphology-guided model efficiently improves the overall segmentation of the pancreas.