Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics

Automatic pancreas segmentation in radiology images, e.g., computed tomography (CT), and magnetic resonance imaging (MRI), is frequently required by computer-aided screening, diagnosis, and quantitative assessment. Yet, pancreas is a challenging abdominal organ to segment due to the high inter-patient anatomical variability in both shape and volume metrics. Recently, convolutional neural networks (CNN) have demonstrated promising performance on accurate segmentation of pancreas. However, the CNN-based method often suffers from segmentation discontinuity for reasons such as noisy image quality and blurry pancreatic boundary. In this chapter, we first discuss the CNN configurations and training objectives that lead to the state-of-the-art performance on pancreas segmentation. We then present a recurrent neural network (RNN) to address the problem of segmentation spatial inconsistency across adjacent image slices. The RNN takes outputs of the CNN and refines the segmentation by improving the shape smoothness. J. Cai · L. Yang (B) J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA e-mail: lin.yang@bme.ufl.edu J. Cai e-mail: jimmycai@ufl.edu L. Lu PAII Inc., Bethesda Research Lab, 6720B Rockledge Drive Ste 410, Bethesda, MD 20817, USA e-mail: le.lu@paii-labs.com; lelu@cs.jhu.edu Johns Hopkins University, Baltimore, MD, USA F. Xing Department of Biostatistics and Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO, USA e-mail: fuyong.xing@ucdenver.edu © Springer Nature Switzerland AG 2019 L. Lu et al. (eds.), Deep Learning and Convolutional Neural Networks for Medical Imaging andClinical Informatics, Advances inComputerVision and PatternRecognition, https://doi.org/10.1007/978-3-030-13969-8_1 3