Deep Distance Transform for Tubular Structure Segmentation in CT Scans

Tubular structure segmentation in medical images, e.g., segmenting vessels in CT scans, serves as a vital step in the use of computers to aid in screening early stages of related diseases. But automatic tubular structure segmentation in CT scans is a challenging problem, due to issues such as poor contrast, noise and complicated background. A tubular structure usually has a cylinder-like shape which can be well represented by its skeleton and cross-sectional radii (scales). Inspired by this, we propose a geometry-aware tubular structure segmentation method, Deep Distance Transform (DDT), which combines intuitions from the classical distance transform for skeletonization and modern deep segmentation networks. DDT first learns a multi-task network to predict a segmentation mask for a tubular structure and a distance map. Each value in the map represents the distance from each tubular structure voxel to the tubular structure surface. Then the segmentation mask is refined by leveraging the shape prior reconstructed from the distance map. We apply our DDT on six medical image datasets. Results show that (1) DDT can boost tubular structure segmentation performance significantly (e.g., over 13% DSC improvement for pancreatic duct segmentation), and (2) DDT additionally provides a geometrical measurement for a tubular structure, which is important for clinical diagnosis (e.g., the cross-sectional scale of a pancreatic duct can be an indicator for pancreatic cancer).

[1]  Tong-Yee Lee,et al.  Skeleton extraction by mesh contraction , 2008, SIGGRAPH 2008.

[2]  Agustín Trujillo-Pino,et al.  Tracking the Aortic Lumen Geometry by Optimizing the 3D Orientation of Its Cross-sections , 2017, MICCAI.

[3]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[4]  Tao Zhao,et al.  Kid-Net: Convolution Networks for Kidney Vessels Segmentation from CT-Volumes , 2018, MICCAI.

[5]  Stephen Lin,et al.  DeepVessel: Retinal Vessel Segmentation via Deep Learning and Conditional Random Field , 2016, MICCAI.

[6]  Vincent Lepetit,et al.  Multiscale Centerline Detection by Learning a Scale-Space Distance Transform , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  A. ROSENFELD,et al.  Distance functions on digital pictures , 1968, Pattern Recognit..

[8]  Wei Shen,et al.  Hi-Fi: Hierarchical Feature Integration for Skeleton Detection , 2018, IJCAI.

[9]  Alan L. Yuille,et al.  A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation , 2017, 2018 International Conference on 3D Vision (3DV).

[10]  Elliot K Fishman,et al.  Diagnosis and Detection of Pancreatic Cancer , 2017, Cancer journal.

[11]  Sven J. Dickinson,et al.  Multiscale Symmetric Part Detection and Grouping , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[12]  J. Broderick,et al.  Heart disease and stroke. , 1993, Heart disease and stroke : a journal for primary care physicians.

[13]  Luc Van Gool,et al.  Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks , 2016, International Journal of Computer Vision.

[14]  Laurent D. Cohen,et al.  Tubular Structure Segmentation Based on Minimal Path Method and Anisotropic Enhancement , 2011, International Journal of Computer Vision.

[15]  Horst Bischof,et al.  Extracting Curve Skeletons from Gray Value Images for Virtual Endoscopy , 2008, MIAR.

[16]  K. Furie,et al.  Heart disease and stroke statistics--2007 update: a report from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee. , 2008, Circulation.

[17]  Horst Bischof,et al.  Segmentation of interwoven 3d tubular tree structures utilizing shape priors and graph cuts , 2010, Medical Image Anal..

[18]  Yaorong Ge,et al.  On the Generation of Skeletons from Discrete Euclidean Distance Maps , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Yan Wang,et al.  Abdominal multi-organ segmentation with organ-attention networks and statistical fusion , 2018, Medical Image Anal..

[20]  Andrea Remuzzi,et al.  Computational Geometry for Patient-Specific Reconstruction and Meshing of Blood Vessels from Angiography , 2003, IEEE Trans. Medical Imaging.

[21]  Anthony J. Yezzi,et al.  Vessel Segmentation Using a Shape Driven Flow , 2004, MICCAI.

[22]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[23]  Peter L. Choyke,et al.  Vessel surface reconstruction with a tubular deformable model , 2001, IEEE Transactions on Medical Imaging.

[24]  Jean-Philippe Domenger,et al.  New methods for the geometrical analysis of tubular organs , 2017, Medical Image Anal..

[25]  Guoying Zhao,et al.  SRN: Side-Output Residual Network for Object Symmetry Detection in the Wild , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Wei Shen,et al.  Training Multi-organ Segmentation Networks with Sample Selection by Relaxed Upper Confident Bound , 2018, MICCAI.

[27]  Ronald M. Summers,et al.  A large annotated medical image dataset for the development and evaluation of segmentation algorithms , 2019, ArXiv.

[28]  Xinlei Chen,et al.  Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[29]  Iasonas Kokkinos,et al.  Learning-Based Symmetry Detection in Natural Images , 2012, ECCV.

[30]  Hao Chen,et al.  Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss , 2018, IJCAI.

[31]  Yan Wang,et al.  Hyper-Pairing Network for Multi-Phase Pancreatic Ductal Adenocarcinoma Segmentation , 2019, MICCAI.

[32]  Sven J. Dickinson,et al.  DeepFlux for Skeletons in the Wild , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Alan L. Yuille,et al.  Multi-Scale Coarse-to-Fine Segmentation for Screening Pancreatic Ductal Adenocarcinoma , 2018, MICCAI.

[34]  Hayit Greenspan,et al.  Endotracheal Tube Detection and Segmentation in Chest Radiographs using Synthetic Data , 2019, MICCAI.

[35]  Qiang Cai,et al.  Clinical significance of main pancreatic duct dilation on computed tomography: single and double duct dilation. , 2007, World journal of gastroenterology.

[36]  Emanuele Trucco,et al.  Scale and Curvature Invariant Ridge Detector for Tortuous and Fragmented Structures , 2015, MICCAI.

[37]  Akshay Pai,et al.  One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation , 2019, MICCAI.

[38]  Zihao Hu,et al.  Multiple instance subspace learning via partial random projection tree for local reflection symmetry in natural images , 2016, Pattern Recognit..

[39]  Alejandro F. Frangi,et al.  Tubular Structure Segmentation Using Spatial Fully Connected Network with Radial Distance Loss for 3D Medical Images , 2019, MICCAI.

[40]  Max A. Viergever,et al.  Fast delineation and visualization of vessels in 3-D angiographic images , 2000, IEEE Transactions on Medical Imaging.

[41]  L. Antiga,et al.  Computational geometry for patient-specific reconstruction and meshing of blood vessels from MR and CT angiography , 2003, IEEE Transactions on Medical Imaging.

[42]  Klaus H. Maier-Hein,et al.  nnU-Net: Breaking the Spell on Successful Medical Image Segmentation , 2019, ArXiv.

[43]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Hans-Peter Seidel,et al.  A data-driven approach for real-time full body pose reconstruction from a depth camera , 2011, 2011 International Conference on Computer Vision.

[45]  Xiang Bai,et al.  DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images , 2016, IEEE Transactions on Image Processing.

[46]  Gabriella Sanniti di Baja,et al.  Ridge points in Euclidean distance maps , 1992, Pattern Recognit. Lett..

[47]  Sven J. Dickinson,et al.  Multiscale symmetric part detection and grouping , 2009, ICCV.

[48]  Sven J. Dickinson,et al.  Detecting Curved Symmetric Parts Using a Deformable Disc Model , 2013, 2013 IEEE International Conference on Computer Vision.

[49]  Yan Wang,et al.  A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans , 2016, MICCAI.

[50]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[51]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[52]  Yuichiro Hayashi,et al.  Hierarchical 3D fully convolutional networks for multi-organ segmentation , 2017, ArXiv.

[53]  David J. Kriegman,et al.  Dense Volume-to-Volume Vascular Boundary Detection , 2016, MICCAI.

[54]  Dong Yang,et al.  3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training , 2018, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).