Learning Shape Representation on Sparse Point Clouds for Volumetric Image Segmentation

Abstract

Volumetric image segmentation with convolutional neural networks (CNNs) encounters several challenges, which are specific to medical images. Among these challenges are large volumes of interest, high class imbalances, and difficulties in learning shape representations. To tackle these challenges, we propose to improve over traditional CNN-based volumetric image segmentation through point-wise classification of point clouds. The sparsity of point clouds allows processing of entire image volumes, balancing highly imbalanced segmentation problems, and explicitly learning an anatomical shape. We build upon PointCNN, a neural network proposed to process point clouds, and propose here to jointly encode shape and volumetric information within the point cloud in a compact and computationally effective manner. We demonstrate how this approach can then be used to refine CNN-based segmentation, which yields significantly improved results in our experiments on the difficult task of peripheral nerve segmentation from magnetic resonance neurography images. By synthetic experiments, we further show the capability of our approach in learning an explicit anatomical shape representation.

arXiv commentAccepted at MICCAI 2019

References in corpus (5)

• A Survey on Deep Learning in Medical Image Analysis
• Brain Tumor Segmentation with Deep Neural Networks
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation
• Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation

Cited by in corpus (4)

• PC-U Net: Learning to Jointly Reconstruct and Segment the Cardiac Walls in 3D from CT Data
• Deep Learning on Point Clouds for False Positive Reduction at Nodule Detection in Chest CT Scans
• Learning Shape Priors by Pairwise Comparison for Robust Semantic Segmentation
• Large Intestine 3D Shape Refinement Using Point Diffusion Models for Digital Phantom Generation