Globally Optimal Surface Segmentation using Deep Learning with Learnable Smoothness Priors

TL;DR

This paper introduces a novel deep learning model that integrates learnable smoothness priors for direct, globally optimal surface segmentation in medical images, eliminating the need for post-processing.

Contribution

It presents the first end-to-end CNN framework that learns smoothness priors for surface segmentation with guaranteed global optimality.

Findings

Effective segmentation of retinal layers in SD-OCT images

Accurate vessel wall segmentation in IVUS images

Promising results demonstrating the method's potential

Abstract

Automated surface segmentation is important and challenging in many medical image analysis applications. Recent deep learning based methods have been developed for various object segmentation tasks. Most of them are a classification based approach, e.g. U-net, which predicts the probability of being target object or background for each voxel. One problem of those methods is lacking of topology guarantee for segmented objects, and usually post processing is needed to infer the boundary surface of the object. In this paper, a novel model based on convolutional neural network (CNN) followed by a learnable surface smoothing block is proposed to tackle the surface segmentation problem with end-to-end training. To the best of our knowledge, this is the first study to learn smoothness priors end-to-end with CNN for direct surface segmentation with global optimality. Experiments carried out on Spectral Domain Optical Coherence Tomography (SD-OCT) retinal layer segmentation and Intravascular Ultrasound (IVUS) vessel wall segmentation demonstrated very promising results.