Deep Small Bowel Segmentation with Cylindrical Topological Constraints

by   Seung Yeon Shin, et al.

We present a novel method for small bowel segmentation where a cylindrical topological constraint based on persistent homology is applied. To address the touching issue which could break the applied constraint, we propose to augment a network with an additional branch to predict an inner cylinder of the small bowel. Since the inner cylinder is free of the touching issue, a cylindrical shape constraint applied on this augmented branch guides the network to generate a topologically correct segmentation. For strict evaluation, we achieved an abdominal computed tomography dataset with dense segmentation ground-truths. The proposed method showed clear improvements in terms of four different metrics compared to the baseline method, and also showed the statistical significance from a paired t-test.



page 2

page 7

page 8


Explicit topological priors for deep-learning based image segmentation using persistent homology

We present a novel method to explicitly incorporate topological prior kn...

Image Segmentation with Topological Priors

Solving segmentation tasks with topological priors proved to make fewer ...

Segmentation of the cortical plate in fetal brain MRI with a topological loss

The fetal cortical plate undergoes drastic morphological changes through...

Detection and Visualization of Endoleaks in CT Data for Monitoring of Thoracic and Abdominal Aortic Aneurysm Stents

In this paper we present an efficient algorithm for the segmentation of ...

Topological Regularization for Dense Prediction

Dense prediction tasks such as depth perception and semantic segmentatio...

A Graph-theoretic Algorithm for Small Bowel Path Tracking in CT Scans

We present a novel graph-theoretic method for small bowel path tracking....

Estimation of Elastic Behavior of Cast Metal Components Containing Process Induced Porosity

Significant progress has been made for assessing the influence of porosi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.