Neural Network Vessel Lumen Regression for Automated Lumen Cross-Section Segmentation in Cardiovascular Image-Based Mode
- PDF / 4,176,409 Bytes
- 15 Pages / 593.972 x 792 pts Page_size
- 36 Downloads / 214 Views
Cardiovascular Engineering and Technology (Ó 2020) https://doi.org/10.1007/s13239-020-00497-5
Original Article
Neural Network Vessel Lumen Regression for Automated Lumen Cross-Section Segmentation in Cardiovascular Image-Based Modeling GABRIEL MAHER,1 DAVID PARKER,2 NATHAN WILSON,3 and ALISON MARSDEN
4
1
Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA, USA; 2Research Computing, Stanford University, Stanford, CA, USA; 3Open Source Medical Software Corporation, Los Angeles, CA, USA; and 4Pediatric Cardiology, Bioengineering, Stanford University, Stanford, CA, USA (Received 26 June 2020; accepted 15 October 2020) Associate Editor Wei Sun oversaw the review of this article.
Abstract Purpose—We accelerate a pathline-based cardiovascular model building method by training machine learning models to directly predict vessel lumen surface points from computed tomography (CT) and magnetic resonance (MR) medical image data. Methods—We formulate vessel lumen detection as a regression task using a polar coordiantes representation. Results—Neural networks trained with our regression formulation allow predictions to be made with significantly higher accuracy than existing methods that identify the vessel lumen through binary pixel classification. The regression formulation enables machine learning models to be trained end-to-end for vessel lumen detection without post-processing steps that reduce accuracy. Conclusion—By employing our models in a pathline-based cardiovascular model building pipeline we substantially reduce the manual segmentation effort required to build accurate cardiovascular models, and reduce the overall time required to perform patient-specific cardiovascular simulations. While our method is applied here for cardiovascular model building it is generally applicable to segmentation of tree-like and tubular structures from image data. Keywords—Cardiovascular modeling, Convolutional neural networks, SimVascular, Patient-specific modeling, Cardiovascular simulation.
INTRODUCTION The increasing worldwide prevalence of cardiovascular disease (CVD)13 has spurred the development of new computational cardiovascular modeling and sim-
Address correspondence to Alison Marsden, Pediatric Cardiology, Bioengineering, Stanford University, Stanford, CA, USA. Electronic mail: [email protected]
ulation technologies6. Image-based patient-specific hemodynamic simulation methods, in particular, are used in personalized medicine and surgical planning for a range of disease applications28,42. However, the typically manual segmentation effort required to construct accurate 3D digital anatomical cardiovascular models for patient-specific hemodynamic simulations is currently a labor intensive and time consuming process.36,42 Lengthy workflows are incompatible with realistic clinical settings where limited time is available to produce simulation results. Furthermore, to validate the efficacy of simulation tools, studies and trials involving large patient cohorts are required to statistically
Data Loading...
