Segmenting computed tomograms for cardiac ablation using machine learning leveraged by domain knowledge encoding

Frontiers in Cardiovascular Medicine

Cardiovascular Medicine

James Zou¹  Matei Zahari²  Francois Haddad³  Albert J. Rogers³  Sanjiv M. Narayan³  Paul Clopton³  Ruibin Feng³  Brototo Deb³  Tina Baykaner³  Prasanth Ganesan³  Sulaiman Somani³  Samuel Ruipérez-Campillo⁴  Miguel Rodrigo⁵  Fleur V. Y. Tjong⁶ 

[1] Department of Biomedical Data Science, Stanford University, Stanford, CA, United States;Department of Computer Science, Stanford University, Stanford, CA, United States;Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, United States;Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, United States;Bioengineering Department, University of California, Berkeley, Berkeley, CA, United States;Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, United States;CoMMLab, Universitat Politècnica de València, Valencia, Spain;Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, United States;Heart Center, Department of Clinical and Experimental Cardiology, Amsterdam UMC, University of Amsterdam, Amsterdam, Netherlands;

关键词: cardiac CT segmentation;    machine learning;    mathematical modeling;    domain knowledge;    atrial fibrillation;    ablation;   

DOI  :  10.3389/fcvm.2023.1189293

 received in 2023-03-18, accepted in 2023-09-18,  发布年份 2023

来源: Frontiers

【 摘 要 】

BackgroundSegmentation of computed tomography (CT) is important for many clinical procedures including personalized cardiac ablation for the management of cardiac arrhythmias. While segmentation can be automated by machine learning (ML), it is limited by the need for large, labeled training data that may be difficult to obtain. We set out to combine ML of cardiac CT with domain knowledge, which reduces the need for large training datasets by encoding cardiac geometry, which we then tested in independent datasets and in a prospective study of atrial fibrillation (AF) ablation.MethodsWe mathematically represented atrial anatomy with simple geometric shapes and derived a model to parse cardiac structures in a small set of N = 6 digital hearts. The model, termed “virtual dissection,” was used to train ML to segment cardiac CT in N = 20 patients, then tested in independent datasets and in a prospective study.ResultsIn independent test cohorts (N = 160) from 2 Institutions with different CT scanners, atrial structures were accurately segmented with Dice scores of 96.7% in internal (IQR: 95.3%–97.7%) and 93.5% in external (IQR: 91.9%–94.7%) test data, with good agreement with experts (r = 0.99; p < 0.0001). In a prospective study of 42 patients at ablation, this approach reduced segmentation time by 85% (2.3 ± 0.8 vs. 15.0 ± 6.9 min, p < 0.0001), yet provided similar Dice scores to experts (93.9% (IQR: 93.0%–94.6%) vs. 94.4% (IQR: 92.8%–95.7%), p = NS).ConclusionsEncoding cardiac geometry using mathematical models greatly accelerated training of ML to segment CT, reducing the need for large training sets while retaining accuracy in independent test data. Combining ML with domain knowledge may have broad applications.

【 授权许可】

Unknown   
© 2023 Feng, Deb, Ganesan, Tjong, Rogers, Ruipérez-Campillo, Somani, Clopton, Baykaner, Rodrigo, Zou, Haddad, Zahari and Narayan.