Dataset Information

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

ABSTRACT:

Background

Segmentation 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.

Methods

We 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.

Results

In 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).

Conclusions

Encoding 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.

SUBMITTER: Feng R

PROVIDER: S-EPMC10577270 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Feng Ruibin R Deb Brototo B Ganesan Prasanth P Tjong Fleur V Y FVY Rogers Albert J AJ Ruipérez-Campillo Samuel S Somani Sulaiman S Clopton Paul P Baykaner Tina T Rodrigo Miguel M Zou James J Haddad Francois F Zahari Matei M Narayan Sanjiv M SM

Frontiers in cardiovascular medicine 20231002

<h4>Background</h4>Segmentation 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 test ...[more]

PMID: 37849936

Similar Datasets

Project description:IntroductionCardiac amyloidosis (CA) shares similar clinical and imaging characteristics (e.g., hypertrophic phenotype) with aortic stenosis (AS), but its prognosis is generally worse than severe AS alone. Recent studies suggest that the presence of CA is frequent (1 out of 8 patients) in patients with severe AS. The coexistence of the two diseases complicates the prognosis and therapeutic management of both conditions. Thus, there is an urgent need to standardize and optimize the diagnostic process of CA and AS. The aim of this study is to develop a robust and reliable radiomics-based pipeline to differentiate the two pathologies.MethodsThirty patients were included in the study, equally divided between CA and AS. For each patient, a cardiac computed tomography (CCT) was analyzed by extracting 107 radiomics features from the LV wall. Feature robustness was evaluated by means of geometrical transformations to the ROIs and intra-class correlation coefficient (ICC) computation. Various correlation thresholds (0.80, 0.85, 0.90, 0.95, 1), feature selection methods [p-value, least absolute shrinkage and selection operator (LASSO), semi-supervised LASSO, principal component analysis (PCA), semi-supervised PCA, sequential forwards selection] and machine learning classifiers (k-nearest neighbors, support vector machine, decision tree, logistic regression and gradient boosting) were assessed using a leave-one-out cross-validation. Data augmentation was performed using the synthetic minority oversampling technique. Finally, explainability analysis was performed by using the SHapley Additive exPlanations (SHAP) method.ResultsNinety-two radiomic features were selected as robust and used in the further steps. Best performances of classification were obtained using a correlation threshold of 0.95, PCA (keeping 95% of the variance, corresponding to 9 PCs) and support vector machine classifier reaching an accuracy, sensitivity and specificity of 0.93. Four PCs were found to be mainly dependent on textural features, two on first-order statistics and three on shape and size features.ConclusionThese preliminary results show that radiomics might be used as non-invasive tool able to differentiate CA from AS using clinical routine available images.

Project description:Metabolomic data often present challenges due to high dimensionality, collinearity, and variability in metabolite concentrations. Machine learning (ML) application in metabolomic analyses is enabling the extraction of meaningful information from complex data. Bringing together domain-specific knowledge from metabolomics with explainable ML methods can refine the predictive performance and interpretability of models used in atherosclerosis research. In this work, we aimed to identify the most impactful metabolites associated with the presence of atherosclerotic cardiovascular disease (ASCVD) in cross-sectional case-control studies using explainable ML methods integrated with metabolomics domain knowledge. For this, a subset from the FLEMENGHO cohort with metabolomic data available was used as the training cohort, including 63 patients with a history of ASCVD and 52 non-smoking controls matched by age, sex, and body mass index from the same population. First, Partial Least Squares Discriminant Analysis (PLS-DA) was applied for dimensionality reduction. The selected metabolites' correlations were analyzed by considering their chemical categorization. Then, eXtreme Gradient Boosting (XGBoost) was used to identify metabolites that characterize ASCVD. Next, the selected metabolites were evaluated in an external cohort to determine their effectiveness in distinguishing between cases and controls. A total of 56 metabolites were selected for ASCVD discrimination using PLS-DA. The primary identified metabolites' superclasses included lipids, organic acids, and organic oxygen compounds. Upon integrating these metabolites with the XGBoost model, the classification yielded a test area under the curve (AUC) of 0.75. SHAP analyses ranked cholesterol, 3-methylhistidine, and glucuronic acid among the most impactful features and showed the diversity of metabolites considered for building the ASCVD discriminator. Also using XGBoost, the selected metabolites achieved an AUC of 0.93 in an independent external validation cohort. In conclusion, the combination of different metabolites has the potential to build classifiers for ASCVD. Integrating metabolite categorization within the SHAP analysis further enhanced the interpretability of the model, offering insights into metabolite-specific contributions to ASCVD risk.

Project description:BackgroundThere is an increasing evidence that pulmonary vein (PV) enlargement is associated with atrial fibrillation (AF); however, the predictive value of PV enlargement in AF recurrence remains unclear. This study sought to evaluate whether PV volume quantification derived from cardiac computed tomographic angiography (CCTA) could serve as a predictive indicator of the success of the catheter ablation (CA) procedure.MethodsThe data of 160 patients diagnosed with AF who underwent both CCTA and CA treatments from January to June 2020 were retrospectively examined; the CCTA was conducted before the CA surgery. The study focused on documenting the PV structure, and the volume of the PV and left atrium (LA). The clinical, CCTA, and echocardiographic predictors of the recurrence and no-recurrence groups were compared. A multivariable logistic regression analysis was performed to adjust for confounders. Receiver operating characteristic (ROC) curves were analyzed to assess the predictive performance of the predictors of AF recurrence.ResultsOf the 160 patients [55.6% male, 62.00 (55.25-68.00) years, 23.1% with persistent AF], 45 (28.1%) experienced AF recurrence within a one-year period. Notably, patients with AF recurrence had elevated CHADS2 scores (P=0.020) and increased LA and PV volumes (P<0.05). Patients with persistent AF (n=37) had significantly larger LA volume indexes (P<0.001) than those with paroxysmal AF, but there was no difference between the two groups in terms of the PV maximum volume index (P=0.200). Moreover, the PV maximum volume index [odds ratio (OR): 1.244, 95% confidence interval (CI): 1.008-1.536, P=0.042] and the LA minimum volume index (OR: 1.026, 95% CI: 1.001-1.052, P=0.038) were found to be significant predictors of AF recurrence. The ROC curves revealed that the PV maximum volume index threshold for predicting AF recurrence was 7.13 mL/m2, with a sensitivity of 84.4% and a specificity of 34.8% [area under the curve (AUC): 0.635, 95% CI: 0.540-0.730, P=0.008], and the LA minimum volume index threshold for predicting AF recurrence was 46.16 mL/m2, with a sensitivity of 88.9% and a specificity of 31.3% (AUC: 0.629, 95% CI: 0.534-0.723, P=0.012). A sub-analysis of patients with a lower left atrial dimension (LAD ≤38 mm in females, LAD ≤40 mm in males, n=120) demonstrated that the PV maximum volume index was a noteworthy indicator of AF recurrence (OR: 1.443: 95% CI: 1.145-1.820, P=0.002). Conversely, no significant correlation between AF recurrence and the LA volume index was found. The AUC value for the PV maximum volume index predictive of recurrent AF was 0.680 (95% CI: 0.577-0.781, P=0.003), with a sensitivity of 75.8%, specificity of 54%, and the cut-off value of the maximum AUC was 7.89 mL/m2.ConclusionsPV volume, derived from CCTA, may help to predict the recurrence of AF after CA, and is superior to the LA size in patients with less pronounced LA enlargement.

Project description:BackgroundProstate cancer is one of the most common cancers worldwide. Currently, convolution neural networks (CNNs) are achieving remarkable success in various computer vision tasks, and in medical imaging research. Various CNN architectures and methodologies have been applied in the field of prostate cancer diagnosis. In this work, we evaluate the impact of the adaptation of a state-of-the-art CNN architecture on domain knowledge related to problems in the diagnosis of prostate cancer. The architecture of the final CNN model was optimised on the basis of the Prostate Imaging Reporting and Data System (PI-RADS) standard, which is currently the best available indicator in the acquisition, interpretation, and reporting of prostate multi-parametric magnetic resonance imaging (mpMRI) examinations.MethodsA dataset containing 330 suspicious findings identified using mpMRI was used. Two CNN models were subjected to comparative analysis. Both implement the concept of decision-level fusion for mpMRI data, providing a separate network for each multi-parametric series. The first model implements a simple fusion of multi-parametric features to formulate the final decision. The architecture of the second model reflects the diagnostic pathway of PI-RADS methodology, using information about a lesion's primary anatomic location within the prostate gland. Both networks were experimentally tuned to successfully classify prostate cancer changes.ResultsThe optimised knowledge-encoded model achieved slightly better classification results compared with the traditional model architecture (AUC = 0.84 vs. AUC = 0.82). We found the proposed model to achieve convergence significantly faster.ConclusionsThe final knowledge-encoded CNN model provided more stable learning performance and faster convergence to optimal diagnostic accuracy. The results fail to demonstrate that PI-RADS-based modelling of CNN architecture can significantly improve performance of prostate cancer recognition using mpMRI.

Dataset Information

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

Background

Methods

Results

Conclusions

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets