Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data
Automatic boundary detection of 4D ultrasound (4DUS) cardiac data is a promising yet challenging application at the intersection of machine learning and medicine. Using recently developed murine 4DUS cardiac imaging data, we demonstrate here a set of three machine learning models that predict left v...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/4/1690 |
| _version_ | 1797396636318564352 |
|---|---|
| author | Frederick W. Damen David T. Newton Guang Lin Craig J. Goergen |
| author_facet | Frederick W. Damen David T. Newton Guang Lin Craig J. Goergen |
| author_sort | Frederick W. Damen |
| collection | DOAJ |
| description | Automatic boundary detection of 4D ultrasound (4DUS) cardiac data is a promising yet challenging application at the intersection of machine learning and medicine. Using recently developed murine 4DUS cardiac imaging data, we demonstrate here a set of three machine learning models that predict left ventricular wall kinematics along both the endo- and epi-cardial boundaries. Each model is fundamentally built on three key features: (1) the projection of raw US data to a lower dimensional subspace, (2) a smoothing spline basis across time, and (3) a strategic parameterization of the left ventricular boundaries. Model 1 is constructed such that boundary predictions are based on individual short-axis images, regardless of their relative position in the ventricle. Model 2 simultaneously incorporates parallel short-axis image data into their predictions. Model 3 builds on the multi-slice approach of model 2, but assists predictions with a single ground-truth position at end-diastole. To assess the performance of each model, Monte Carlo cross validation was used to assess the performance of each model on unseen data. For predicting the radial distance of the endocardium, models 1, 2, and 3 yielded average R<sup>2</sup> values of 0.41, 0.49, and 0.71, respectively. Monte Carlo simulations of the endocardial wall showed significantly closer predictions when using model 2 versus model 1 at a rate of 48.67%, and using model 3 versus model 2 at a rate of 83.50%. These finding suggest that a machine learning approach where multi-slice data are simultaneously used as input and predictions are aided by a single user input yields the most robust performance. Subsequently, we explore the how metrics of cardiac kinematics compare between ground-truth contours and predicted boundaries. We observed negligible deviations from ground-truth when using predicted boundaries alone, except in the case of early diastolic strain rate, providing confidence for the use of such machine learning models for rapid and reliable assessments of murine cardiac function. To our knowledge, this is the first application of machine learning to murine left ventricular 4DUS data. Future work will be needed to strengthen both model performance and applicability to different cardiac disease models. |
| first_indexed | 2024-03-09T00:54:15Z |
| format | Article |
| id | doaj.art-292a7a1a48434f1dbfdf3947d143174e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T00:54:15Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-292a7a1a48434f1dbfdf3947d143174e2023-12-11T17:00:19ZengMDPI AGApplied Sciences2076-34172021-02-01114169010.3390/app11041690Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound DataFrederick W. Damen0David T. Newton1Guang Lin2Craig J. Goergen3Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN 47907, USADepartment of Statistics, Purdue University, West Lafayette, IN 47907, USADepartment of Mathematics & School of Mechanical Engineering, Purdue University, West Lafayette, IN 47907, USAWeldon School of Biomedical Engineering, Purdue University, West Lafayette, IN 47907, USAAutomatic boundary detection of 4D ultrasound (4DUS) cardiac data is a promising yet challenging application at the intersection of machine learning and medicine. Using recently developed murine 4DUS cardiac imaging data, we demonstrate here a set of three machine learning models that predict left ventricular wall kinematics along both the endo- and epi-cardial boundaries. Each model is fundamentally built on three key features: (1) the projection of raw US data to a lower dimensional subspace, (2) a smoothing spline basis across time, and (3) a strategic parameterization of the left ventricular boundaries. Model 1 is constructed such that boundary predictions are based on individual short-axis images, regardless of their relative position in the ventricle. Model 2 simultaneously incorporates parallel short-axis image data into their predictions. Model 3 builds on the multi-slice approach of model 2, but assists predictions with a single ground-truth position at end-diastole. To assess the performance of each model, Monte Carlo cross validation was used to assess the performance of each model on unseen data. For predicting the radial distance of the endocardium, models 1, 2, and 3 yielded average R<sup>2</sup> values of 0.41, 0.49, and 0.71, respectively. Monte Carlo simulations of the endocardial wall showed significantly closer predictions when using model 2 versus model 1 at a rate of 48.67%, and using model 3 versus model 2 at a rate of 83.50%. These finding suggest that a machine learning approach where multi-slice data are simultaneously used as input and predictions are aided by a single user input yields the most robust performance. Subsequently, we explore the how metrics of cardiac kinematics compare between ground-truth contours and predicted boundaries. We observed negligible deviations from ground-truth when using predicted boundaries alone, except in the case of early diastolic strain rate, providing confidence for the use of such machine learning models for rapid and reliable assessments of murine cardiac function. To our knowledge, this is the first application of machine learning to murine left ventricular 4DUS data. Future work will be needed to strengthen both model performance and applicability to different cardiac disease models.https://www.mdpi.com/2076-3417/11/4/1690echocardiography4D ultrasoundvolumetric imagingmurineleft ventriclemyocardium |
| spellingShingle | Frederick W. Damen David T. Newton Guang Lin Craig J. Goergen Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data Applied Sciences echocardiography 4D ultrasound volumetric imaging murine left ventricle myocardium |
| title | Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data |
| title_full | Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data |
| title_fullStr | Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data |
| title_full_unstemmed | Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data |
| title_short | Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data |
| title_sort | machine learning driven contouring of high frequency four dimensional cardiac ultrasound data |
| topic | echocardiography 4D ultrasound volumetric imaging murine left ventricle myocardium |
| url | https://www.mdpi.com/2076-3417/11/4/1690 |
| work_keys_str_mv | AT frederickwdamen machinelearningdrivencontouringofhighfrequencyfourdimensionalcardiacultrasounddata AT davidtnewton machinelearningdrivencontouringofhighfrequencyfourdimensionalcardiacultrasounddata AT guanglin machinelearningdrivencontouringofhighfrequencyfourdimensionalcardiacultrasounddata AT craigjgoergen machinelearningdrivencontouringofhighfrequencyfourdimensionalcardiacultrasounddata |