1
|
Kim Y, Wang K, Lock RI, Nash TR, Fleischer S, Wang BZ, Fine BM, Vunjak-Novakovic G. BeatProfiler: Multimodal In Vitro Analysis of Cardiac Function Enables Machine Learning Classification of Diseases and Drugs. IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY 2024; 5:238-249. [PMID: 38606403 PMCID: PMC11008807 DOI: 10.1109/ojemb.2024.3377461] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2023] [Revised: 02/13/2024] [Accepted: 03/10/2024] [Indexed: 04/13/2024] Open
Abstract
Goal: Contractile response and calcium handling are central to understanding cardiac function and physiology, yet existing methods of analysis to quantify these metrics are often time-consuming, prone to mistakes, or require specialized equipment/license. We developed BeatProfiler, a suite of cardiac analysis tools designed to quantify contractile function, calcium handling, and force generation for multiple in vitro cardiac models and apply downstream machine learning methods for deep phenotyping and classification. Methods: We first validate BeatProfiler's accuracy, robustness, and speed by benchmarking against existing tools with a fixed dataset. We further confirm its ability to robustly characterize disease and dose-dependent drug response. We then demonstrate that the data acquired by our automatic acquisition pipeline can be further harnessed for machine learning (ML) analysis to phenotype a disease model of restrictive cardiomyopathy and profile cardioactive drug functional response. To accurately classify between these biological signals, we apply feature-based ML and deep learning models (temporal convolutional-bidirectional long short-term memory model or TCN-BiLSTM). Results: Benchmarking against existing tools revealed that BeatProfiler detected and analyzed contraction and calcium signals better than existing tools through improved sensitivity in low signal data, reduction in false positives, and analysis speed increase by 7 to 50-fold. Of signals accurately detected by published methods (PMs), BeatProfiler's extracted features showed high correlations to PMs, confirming that it is reliable and consistent with PMs. The features extracted by BeatProfiler classified restrictive cardiomyopathy cardiomyocytes from isogenic healthy controls with 98% accuracy and identified relax90 as a top distinguishing feature in congruence with previous findings. We also show that our TCN-BiLSTM model was able to classify drug-free control and 4 cardiac drugs with different mechanisms of action at 96% accuracy. We further apply Grad-CAM on our convolution-based models to identify signature regions of perturbations by these drugs in calcium signals. Conclusions: We anticipate that the capabilities of BeatProfiler will help advance in vitro studies in cardiac biology through rapid phenotyping, revealing mechanisms underlying cardiac health and disease, and enabling objective classification of cardiac disease and responses to drugs.
Collapse
Affiliation(s)
- Youngbin Kim
- Department of Biomedical EngineeringColumbia UniversityNew YorkNY10032USA
| | - Kunlun Wang
- Department of Biomedical EngineeringColumbia UniversityNew YorkNY10032USA
| | - Roberta I. Lock
- Department of Biomedical EngineeringColumbia UniversityNew YorkNY10032USA
| | - Trevor R. Nash
- Department of Biomedical EngineeringColumbia UniversityNew YorkNY10032USA
| | - Sharon Fleischer
- Department of Biomedical EngineeringColumbia UniversityNew YorkNY10032USA
| | - Bryan Z. Wang
- Department of Biomedical EngineeringColumbia UniversityNew YorkNY10032USA
| | - Barry M. Fine
- Department of MedicineDivision of CardiologyColumbia University Medical CenterNew YorkNY10032USA
| | - Gordana Vunjak-Novakovic
- Department of Biomedical EngineeringColumbia UniversityNew YorkNY10032USA
- Department of MedicineDivision of CardiologyColumbia University Medical CenterNew YorkNY10032USA
| |
Collapse
|
2
|
Burattini M, Lo Muzio FP, Hu M, Bonalumi F, Rossi S, Pagiatakis C, Salvarani N, Fassina L, Luciani GB, Miragoli M. Unlocking cardiac motion: assessing software and machine learning for single-cell and cardioid kinematic insights. Sci Rep 2024; 14:1782. [PMID: 38245558 PMCID: PMC10799933 DOI: 10.1038/s41598-024-52081-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Accepted: 01/12/2024] [Indexed: 01/22/2024] Open
Abstract
The heart coordinates its functional parameters for optimal beat-to-beat mechanical activity. Reliable detection and quantification of these parameters still represent a hot topic in cardiovascular research. Nowadays, computer vision allows the development of open-source algorithms to measure cellular kinematics. However, the analysis software can vary based on analyzed specimens. In this study, we compared different software performances in in-silico model, in-vitro mouse adult ventricular cardiomyocytes and cardioids. We acquired in-vitro high-resolution videos during suprathreshold stimulation at 0.5-1-2 Hz, adapting the protocol for the cardioids. Moreover, we exposed the samples to inotropic and depolarizing substances. We analyzed in-silico and in-vitro videos by (i) MUSCLEMOTION, the gold standard among open-source software; (ii) CONTRACTIONWAVE, a recently developed tracking software; and (iii) ViKiE, an in-house customized video kinematic evaluation software. We enriched the study with three machine-learning algorithms to test the robustness of the motion-tracking approaches. Our results revealed that all software produced comparable estimations of cardiac mechanical parameters. For instance, in cardioids, beat duration measurements at 0.5 Hz were 1053.58 ms (MUSCLEMOTION), 1043.59 ms (CONTRACTIONWAVE), and 937.11 ms (ViKiE). ViKiE exhibited higher sensitivity in exposed samples due to its localized kinematic analysis, while MUSCLEMOTION and CONTRACTIONWAVE offered temporal correlation, combining global assessment with time-efficient analysis. Finally, machine learning reveals greater accuracy when trained with MUSCLEMOTION dataset in comparison with the other software (accuracy > 83%). In conclusion, our findings provide valuable insights for the accurate selection and integration of software tools into the kinematic analysis pipeline, tailored to the experimental protocol.
Collapse
Affiliation(s)
- Margherita Burattini
- Department of Surgery, Dentistry and Maternity, University of Verona, Verona, Italy
- Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Francesco Paolo Lo Muzio
- Department of Medicine and Surgery, University of Parma, Parma, Italy
- Deutsches Herzzentrum Der Charité, Department of Cardiology, Angiology and Intensive Care Medicine, Berlin, Germany
| | - Mirko Hu
- Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Flavia Bonalumi
- Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Stefano Rossi
- Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Christina Pagiatakis
- Humanitas Research Hospital, IRCCS, Rozzano (Milan), Italy
- Department of Biotechnology and Life Sciences, University of Insubria, Varese, Italy
| | - Nicolò Salvarani
- Humanitas Research Hospital, IRCCS, Rozzano (Milan), Italy
- Institute of Genetic and Biomedical Research (IRGB), UOS of Milan, National Research Council of Italy, Milan, Italy
| | - Lorenzo Fassina
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| | | | - Michele Miragoli
- Department of Medicine and Surgery, University of Parma, Parma, Italy.
- Humanitas Research Hospital, IRCCS, Rozzano (Milan), Italy.
| |
Collapse
|