Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients
Scar quantification on cardiovascular magnetic resonance (CMR) late gadolinium enhancement (LGE) images is important in risk stratifying patients with hypertrophic cardiomyopathy (HCM) due to the importance of scar burden in predicting clinical outcomes. We aimed to develop a machine learning (ML) m...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLOS Digital Health |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931226/?tool=EBI |
| _version_ | 1797698484412874752 |
|---|---|
| author | Zeinab Navidi Jesse Sun Raymond H. Chan Kate Hanneman Amna Al-Arnawoot Alif Munim Harry Rakowski Martin S. Maron Anna Woo Bo Wang Wendy Tsang |
| author_facet | Zeinab Navidi Jesse Sun Raymond H. Chan Kate Hanneman Amna Al-Arnawoot Alif Munim Harry Rakowski Martin S. Maron Anna Woo Bo Wang Wendy Tsang |
| author_sort | Zeinab Navidi |
| collection | DOAJ |
| description | Scar quantification on cardiovascular magnetic resonance (CMR) late gadolinium enhancement (LGE) images is important in risk stratifying patients with hypertrophic cardiomyopathy (HCM) due to the importance of scar burden in predicting clinical outcomes. We aimed to develop a machine learning (ML) model that contours left ventricular (LV) endo- and epicardial borders and quantifies CMR LGE images from HCM patients.We retrospectively studied 2557 unprocessed images from 307 HCM patients followed at the University Health Network (Canada) and Tufts Medical Center (USA). LGE images were manually segmented by two experts using two different software packages. Using 6SD LGE intensity cutoff as the gold standard, a 2-dimensional convolutional neural network (CNN) was trained on 80% and tested on the remaining 20% of the data. Model performance was evaluated using the Dice Similarity Coefficient (DSC), Bland-Altman, and Pearson’s correlation. The 6SD model DSC scores were good to excellent at 0.91 ± 0.04, 0.83 ± 0.03, and 0.64 ± 0.09 for the LV endocardium, epicardium, and scar segmentation, respectively. The bias and limits of agreement for the percentage of LGE to LV mass were low (-0.53 ± 2.71%), and correlation high (r = 0.92). This fully automated interpretable ML algorithm allows rapid and accurate scar quantification from CMR LGE images. This program does not require manual image pre-processing, and was trained with multiple experts and software, increasing its generalizability. Author summary Accurate scar quantification of cardiac magnetic resonance (CMR) late gadolinium enhancement (LGE) images is important in managing hypertrophic cardiomyopathy (HCM) patients. We developed a 2D convolutional neural network to quantify CMR LGE in HCM patients that is computationally interpretable and trained using multicenter data analyzed by 2 expert readers using 2 different analysis packages. Our model demonstrated low bias and limits of agreement and high correlation with expert analysis. Benchmarking comparison was performed between our algorithm and standard U-Net model with and without cropped raw images. Our method showed superior performance and has high potential for clinical adaptability. |
| first_indexed | 2024-03-12T03:54:47Z |
| format | Article |
| id | doaj.art-7bdeae2d472f4e7484de1f803c5d25a7 |
| institution | Directory Open Access Journal |
| issn | 2767-3170 |
| language | English |
| last_indexed | 2024-03-12T03:54:47Z |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Digital Health |
| spelling | doaj.art-7bdeae2d472f4e7484de1f803c5d25a72023-09-03T12:02:34ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702023-01-0121Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patientsZeinab NavidiJesse SunRaymond H. ChanKate HannemanAmna Al-ArnawootAlif MunimHarry RakowskiMartin S. MaronAnna WooBo WangWendy TsangScar quantification on cardiovascular magnetic resonance (CMR) late gadolinium enhancement (LGE) images is important in risk stratifying patients with hypertrophic cardiomyopathy (HCM) due to the importance of scar burden in predicting clinical outcomes. We aimed to develop a machine learning (ML) model that contours left ventricular (LV) endo- and epicardial borders and quantifies CMR LGE images from HCM patients.We retrospectively studied 2557 unprocessed images from 307 HCM patients followed at the University Health Network (Canada) and Tufts Medical Center (USA). LGE images were manually segmented by two experts using two different software packages. Using 6SD LGE intensity cutoff as the gold standard, a 2-dimensional convolutional neural network (CNN) was trained on 80% and tested on the remaining 20% of the data. Model performance was evaluated using the Dice Similarity Coefficient (DSC), Bland-Altman, and Pearson’s correlation. The 6SD model DSC scores were good to excellent at 0.91 ± 0.04, 0.83 ± 0.03, and 0.64 ± 0.09 for the LV endocardium, epicardium, and scar segmentation, respectively. The bias and limits of agreement for the percentage of LGE to LV mass were low (-0.53 ± 2.71%), and correlation high (r = 0.92). This fully automated interpretable ML algorithm allows rapid and accurate scar quantification from CMR LGE images. This program does not require manual image pre-processing, and was trained with multiple experts and software, increasing its generalizability. Author summary Accurate scar quantification of cardiac magnetic resonance (CMR) late gadolinium enhancement (LGE) images is important in managing hypertrophic cardiomyopathy (HCM) patients. We developed a 2D convolutional neural network to quantify CMR LGE in HCM patients that is computationally interpretable and trained using multicenter data analyzed by 2 expert readers using 2 different analysis packages. Our model demonstrated low bias and limits of agreement and high correlation with expert analysis. Benchmarking comparison was performed between our algorithm and standard U-Net model with and without cropped raw images. Our method showed superior performance and has high potential for clinical adaptability.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931226/?tool=EBI |
| spellingShingle | Zeinab Navidi Jesse Sun Raymond H. Chan Kate Hanneman Amna Al-Arnawoot Alif Munim Harry Rakowski Martin S. Maron Anna Woo Bo Wang Wendy Tsang Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients PLOS Digital Health |
| title | Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients |
| title_full | Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients |
| title_fullStr | Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients |
| title_full_unstemmed | Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients |
| title_short | Interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients |
| title_sort | interpretable machine learning for automated left ventricular scar quantification in hypertrophic cardiomyopathy patients |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9931226/?tool=EBI |
| work_keys_str_mv | AT zeinabnavidi interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT jessesun interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT raymondhchan interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT katehanneman interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT amnaalarnawoot interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT alifmunim interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT harryrakowski interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT martinsmaron interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT annawoo interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT bowang interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients AT wendytsang interpretablemachinelearningforautomatedleftventricularscarquantificationinhypertrophiccardiomyopathypatients |