Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model
Abstract Echocardiographic interpretation during the prenatal or postnatal period is important for diagnosing cardiac septal abnormalities. However, manual interpretation can be time consuming and subject to human error. Automatic segmentation of echocardiogram can support cardiologists in making an...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-09-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-023-05493-9 |
| _version_ | 1797451294185619456 |
|---|---|
| author | Siti Nurmaini Ade Iriani Sapitri Bambang Tutuko Muhammad Naufal Rachmatullah Dian Palupi Rini Annisa Darmawahyuni Firdaus Firdaus Satria Mandala Ria Nova Nuswil Bernolian |
| author_facet | Siti Nurmaini Ade Iriani Sapitri Bambang Tutuko Muhammad Naufal Rachmatullah Dian Palupi Rini Annisa Darmawahyuni Firdaus Firdaus Satria Mandala Ria Nova Nuswil Bernolian |
| author_sort | Siti Nurmaini |
| collection | DOAJ |
| description | Abstract Echocardiographic interpretation during the prenatal or postnatal period is important for diagnosing cardiac septal abnormalities. However, manual interpretation can be time consuming and subject to human error. Automatic segmentation of echocardiogram can support cardiologists in making an initial interpretation. However, such a process does not always provide straightforward information to make a complete interpretation. The segmentation process only identifies the region of cardiac septal abnormality, whereas complete interpretation should determine based on the position of defect. In this study, we proposed a stacked residual-dense network model to segment the entire region of cardiac and classifying their defect positions to generate automatic echocardiographic interpretation. We proposed the generalization model with incorporated two modalities: prenatal and postnatal echocardiography. To further evaluate the effectiveness of our model, its performance was verified by five cardiologists. We develop a pipeline process using 1345 echocardiograms for training data and 181 echocardiograms for unseen data from prospective patients acquired during standard clinical practice at Muhammad Hoesin General Hospital in Indonesia. As a result, the proposed model produced of 58.17% intersection over union (IoU), 75.75% dice similarity coefficient (DSC), and 76.36% mean average precision (mAP) for the validation data. Using unseen data, we achieved 42.39% IoU, 55.72% DSC, and 51.04% mAP. Further, the classification of defect positions using unseen data had approximately 92.27% accuracy, 94.33% specificity, and 92.05% sensitivity. Finally, our proposed model is validated with human expert with varying Kappa value. On average, these results hold promise of increasing suitability in clinical practice as a supporting diagnostic tool for establishing the diagnosis. |
| first_indexed | 2024-03-09T14:52:39Z |
| format | Article |
| id | doaj.art-c59e08a05bf448749260a6caa3b62364 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-03-09T14:52:39Z |
| publishDate | 2023-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-c59e08a05bf448749260a6caa3b623642023-11-26T14:23:20ZengBMCBMC Bioinformatics1471-21052023-09-0124112110.1186/s12859-023-05493-9Automatic echocardiographic anomalies interpretation using a stacked residual-dense network modelSiti Nurmaini0Ade Iriani Sapitri1Bambang Tutuko2Muhammad Naufal Rachmatullah3Dian Palupi Rini4Annisa Darmawahyuni5Firdaus Firdaus6Satria Mandala7Ria Nova8Nuswil Bernolian9Intelligent System Research Group, Faculty of Computer Science, Universitas SriwijayaIntelligent System Research Group, Faculty of Computer Science, Universitas SriwijayaIntelligent System Research Group, Faculty of Computer Science, Universitas SriwijayaIntelligent System Research Group, Faculty of Computer Science, Universitas SriwijayaDepartment of Informatic Engineering, Faculty of Computer Science, Universitas SriwijayaIntelligent System Research Group, Faculty of Computer Science, Universitas SriwijayaIntelligent System Research Group, Faculty of Computer Science, Universitas SriwijayaHuman Centric Engineering, School of Computing, Telkom UniversityDivision of Pediatric Cardiology, Department of Child Health, Mohammad Hoesin General HospitalDivision of Fetomaternal, Department of Obstetrics and Gynaecology, Mohammad Hoesin General HospitalAbstract Echocardiographic interpretation during the prenatal or postnatal period is important for diagnosing cardiac septal abnormalities. However, manual interpretation can be time consuming and subject to human error. Automatic segmentation of echocardiogram can support cardiologists in making an initial interpretation. However, such a process does not always provide straightforward information to make a complete interpretation. The segmentation process only identifies the region of cardiac septal abnormality, whereas complete interpretation should determine based on the position of defect. In this study, we proposed a stacked residual-dense network model to segment the entire region of cardiac and classifying their defect positions to generate automatic echocardiographic interpretation. We proposed the generalization model with incorporated two modalities: prenatal and postnatal echocardiography. To further evaluate the effectiveness of our model, its performance was verified by five cardiologists. We develop a pipeline process using 1345 echocardiograms for training data and 181 echocardiograms for unseen data from prospective patients acquired during standard clinical practice at Muhammad Hoesin General Hospital in Indonesia. As a result, the proposed model produced of 58.17% intersection over union (IoU), 75.75% dice similarity coefficient (DSC), and 76.36% mean average precision (mAP) for the validation data. Using unseen data, we achieved 42.39% IoU, 55.72% DSC, and 51.04% mAP. Further, the classification of defect positions using unseen data had approximately 92.27% accuracy, 94.33% specificity, and 92.05% sensitivity. Finally, our proposed model is validated with human expert with varying Kappa value. On average, these results hold promise of increasing suitability in clinical practice as a supporting diagnostic tool for establishing the diagnosis.https://doi.org/10.1186/s12859-023-05493-9Cardiac septal defectClassificationDeep learningEchocardiographySegmentation |
| spellingShingle | Siti Nurmaini Ade Iriani Sapitri Bambang Tutuko Muhammad Naufal Rachmatullah Dian Palupi Rini Annisa Darmawahyuni Firdaus Firdaus Satria Mandala Ria Nova Nuswil Bernolian Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model BMC Bioinformatics Cardiac septal defect Classification Deep learning Echocardiography Segmentation |
| title | Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model |
| title_full | Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model |
| title_fullStr | Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model |
| title_full_unstemmed | Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model |
| title_short | Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model |
| title_sort | automatic echocardiographic anomalies interpretation using a stacked residual dense network model |
| topic | Cardiac septal defect Classification Deep learning Echocardiography Segmentation |
| url | https://doi.org/10.1186/s12859-023-05493-9 |
| work_keys_str_mv | AT sitinurmaini automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT adeirianisapitri automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT bambangtutuko automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT muhammadnaufalrachmatullah automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT dianpalupirini automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT annisadarmawahyuni automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT firdausfirdaus automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT satriamandala automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT rianova automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel AT nuswilbernolian automaticechocardiographicanomaliesinterpretationusingastackedresidualdensenetworkmodel |