FetalNet: Low-light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect prediction
Background: Fetal heart defect (FHD) examination by ultrasound (US) is challenging because it involves low light, contrast, and brightness. Inadequate US images of fetal echocardiography play an important role in the failure to detect FHDs manually. The automatic interpretation of fetal echocardiogr...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914822002738 |
| _version_ | 1797987272533999616 |
|---|---|
| author | Sutarno Sutarno Siti Nurmaini Radiyati Umi Partan Ade Iriani Sapitri Bambang Tutuko Muhammad Naufal Rachmatullah Annisa Darmawahyuni Firdaus Firdaus Nuswil Bernolian Deny Sulistiyo |
| author_facet | Sutarno Sutarno Siti Nurmaini Radiyati Umi Partan Ade Iriani Sapitri Bambang Tutuko Muhammad Naufal Rachmatullah Annisa Darmawahyuni Firdaus Firdaus Nuswil Bernolian Deny Sulistiyo |
| author_sort | Sutarno Sutarno |
| collection | DOAJ |
| description | Background: Fetal heart defect (FHD) examination by ultrasound (US) is challenging because it involves low light, contrast, and brightness. Inadequate US images of fetal echocardiography play an important role in the failure to detect FHDs manually. The automatic interpretation of fetal echocardiography was proposed in a previous study. However, the low quality of US images reduces the prediction rate of computer-assisted diagnosis results. Methods: To increase the FHD prediction rate, we propose low-light fetal echocardiography enhancement stacking with a dense convolutional network classifier named “FetalNet.” Our proposed FetalNet model was developed using 460 US images to produce an image enhancement model. The results showed that all raw US images could be improved with satisfactory performance in terms of increasing the peak signal-to-noise ratio of 30.85 dB, a structural similarity index of 0.96, and a mean squared error of 18.16. Furthermore, all reconstructed images were used as inputs in a convolutional neural network to generate the best classifier for predicting FHD. Results: The proposed FetalNet model increased the FHD prediction rate by approximately 25% in terms of accuracy, sensitivity, and specificity and produced 100% predictive negative using unseen data. Conclusions: The proposed deep learning model has the potential to identify FHD accurately and shows potential for practical use in identifying congenital heart diseases in the future. |
| first_indexed | 2024-04-11T07:46:24Z |
| format | Article |
| id | doaj.art-999607e08cb44b63b2f6d0794ae4f2f2 |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-04-11T07:46:24Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-999607e08cb44b63b2f6d0794ae4f2f22022-12-22T04:36:18ZengElsevierInformatics in Medicine Unlocked2352-91482022-01-0135101136FetalNet: Low-light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect predictionSutarno Sutarno0Siti Nurmaini1Radiyati Umi Partan2Ade Iriani Sapitri3Bambang Tutuko4Muhammad Naufal Rachmatullah5Annisa Darmawahyuni6Firdaus Firdaus7Nuswil Bernolian8Deny Sulistiyo9Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Indonesia; Doctoral Program, Faculty of Engineering, Universitas Sriwijaya, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Indonesia; Corresponding author. Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, Indonesia.Faculty of Medicine, Universitas Sriwijaya, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, IndonesiaDivision of Fetomaternal, Department of Obstetrics and Gynaecology, Mohammad Hoesin General Hospital, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, IndonesiaBackground: Fetal heart defect (FHD) examination by ultrasound (US) is challenging because it involves low light, contrast, and brightness. Inadequate US images of fetal echocardiography play an important role in the failure to detect FHDs manually. The automatic interpretation of fetal echocardiography was proposed in a previous study. However, the low quality of US images reduces the prediction rate of computer-assisted diagnosis results. Methods: To increase the FHD prediction rate, we propose low-light fetal echocardiography enhancement stacking with a dense convolutional network classifier named “FetalNet.” Our proposed FetalNet model was developed using 460 US images to produce an image enhancement model. The results showed that all raw US images could be improved with satisfactory performance in terms of increasing the peak signal-to-noise ratio of 30.85 dB, a structural similarity index of 0.96, and a mean squared error of 18.16. Furthermore, all reconstructed images were used as inputs in a convolutional neural network to generate the best classifier for predicting FHD. Results: The proposed FetalNet model increased the FHD prediction rate by approximately 25% in terms of accuracy, sensitivity, and specificity and produced 100% predictive negative using unseen data. Conclusions: The proposed deep learning model has the potential to identify FHD accurately and shows potential for practical use in identifying congenital heart diseases in the future.http://www.sciencedirect.com/science/article/pii/S2352914822002738Deep learningUltrasoundCongenital heart diseaseLow light image enhancement |
| spellingShingle | Sutarno Sutarno Siti Nurmaini Radiyati Umi Partan Ade Iriani Sapitri Bambang Tutuko Muhammad Naufal Rachmatullah Annisa Darmawahyuni Firdaus Firdaus Nuswil Bernolian Deny Sulistiyo FetalNet: Low-light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect prediction Informatics in Medicine Unlocked Deep learning Ultrasound Congenital heart disease Low light image enhancement |
| title | FetalNet: Low-light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect prediction |
| title_full | FetalNet: Low-light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect prediction |
| title_fullStr | FetalNet: Low-light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect prediction |
| title_full_unstemmed | FetalNet: Low-light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect prediction |
| title_short | FetalNet: Low-light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect prediction |
| title_sort | fetalnet low light fetal echocardiography enhancement and dense convolutional network classifier for improving heart defect prediction |
| topic | Deep learning Ultrasound Congenital heart disease Low light image enhancement |
| url | http://www.sciencedirect.com/science/article/pii/S2352914822002738 |
| work_keys_str_mv | AT sutarnosutarno fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT sitinurmaini fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT radiyatiumipartan fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT adeirianisapitri fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT bambangtutuko fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT muhammadnaufalrachmatullah fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT annisadarmawahyuni fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT firdausfirdaus fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT nuswilbernolian fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction AT denysulistiyo fetalnetlowlightfetalechocardiographyenhancementanddenseconvolutionalnetworkclassifierforimprovingheartdefectprediction |