Advanced Fetal Cardiac Anomaly Diagnosis with Multispectral LBP Transformation Techniques and Deep Learning Models
Keywords:
Deep learning, Diagnosis, Fetal cardiac anomaly, Image transformation, Local Binary Pattern, MultispectralAbstract
This research is dedicated to developing an advanced deep learning diagnostic model capable of accurately diagnosing fetal cardiac anomalies in real-time ultrasound scan images. To achieve this, the dataset utilized in the previous research has undergone a transformation using Multispectral Local Binary Pattern (MLBP) and Adaptive Multispectral Local Binary Pattern (AMLBP) techniques. Local Binary Pattern (LBP) is an essential texture image feature, and MLBP and AMLBP are enhanced versions designed to capture intricate local structures and patterns within each image. Unlike the traditional LBP transformation, MLBP and AMLBP take color channels into account, allowing for more comprehensive feature extraction from the input images. The previously formed FetalEcho_V05 dataset has been transformed into two distinct datasets: FetalEcho_V0502 using MLBP and FetalEcho_V0503 using AMLBP. Both of these datasets are then employed in training customized versions of AlexNet, custom CNN(CCNN), VGG16, and ResNet50 deep learning (DL) models to create powerful classifiers. Among all the models, CCNN model demonstrated the best performance on the FetalEcho_V0503 dataset, showcasing its superiority in accurately diagnosing fetal cardiac anomalies from real-time ultrasound scan images.
Downloads
References
Patil, V. K., et al. ‘Real Time Emotion Recognition with AD8232 ECG Sensor for Classwise Performance Evaluation of Machine Learning Methods’. International Journal of Engineering, vol. 36, no. 6, 2023, pp. 1040–1047.
Khazendar, S., et al. ‘Automated Characterisation of Ultrasound Images of Ovarian Tumours: The Diagnostic Accuracy of a Support Vector Machine and Image Processing with a LocalBinaryPattern Operator’. Facts, Views & Vision in ObGyn, vol. 7, 2015.
Zeebaree, D. Q., et al. ‘Multi-Level Fusion in Ultrasound for Cancer Detection Based on Uniform LBP Features’. Uniform LBP Features. Computers, Materials & Continua, no. 3, 2021.
Iakovidis, Dimitris K., et al. ‘Fuzzy Local Binary Patterns for Ultrasound Texture Characterization’. Lecture Notes in Computer Science, Springer Berlin Heidelberg, 2008, pp. 750–759, https://doi.org10.1007/978-3-540-69812-8_74. Lecture Notes in Computer Science.
Liu, Tianjiao, et al. ‘Classification of Thyroid Nodules in Ultrasound Images Using Deep Model Based Transfer Learning and Hybrid Features’. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2017, https://doi.org10.1109/icassp.2017.7952290.
Divya, M. O., and M. S. Vijaya. ‘Artificial Intelligent Models for Automatic Diagnosis of Foetal Cardiac Anomalies: A Meta-Analysis’. Proceedings of the International Conference on Cognitive and Intelligent Computing, Springer Nature Singapore, 2023, pp. 179–192, https://doi.org10.1007/978-981-19-2358-6_18.
Divya, M. O., and M. S. Vijaya. "Optimizing Pre-processing for Foetal Cardiac Ultra Sound Image Classification." International Conference on Innovations in Bio-Inspired Computing and Applications. Cham: Springer Nature Switzerland, 2022.
Divya, M. O., and E. R. Vimina. ‘Content Based Image Retrieval with Multi-Channel LBP and Colour Features’. International Journal of Applied Pattern Recognition, vol. 6, no. 2, Inderscience Publishers, 2020, p. 177, https://doi.org10. 1504/ijapr.2020.111524.
Vimina, E. R., and M. O. Divya. ‘Maximal Multi-Channel Local Binary Pattern with Colour Information for CBIR’. Multimedia Tools and Applications, vol. 79, 2020, pp. 25357–25377.
‘Diagnostic Models for Foetal Cardiac Anomalies Using Pattern Classification and FetalEcho_V01 Dataset (In Press)’. Proceedings of the Eighth International Conference on Computing, Communication and Security (ICCCS 2023, 2023.
MO, DIVYA, and M. S. Vijaya. "REVOLUTIONIZING FOETAL CARDIAC ANOMALY DIAGNOSIS: UNLEASHING THE POWER OF DEEP LEARNING ON FOETALECHO IMAGES." Journal of Theoretical and Applied Information Technology 101.16 (2023).
Holland, B. J., et al. ‘Prenatal Diagnosis of Critical Congenital Heart Disease Reduces Risk of Death from Cardiovascular Compromise Prior to Planned Neonatal Cardiac Surgery: A Meta-Analysis’. Ultrasound in Obstetrics & Gynecology: The Official Journal of the International Society of Ultrasound in Obstetrics and Gynecology, vol. 45, no. 6, Wiley, June 2015, pp. 631–638, https://doi.org10.1002/uog.14882.
Suard, Cornélie, et al. ‘Accuracy of Prenatal Screening for Congenital Heart Disease in Population: A Retrospective Study in Southern France’. PloS One, vol. 15, no. 10, Public Library of Science (PLoS), Oct. 2020, p. e0239476, https://doi.org10.1371/journal.pone.0239476.
Changlani, Trupti Deepak, et al. ‘Outcomes of Infants with Prenatally Diagnosed Congenital Heart Disease Delivered in a Tertiary-Care Pediatric Cardiac Facility’. Indian Pediatrics, vol. 52, no. 10, Springer Science and Business Media LLC, Oct. 2015, pp. 852–856, https://doi.org10.1007/s13312-015-0731-x.
Vijayaraghavan, Aparna, et al. ‘Prenatal Diagnosis and Planned Peri-Partum Care as a Strategy to Improve Pre-Operative Status in Neonates with Critical CHDs in Low-Resource Settings: A Prospective Study’. Cardiology in the Young, vol. 29, no. 12, Cambridge University Press (CUP), Dec. 2019, pp. 1481–1488, https://doi.org10.1 017/S104 795111900252X.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
