HPRUNET: A High-Precision Network for ALCAPA Segmentation with Residual Learning and Conditional Refinement
محورهای موضوعی : Neural Network
C. Rajeev
1
,
Karthika Natarajan
2
1 - School of Computer Science and Engineering, VIT-AP University, G-30, Inavolu, Beside AP Secretariat Amaravati, Andhra Pradesh-522237, India
2 - School of Computer Science and Engineering, VIT-AP University, G-30, Inavolu, Beside AP Secretariat Amaravati, Andhra Pradesh-522237, India
کلید واژه: ALCAPA, Medical Image segmentation, 3D Computed Tomography Angiography, Congenital heart disease, Deep Learning, High Pitched Residual U-Network (HPRUNET), Computed Tomography Angiography (CTA), Conditional Random Fields (CRFs),
چکیده مقاله :
Anomalous Left Coronary Artery from the Pulmonary Artery (ALCAPA) is a series of congenital heart defects requiring precise image segmentation for accurate diagnosis. Existing research faced limitations such as loss of image detail, poor contrast handling, and vulnerability to noise leading to decreased accuracy. To address these challenges, this research introduces the High-Pitched Residual U-Network designed for automatic segmentation of ALCAPA from 3D Computed Tomography Angiography images. The proposed model integrates U-Net with residual blocks to extract low and mid-level features, mitigating information degradation. The encoder compresses the image using convolution, max-pooling, and dropout layers, while the decoder reconstructs the segmented image with Conv2DTranspose layers and residual block concatenation. Segmentation is performed using swish activation and sigmoid activation, with segmentation masks refined using Conditional Random Fields. The proposed method achieved an accuracy of 98.65% demonstrating a significant improvement over traditional method. This study highlights the potential of HPRUNET in transforming clinical diagnosis and treatment planning by automating the segmentation process, reducing manual intervention, and improving the detection of ALCAPA.
Anomalous Left Coronary Artery from the Pulmonary Artery (ALCAPA) is a series of congenital heart defects requiring precise image segmentation for accurate diagnosis. Existing research faced limitations such as loss of image detail, poor contrast handling, and vulnerability to noise leading to decreased accuracy. To address these challenges, this research introduces the High-Pitched Residual U-Network designed for automatic segmentation of ALCAPA from 3D Computed Tomography Angiography images. The proposed model integrates U-Net with residual blocks to extract low and mid-level features, mitigating information degradation. The encoder compresses the image using convolution, max-pooling, and dropout layers, while the decoder reconstructs the segmented image with Conv2DTranspose layers and residual block concatenation. Segmentation is performed using swish activation and sigmoid activation, with segmentation masks refined using Conditional Random Fields. The proposed method achieved an accuracy of 98.65% demonstrating a significant improvement over traditional method. This study highlights the potential of HPRUNET in transforming clinical diagnosis and treatment planning by automating the segmentation process, reducing manual intervention, and improving the detection of ALCAPA.
[1] Kumar, K. (2022). MDCT Evaluation of Congenital Coronary Anomalies: Pictorial Essay.
[2] Evangelista, M., Ferrero, P., D’Aiello, A. F., Negura, D., Micheletti, A., Bevilacqua, F., & Chessa, M. (2024). Coronary artery anomalies: what are they? when to suspect? how to treat? —a narrative review. Translational Pediatrics, 13(7), 1242.
[3] Aboshahba, A., Alttahan, A. H. A. M., Mokarrab, M., & Sadek, Y. (2021). Long term follows up after successful recanalization of coronary artery chronic total occlusion using antegrade versus retrograde approach by single photon emission computed tomography. Journal of Cardiology Research Review & Reports. SRC/JCRRR-138. DOI: https://doi. org/10.47363/JCRRR/2021 (2), 133, 3.
[4] Jiang, M., Xie, X., Cao, F., & Wang, Y. (2021). Mitochondrial metabolism in myocardial remodeling and mechanical unloading: implications for ischemic heart disease. Frontiers in Cardiovascular Medicine, 8, 789267.
[5] Kubota, H., Endo, H., Ishii, H., Tsuchiya, H., Inaba, Y., Terakawa, K., & Sudo, K. (2020). Adult ALCAPA: from histological picture to clinical features. Journal of Cardiothoracic Surgery, 15, 1-9.
[6] Menahem, S., Sehgal, A., & Wurzel, D. F. (2023). Persistent tachypnoea in early infancy: a clinical perspective. Children, 10(5), 789.
[7] López, D. E. S., Ynostroza, S. I. M., Rodríguez, K. V., Saldaña, M. K. L., Chávez, J. A. V., & Pimentel, X. A. A. (2024). Anomalous Left Coronary Artery from the Pulmonary Artery (ALCAPA) Syndrome: Pathophysiology, Clinical Manifestations, and Management Strategies. International Journal of Medical Science and Clinical Research Studies, 4(05), 953-959.
[8] Prandi, F. R., Zaidi, A. N., LaRocca, G., Hadley, M., Riasat, M., Anastasius, M. O., & Lerakis, S. (2022). Sudden cardiac arrest in an adult with anomalous origin of the left coronary artery from the pulmonary artery (ALCAPA): case report. International Journal of Environmental Research and Public Health, 19(3), 1554.
[9] Gondal, M. U. R., Nair, D. P. J. R., Shah, S., Zafar, M., Hanif, M. A., McCauley, B., & Hope, E. (2024). Myocardial Infarction and Complete Heart Block in a Patient with Anomalous Origin of the Left Coronary Artery from the Pulmonary Artery (ALCAPA). Cureus, 16(6).
[10] Cambronero-Cortinas, E., Moratalla-Haro, P., González-García, A. E., & Oliver-Ruiz, J. M. (2020). Case report of asymptomatic very late presentation of ALCAPA syndrome: review of the literature since pathophysiology until treatment. European Heart Journal-Case Reports, 4(5), 1-5.
[11] Pačarić, S., Turk, T., Erić, I., Orkić, Ž., Petek Erić, A., Milostić-Srb, A., ... & Nemčić, A. (2020). Assessment of the quality of life in patients before and after coronary artery bypass grafting (CABG): a prospective study. International journal of environmental research and public health, 17(4), 1417.
[12] Lourens, E. C., Baker, R. A., & Krieg, B. M. (2022). Quality of life following cardiac rehabilitation in cardiac surgery patients. Journal of Cardiothoracic Surgery, 17(1), 137.
[13] Samaras, A., Moysidis, D. V., Papazoglou, A. S., Rampidis, G., Kampaktsis, P. N., Kouskouras, K., & Giannakoulas, G. (2023). Diagnostic Puzzles and Cause-Targeted Treatment Strategies in Myocardial Infarction with Non-Obstructive Coronary Arteries: An Updated Review. Journal of Clinical Medicine, 12(19), 6198.
[14] Šulcová, J., & Murgová, A. (2020). Quality of life in patients after acute coronary syndrome in a lifestyle context. Україна. Здоров’я нації, 2(3).
[15] Xin, H., & Zhu, M. (2023). Imaging options for defining anomalous origin of the coronary artery from the pulmonary artery. Quantitative Imaging in Medicine and Surgery, 13(2), 1164.
[16] Stephenson, N., Pushparajah, K., Wheeler, G., Deng, S., Schnabel, J. A., & Simpson, J. M. (2023). Extended reality for procedural planning and guidance in structural heart disease–a review of the state-of-the-art. The International Journal of Cardiovascular Imaging, 39(7), 1405-1419.
[17] Kong, B., Wang, X., Bai, J., et al. (2020). Learning tree-structured representation for 3D coronary artery segmentation. Computerized Medical Imaging and Graphics.
[18] Yang, X., Xu, L., Yu, S., Xia, Q., Li, H., & Zhang, S. (2024). Segmentation and vascular vectorization for coronary artery by geometry-based cascaded neural network. IEEE Transactions on Medical Imaging.
[19] Yang, Y. C., Dou, Y., Wang, Z. W., Yin, R. H., Pan, C. J., Duan, S. F., & Tang, X. Q. (2023). Prediction of myocardial ischemia in coronary heart disease patients using a CCTA–Based radiomic nomogram. Frontiers in Cardiovascular Medicine, 10, 1024773.
[20] Secinaro, A., Ntsinjana, H., Tann, O., Schuler, P. K., Muthurangu, V., Hughes, M., & Taylor, A. M. (2011). Cardiovascular magnetic resonance findings in repaired anomalous left coronary artery to pulmonary artery connection (ALCAPA). Journal of Cardiovascular Magnetic Resonance, 13, 1-6.
[21] Castaldi, B., Vida, V., Reffo, E., Padalino, M., Daniels, Q., Stellin, G., & Milanesi, O. (2017). Speckle tracking in ALCAPA patients after surgical repair as predictor of residual coronary disease. Pediatric cardiology, 38, 794-800.
[22] Krokovay, A., Pretre, R., Kretschmar, O., Knirsch, W., Valsangiacomo Buechel, E., & Dave, H. (2022). Anatomical reconstruction of proximal coronary artery stenosis in children. European Journal of Cardio-Thoracic Surgery, 62(3), ezac302.
[23] Jinmei, Z., Yunfei, L., Yue, W., & Yongjun, Q. (2020). Anomalous origin of the left coronary artery from the pulmonary artery (ALCAPA) is diagnosed in children and adolescents. Journal of cardiothoracic surgery, 15(1), 1-6.
[24] Zeng, A., Mi, C., Pan, D., Lu, Q., & Xu, X. (2022, December). ImageALCAPA: A 3D Computed Tomography Image Dataset for Automatic Segmentation of Anomalous Left Coronary Artery from Pulmonary Artery. In 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, 1800-1803.
