A Split and Merge UNet: A Deep Learning Assisted UNet Model to Segment Corpus Callosum of Brain for Automatic Autism Detection

Year : 2024 | Volume : 11 | Issue : 03 | Page : 1 9
    By

    Nagashree N.,

  • Amarnath Patil,

  • Ananya Rao G.R.,

  • Sanjana R.S.,

  1. Associate Professor and Head, Department of Computer Science and Engineering (Data Science), Sai Vidya Institute of Technology, Rajanukunte, Karnataka, India
  2. Assistant Professor, Department of Computer Science and Engineering (Data Science), Sai Vidya Institute of Technology, Rajanukunte, Karnataka, India
  3. Student, Department of Computer Science and Engineering (Data Science), Sai Vidya Institute of Technology, Rajanukunte, Karnataka, India
  4. Student, Department of Computer Science and Engineering (Data Science), Sai Vidya Institute of Technology, Rajanukunte, Karnataka, India

Abstract

In recent years, deep learning techniques have shown remarkable performance in various image analysis applications, particularly in the domain of medical image processing. Among these, image segmentation plays a critical role, as it helps in isolating and analyzing specific regions within medical images. The proposed study focuses on segmenting the corpus callosum, a vital structure in the human brain, using a novel optimization technique known as the Split and Merge algorithm, combined with the UNet architecture—a fully connected neural network widely recognized for its effectiveness in biomedical image segmentation. Autism, a neurodevelopmental disorder that affects social communication, behavior, and cognitive functioning, is typically diagnosed in children between the ages of 2 and 5. Research has identified the corpus callosum, the largest white matter structure in the brain, as a potential biomarker for detecting autism, especially through MRI scans. Structural abnormalities in the corpus callosum have been correlated with autism, making it a key focus in early diagnosis. This work introduces an automated approach to detecting autism by leveraging the Split and Merge UNet segmentation methodology. The proposed system aims to accurately segment the corpus callosum region from MRI images, facilitating the early detection of autism. By combining the precision of the Split and Merge algorithm with the robust learning capabilities of UNet, this methodology promises to offer an efficient and reliable tool for medical professionals, ultimately aiding in the timely intervention and treatment of autism.

Keywords: ASD, MRI, UNet, segmentation, split and merge classification, ABIDE

[This article belongs to Journal of Multimedia Technology & Recent Advancements ]

How to cite this article:
Nagashree N., Amarnath Patil, Ananya Rao G.R., Sanjana R.S.. A Split and Merge UNet: A Deep Learning Assisted UNet Model to Segment Corpus Callosum of Brain for Automatic Autism Detection. Journal of Multimedia Technology & Recent Advancements. 2024; 11(03):1-9.
How to cite this URL:
Nagashree N., Amarnath Patil, Ananya Rao G.R., Sanjana R.S.. A Split and Merge UNet: A Deep Learning Assisted UNet Model to Segment Corpus Callosum of Brain for Automatic Autism Detection. Journal of Multimedia Technology & Recent Advancements. 2024; 11(03):1-9. Available from: https://journals.stmjournals.com/jomtra/article=2024/view=178758


References

  1. Geschwind DH. Genetics of autism spectrum disorders. Trends Cogn Sci. 2011;15:409-16. DOI: 10.1016/j.tics.2011.07.003. PubMed PMID: 21855394.
  2. Nagashree N, Patil P, Patil S, Kokatanur M. Performance metrics for segmentation algorithms in brain MRI for early detection of autism. Int J Innov Technol Explor Eng. 2019;9:561-4. DOI: 10.35940/ijitee.B1401.1292S19.
  3. Nagashree N, Chitralekha M, Harsha SM, Sai Usha Sree SM, Chinmayee M, Basavaraj SH. A Modified UNet based Framework towards Early Detection of autism using EEG Waves. In: 2023 2nd International Conference for Innovation in Technology (INOCON); 2023. IEEE Publications; p. 1-4. DOI: 10.1109/INOCON57975.2023.10101224.
  4. Harshini R, Gaokar N, Nagashree N. A deep learning semantic segmentation-based document classification method. Int J Comput Learn Intell. 2023;2:14-6.
  5. Desai V, Hagare Annappaiah DH. Reputation-based security model for detecting biased attacks in big data. Indones J Electr Eng Comput Sci. 2023;29:1567-76. DOI: 10.11591/ijeecs.v29.i3.pp1567-1576.
  6. Desai V, Annappaiah DH. Secure efficient task communication mechanisms for big data environment. Int J Inf Technol Secur. 2023;15:3-14. DOI: 10.59035/EZOB4017.
  7. Desai V, Dinesh HA. Efficient reputation-based cyber attack detection mechanism for Big Data environment. Indian J Sci Technol. 2022;15:592-602. DOI: 10.17485/IJST/v15i13.2102.
  8. Karthigai S, Vantamuri SB, Arunpriya C, Desai V, Daniel AN. Securing wireless sensor networks using deep learning-based approach for eliminating data modification in sensor nodes. Commun Technol. 2023;14:2939-44.
  9. Varun E, Ravikumar P. Community mining in multi-relational and heterogeneous telecom network. In: 2016 IEEE 6th International Conference on Advanced Computing (IACC). IEEE Publications; 2016. p. 232–4. DOI: 10.1109/IACC.2016.58.
  10. Ajay VG, Mathew T. Size reduction of microstrip patch antenna through metamaterial approach for WiMAX application. In: 2017 international conference on wireless communications, signal processing and networking (WiSPNET); 2017. IEEE Publications; p. 379-81. DOI: 10.1109/WiSP
    2017.8299782.
  11. Ajay VG, Parvathy AR, Mathew T. Microstrip antenna with DGS based on CSRR array for WiMAX applications. Int J Electr Comput Eng. 2019;9:157.
  12. Gowda MB, Boraiah NK, Eshappa V, Shekara GK. Classification of epileptic EEG signals using improved atomic search optimization algorithm. Int J Intell Eng Syst. 2023;16:134-44. DOI: 10.22266/ijies2023.1231.12.
  13. Cardoso IL, Almeida S. Genes involved in the development of autism. Int Arch Commun Disord. 2019;2:1-9.
  14. Canali G, Garcia M, Hivert B, Pinatel D, Goullancourt A, Oguievetskaia K, et al. Genetic variants in autism-related CNTNAP2 impair axonal growth of cortical neurons. Hum Mol Genet. 2018;27:1941-54. DOI: 10.1093/hmg/ddy102. PubMed PMID: 29788201.
  15. Rodenas-Cuadrado P, Ho J, Vernes SC. Shining a light on CNTNAP2: Complex functions to complex disorders. Eur J Hum Genet. 2014;22:171-8. DOI: 10.1038/ejhg.2013.100. PubMed PMID: 23714751.
  16. Nagesh N, Patil P, Patil S, Kokatanur M. An architectural framework for automatic detection of autism using deep convolution networks and genetic algorithm. Int J Electr Comput Eng. 2022;12:1768-75. DOI: 10.11591/ijece.v12i2.pp1768-75.
  17. Peñagarikano O, Geschwind DH. What does CNTNAP2 reveal about autism spectrum disorder? Trends Mol Med. 2012;18:156-63. DOI: 10.1016/j.molmed.2012.01.003. PubMed PMID: 22365836.
  18. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI. 18th international conference; Munich, Germany; 2015 Oct 5-9. Springer International Publishing; p. 234-41.
  19. Nielsen JA, Zielinski BA, Fletcher PT, Alexander AL, Lange N, Bigler ED, et al. Abnormal lateralization of functional connectivity between language and default mode regions in autism. Mol Autism. 2014;5:8. DOI: 10.1186/2040-2392-5-8. PubMed PMID: 24502324.
  20. Bieniecki W. New image processing algorithms in computer vision systems for pathomorphologic diagnostics. Zeszyty Naukowe. Elektryka/Politechnika Łódzka. 2006;109:5-14.
  21. Nair BB, Pruthvi TR. A segmentation approaches to detect autism and dementia from brain MRI. Int J Recent Technol Eng (IJRTE). 2019;7:141-4.
  22. Sherkatghanad Z, Akhondzadeh M, Salari S, Zomorodi-Moghadam M, Abdar M, Acharya UR, et al. Automated detection of autism spectrum disorder using a convolutional neural network. Front Neurosci. 2019;13:1325. DOI: 10.3389/fnins.2019.01325. PubMed: 32009868.
  23. Sharif H, Khan RA. A novel machine learning based framework for detection of autism spectrum disorder (ASD). Appl Artif Intell. 2022;36:2004655. DOI: 10.1080/08839514.2021.2004655.
  24. Mostafa S, Tang L, Wu FX. Diagnosis of autism spectrum disorder based on eigenvalues of brain networks. IEEE Access. 2019;7:128474-86. DOI: 10.1109/ACCESS.2019.2940198.
  25. Katuwal GJ. Machine-Learning-Based Autism Detection Using Brain Imaging [Master’s thesis]. Rochester Institute of Technology; 2017.
  26. Hyde KK, Novack MN, LaHaye N, Parlett-Pelleriti C, Anden R, Dixon DR, Linstead E. Applications of supervised machine learning in autism spectrum disorder research: A review. Rev J Autism Dev Disord. 2019;6:128-46. DOI: 10.1007/s40489-019-00158-x.
  27. Despotović I, Goossens B, Philips W. MRI segmentation of the human brain: Challenges, methods, and applications. Comput Math Methods Med. 2015;2015:450341. DOI: 10.1155/2015/450341. PubMed PMID: 25945121.
  28. Chen R, Jiao Y, Herskovits EH. Structural MRI in autism spectrum disorder. Pediatr Res. 2011;69:63R-8R. DOI: 10.1203/PDR.0b013e318212c2b3. PubMed PMID: 21289538.
  29. Raj S, Masood S. Analysis and detection of autism spectrum disorder using machine learning techniques. Procedia Comput Sci. 2020;167:994-1004. DOI: 10.1016/j.procs.2020.03.399.
  30. Tepest R. The meaning of diagnosis for different designations in talking about autism. J Autism Dev Disord. 2021;51:760–1. DOI: 10.1007/s10803-020-04584-3. PubMed: 32607797.
  31. Premkumar K, Murugapriya K, Varsha MR, Asmitha R, Sureka S. Facial emotion recognition for autism children. Int J Innov Technol Explor Eng. 2020;9:1274-8. DOI: 10.35940/ijitee.F3772.
  32. Nagashree N, Patil P, Patil S, Kokatanur M. Alpha beta pruned UNet-a modified unet framework to segment MRI brain image to analyse the effects of CNTNAP2 gene towards autism detection. In: 2021 3rd International Conference on Computer Communication and the Internet (ICCCI); 2021. IEEE Publications; p. 23-6.
Regular Issue Subscription Review Article
Volume 11
Issue 03
Received 03/05/2024
Accepted 01/10/2024
Published 18/10/2024
273

Login


My IP

PlumX Metrics