Parkinson’s Disease Detection on Spiral Images Using CNN With Meta-Classifiers


Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 16 | Issue : 01 | Page : –
    By

    S. Sumahasan,

  • K Purushotam Naidu,

  • V Lakshmana Rao,

  • A Udaya Kumar,

  1. Assistant Professor, Department of CSE, Gayatri Vidya Parishad for women, Visakhapatnam, Andhra Pradesh, India
  2. Assistant Professor, Dept of CSE (AI&ML), Gayatri Vidya Parishad for women, Visakhapatnam, Andhra Pradesh, India
  3. Assistant Professor, Department of CSE, Gayatri Vidya Parishad for women, Visakhapatnam, Andhra Pradesh, India
  4. Assistant Professor, Department of CSE, Gayatri Vidya Parishad for women, Visakhapatnam, Andhra Pradesh, India

Abstract

In this work, we provide a detailed method for identifying Parkinson’s Disease (PD) by integrating Convolutional Neural Network (CNN) and meta-classifiers. Through the utilization of a varied dataset consisting of handwritten spiral images, our methodology demonstrates commendable accuracy across a range of models. Specifically, our CNN model with meta-classifiers surpasses alternative approaches, achieving an impressive accuracy rate of 95.07%. By utilizing pre-established VGG16 and ResNet50 architectures as bases, the region-based CNN model achieves improved accuracy in PD detection, along with notable precision, recall, and f1-score evaluations. The results of this study emphasize the potential benefits of merging deep learning methodologies with ensemble techniques for reliable PD detection. Through the incorporation of CNNs with meta-classifiers, a hopeful route is introduced for non-invasive and precise identification of PD. This progress holds potential for enhancing patient outcomes and optimizing the efficacy of PD management protocols.

Keywords: Parkinson’s Disease, Convolutional Neural Network (CNN), Meta-classifiers, handwritten spiral images, VGG16, ResNet50.

[This article belongs to Journal of Computer Technology & Applications (jocta)]

How to cite this article:
S. Sumahasan, K Purushotam Naidu, V Lakshmana Rao, A Udaya Kumar. Parkinson’s Disease Detection on Spiral Images Using CNN With Meta-Classifiers. Journal of Computer Technology & Applications. 2024; 16(01):-.
How to cite this URL:
S. Sumahasan, K Purushotam Naidu, V Lakshmana Rao, A Udaya Kumar. Parkinson’s Disease Detection on Spiral Images Using CNN With Meta-Classifiers. Journal of Computer Technology & Applications. 2024; 16(01):-. Available from: https://journals.stmjournals.com/jocta/article=2024/view=191741


References

[1] Oñatibia‐Astibia A, Franco R, Martínez‐Pinilla E. Health benefits of methylxanthines in neurodegenerative diseases. Molecular nutrition & food research. 2017 Jun;61(6):1600670.

[2] Lang AE, Espay AJ. Disease modification in Parkinson’s disease: current approaches, challenges, and future considerations. Movement Disorders. 2018 May;33(5):660-77.

[3] Nolazco-Flores JA, Faundez-Zanuy M, De La Cueva VM, Mekyska J. Exploiting spectral and cepstral handwriting features on diagnosing Parkinson’s disease. IEEE Access. 2021 Oct 8;9:141599-610.

[4] Shalaby M, Belal NA, Omar Y. Data clustering improves Siamese neural networks classification of Parkinson’s disease. Complexity. 2021;2021(1):3112771.

[5] Thukroo IA, Bashir R, Giri KJ. A review into deep learning techniques for spoken language identification. Multimedia Tools and Applications. 2022 Sep;81(22):32593-624.

[6] Singh YB, Goel S. A systematic literature review of speech emotion recognition approaches. Neurocomputing. 2022 Jul 1;492:245-63.

[7] Cantürk I. Fuzzy recurrence plot-based analysis of dynamic and static spiral tests of Parkinson’s disease patients. Neural Computing and Applications. 2021 Jan;33(1):349-60.

[8] Diaz M, Moetesum M, Siddiqi I, Vessio G. Sequence-based dynamic handwriting analysis for Parkinson’s disease detection with one-dimensional convolutions and BiGRUs. Expert Systems with Applications. 2021 Apr 15;168:114405.

[9] Aghanavesi S, Memedi M, Dougherty M, Nyholm D, Westin J. Verification of a method for measuring Parkinson’s disease related temporal irregularity in spiral drawings. Sensors. 2017 Oct 13;17(10):2341.

[10] Parisi LU, Ma R, Zaernia A, Youseffi MA. Ηyper-sinh-convolutional neural network for early detection of parkinson’s disease from spiral drawings. WSEAS Trans Comput Res. 2021 Mar 31;9:1-7.

[11] Chakraborty S, Aich S, Han E, Park J, Kim HC. Parkinson’s disease detection from spiral and wave drawings using convolutional neural networks: A multistage classifier approach. In2020 22nd International Conference on Advanced Communication Technology (ICACT) 2020 Feb 16 (pp. 298-303). IEEE.

[12] Akter L. Early identification of Parkinson’s Disease from Hand-drawn Images using Histogram of oriented gradients and machine learning techniques. In2020 Emerging Technology in Computing, Communication and Electronics (ETCCE) 2020 Dec 21 (pp. 1-6). IEEE.

[13] Sivakumar M, Christinal AH, Jebasingh S. Parkinson’s disease diagnosis using a combined deep learning approach. In2021 3rd International Conference on Signal Processing and Communication (ICPSC) 2021 May 13 (pp. 81-84). IEEE.

[14] Kamble M, Shrivastava P, Jain M. Digitized spiral drawing classification for Parkinson’s disease diagnosis. Measurement: Sensors. 2021 Aug 1;16:100047.

[15] Moetesum M, Siddiqi I, Vincent N, Cloppet F. Assessing visual attributes of handwriting for prediction of neurological disorders—A case study on Parkinson’s disease. Pattern Recognition Letters. 2019 Apr 15;121:19-27.

[16] Impedovo D, Pirlo G, Vessio G. Dynamic handwriting analysis for supporting earlier Parkinson’s disease diagnosis. Information. 2018 Oct 3;9(10):247.

[17] Gupta JD, Chanda B. Novel features for diagnosis of Parkinson’s disease from off-line archimedean spiral images. In2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST) 2019 Oct 23 (pp. 1-6). IEEE.

[18] Zham P, Kumar DK, Dabnichki P, Poosapadi Arjunan S, Raghav S. Distinguishing different stages of Parkinson’s disease using composite index of speed and pen-pressure of sketching a spiral. Frontiers in neurology. 2017 Sep 6;8:435.

[19] Sun Y, Xue B, Zhang M, Yen GG, Lv J. Automatically designing CNN architectures using the genetic algorithm for image classification. IEEE transactions on cybernetics. 2020 Apr 21;50(9):3840-54.

[20] Razzak I, Kamran I, Naz S. Deep analysis of handwritten notes for early diagnosis of neurological disorders. In2020 International Joint Conference on Neural Networks (IJCNN) 2020 Jul 19 (pp. 1-6). IEEE.

[21] Shaban M. Deep convolutional neural network for Parkinson’s disease based handwriting screening. In2020 IEEE 17th International Symposium on Biomedical Imaging Workshops (ISBI Workshops) 2020 Apr 4 (pp. 1-4). IEEE.


Regular Issue Subscription Review Article
Volume 16
Issue 01
Received 05/10/2024
Accepted 04/11/2024
Published 31/12/2024


Loading citations…