HWR-PDNET: A TRANSFER LEARNING CNN FOR PARKINSON’S DETECTION FROM HANDWRITING IMAGES

(Received: 6-Jun.-2025, Revised: 13-Aug.-2025 , Accepted: 22-Aug.-2025)

Authors Mathu T., Ronal Roy, Jenefa Archpaul, Ebenezer V.,

Keywords #Parkinson’s disease #Handwriting analysis #Early diagnosis #Transfer learning #Deep learning in healthcare #Convolutional neural networks (CNNs)

Abstract Parkinson’s Disease (PD) is a progressive, chronic neurological disorder that is distinguished by abnormalities in the motor system. The condition can be detected in the early stage by the irregular handwriting of the individual. Early diagnosis is critical to enable timely therapeutic intervention and slow disease advancement. However, traditional diagnostic approaches largely depend on subjective clinical assessments, which lack scalability and exhibit reduced sensitivity in the prodromal phase. The present study proposes a well-established deep-learning architecture using transfer learning with MobileNetV2, which can be used for early diagnosis of Parkinson’s Disease through handwriting images. The dataset includes 816 samples from 120 people. It is augmented through grayscale and HSL to add more variety to feature samples of the model. A two-stage training regimen—initial base freezing followed by fine-tuning with a reduced learning rate—was employed to optimize convergence and generalization. The approach presented in this study scored 92% on accuracy with an F1- score of 0.88 and a precision of 0.81, outperforming those of conventional baselines in regard to sensitivity and robustness. The resulting framework is lightweight, non-invasive, and well-suited for real-time screening applications, offering significant potential for clinical decision support and remote telehealth deployments.

References

[1] M. Alissa et al., "Parkinson’s Disease Diagnosis Using Convolutional Neural Networks and Figure-copying Tasks," Neural Computing and Applications, vol. 34, no. 2, pp. 1433–53, Sept. 2021.

[2] M. Hireš et al., "Convolutional Neural Network Ensemble for Parkinson’s Disease Detection fromVoice Recordings," Computers in Biology and Medicine, vol. 141, pp. 105021–105021, Nov. 2021.

[3] H. Chen et al., "A Parkinson’s Disease-related Nuclei Segmentation Network Based on CNN-Transformer Interleaved Encoder with Feature Fusion," Computerized Medical Imaging and Graphics, vol. 118, p. 102465, 2024.

[4] N. Aggarwal, B. S. Saini and Savita Gupta, "A Deep 1-D CNN Learning Approach with DataAugmentation for Classification of Parkinson’s Disease and Scans without Evidence of Dopamine Deficit (SWEDD)," Biomedical Signal Processing and Control, vol. 91, p. 106008, 2024.

[5] X.-C. Wang et al., "Comparison of One- Two- and Three-dimensional CNN Models for Drawing Test-based Diagnostics of Parkinson’s Disease," Biomedical Signal Processing and Control, vol. 87, p. 105436, 2024.

[6] M. F. Allebawi et al., "Parkinson’s Disease Detection from Online Handwriting Based on Beta-Elliptical Approach and Fuzzy Perceptual Detector," IEEE Access, vol. 12, pp. 56936-56950, 2024.

[7] L. Sigcha, L. Borz and G. Olmo, "Deep Learning Algorithms for Detecting Freezing of Gait inParkinson’s Disease: A Cross-dataset Study," Expert Systems with Applications, vol. 255, Part A, p. 124522, 2024.

[8] G. Celik and E. Başaran, "Proposing a New Approach Based on Convolutional Neural Networks andRandom Forest for the Diagnosis of Parkinson’s Disease from Speech Signals," Applied Acoustics, vol. 211, p. 109476, 2023.

[9] N. Madusanka and B.-il Lee, "Vocal Biomarkers for Parkinson’s Disease Classification Using Audio Spectrogram Transformers," Journal of Voice, in Press, 10.1016/j.jvoice.2024.11.008, 2024.

[10] N. Khalid and M. S. Ehsan, "Critical Analysis of Parkinson’s Disease Detection Using EEG Sub-bandsand Gated Recurrent Unit," Engineering Science and Technology, an Int. J., vol. 59, p. 101855, 2024.

[11] Z. Li et al., "A Survey of Convolutional Neural Networks: Analysis, Applications and Prospects," IEEETransactions on Neural Networks and Learning Systems, vol. 33, no. 12, pp. 6999-7019, 2021.

[12] Y. Qi et al., "A Comprehensive Overview of Image Enhancement Techniques," Archives ofComputational Methods in Engineering, vol. 29, pp. 583-607, 2021.

[13] D. A. Van Dyk and X.-L. Meng, "The Art of Data Augmentation," Journal of Computational andGraphical Statistics, vol. 10, no. 1, pp. 1-50, 2001.

[14] D. Ping Tian, "A Review on Image Feature Extraction and Representation Techniques," Int. Journal ofMultimedia and Ubiquitous Engineering, vol. 8, no. 4, pp. 385-396, 2013.

[15] K. Dong et al., "MobileNetV2 Model for Image Classification," Proc. of the 2020 2nd IEEE Int. Conf.on Information Technology and Computer Application (ITCA), pp. 476-480, Guangzhou, China, 2020.

[16] J. He et al., "ReLU Deep Neural Networks and Linear Finite Elements," arXiv preprintarXiv:1807.03973, 2018.

[17] Z. Zhang, "Improved Adam Optimizer for Deep Neural Networks," Proc. of the 2018 IEEE/ACM 26thInt. Symposium on Quality of Service (IWQoS), Banff, AB, Canada, 2018.

[18] F. Zhuang et al., "A Comprehensive Survey on Transfer Learning," Proceedings of the IEEE, vol. 109,no. 1, pp. 43-76, 2020.

[19] F. Radenović, G. Tolias and O. Chum, "CNN Image Retrieval Learns from BoW: Unsupervised Fine-tuning with Hard Examples," Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016.

[20] C. S. Corley et al., "Exploring the Use of Deep Learning for Feature Location," Proc. of the 2015 IEEEInt. Conf. on Software Maintenance and Evolution (ICSME), Bremen, Germany, pp. 556-560, 2015.

[21] X. Jiang, H. Yu, J. Yang, X. Liu and Z. Li, "A New Network Structure for Parkinson’s HandwritingImage Recognition," Medical Engineering & Physics, vol. 139, Article no. 104333, 2025.

[22] H. Lu, G. Qi, D. Wu et al., "A Novel Feature Extraction Method Based on Dynamic Handwriting forParkinson’s Disease Detection," PloS One, vol. 20, no. 1, Article no. e0318021, 2025.

[23] I. Kansizoglou, K. A. Tsintotas, D. Bratanov and A. Gasteratos, "Drawing-aware Parkinson’s DiseaseDetection through Hierarchical Deep Learning Models," IEEE Access, vol. 13, pp. 21880-21890, 2025.

[24] A. S. M. Miah, T. Suzuki and J. Shin, "A Methodological and Structural Review of Parkinson’s DiseaseDetection across Diverse Data Modalities," IEEE Access, vol.13, pp. 98931-98975, 2025.

[25] A. Javeed, L. Ali, R. Nour, A. Noor and N. Golilarz, "Handwriting-based Detection of Schizophreniaand Bipolar Disorder Using Machine Learning," IEEE Sensors J., vol. 25, no. 5, pp. 9113-9120, 2025.

[26] A. Al-Shannaq and L. Elrefaei, "Age Estimation Using Specific Domain Transfer Learning," JordanianJournal of Computers and Information Technology (JJCIT), vol. 6, no. 2, pp. 122–139, 2020.