Deep Neuro-Fuzzy System For Early-Stage Identification of Parkinson’s Disease Using SPECT Images

Jothi S, Jothi S, Anita Sebasthiyar, Sivakumar S, Sivakumar S

Abstract


A neurodegenerative disorder called Parkinson’s disease (PD) is identified at the increasing loss of neurons that produce dopamine in the substantia nigra region of human brain. It significantly impairs motor and non-motor functions, thereby diminishing the overall quality of life in affected individuals. A novel framework is proposed for detecting early stage of PD, employing Deep Neuro-Fuzzy System (DNFS) optimized with Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). Data utilized for this analysis are extracted from 16 image slices showing striatal uptake content in the striatum, named as volume-containing DaTscan image slices (VCDIS) taken from the database called Parkinson’s Progression Markers Initiative (PPMI). The shape and texture characteristics of segmented VCDIS are utilized as features which are combined with Striatal biding ratio (SBR) to distinguish Healthy Individuals (HI) from early-stage PD (EPD). The dataset includes values of 620 DaTscan images with SBR values: 430 from EPD cases and 190 from HI. The effectiveness of the framework is evaluated using 70:30 and 80:20 split ratios, based on metrics such as accuracy, loss, F1 score, precision, and recall. The DNFS-PSO model is presented an impressive accuracy of 98.77% and an error rate of 0.0199 for the chosen features using a 70:30 data split. The outcomes of the proposed model potentially aid clinicians in prompt diagnosis.


Full Text:

PDF

References


References

Konnova, E.A. and Swanberg, M., 2018. Animal models of Parkinson’s disease. In: T.B. Stoker and J.C. Greenland, eds. Parkinson’s Disease: Pathogenesis and Clinical Aspects [online]. Brisbane (AU): Codon Publications, Chapter 5. Available at: https://pubmed.ncbi.nlm.nih.gov/30702844

Mahmood, A., Khan, M.M., Imran, M., Alhajlah, O., Dhahri, H. and Karamat, T., 2023. End-to-end deep learning method for detection of invasive Parkinson’s disease. Diagnostics, 13(6), p.1088. https://doi.org/10.3390/diagnostics13061088

Wooten, G.F., Currie, L.J., Bovbjerg, V.E., Lee, J.K. and Patrie, J., 2004. Are men at greater risk for Parkinson’s disease than women? Journal of Neurology, Neurosurgery and Psychiatry, 75(4), pp.637–639. https://doi.org/10.1136/jnnp.2003.020982

Constantinides, V.C. et al., 2023. Dopamine transporter SPECT imaging in Parkinson’s disease and atypical Parkinsonism: A study of 137 patients. Neurological Sciences, 44(5), pp.1613–1623. https://doi.org/10.1007/s10072-023-06628-9

Prashanth, R., Roy, S.D., Mandal, P. and Ghosh, S., 2014. Automatic classification and prediction models for early Parkinson’s disease diagnosis from SPECT imaging. Expert Systems with Applications, 41, pp.3333–3342. https://doi.org/10.1016/j.eswa.2013.11.031

Kaufman, M.J. and Madras, B.K., 1991. Severe depletion of cocaine recognition sites associated with the dopamine transporter in Parkinson’s-diseased striatum. Synapse, 9, pp.43–49. https://doi.org/10.1002/syn.890090107

Cummings, J.L. et al., 2011. The role of dopaminergic imaging in patients with symptoms of dopaminergic system neurodegeneration. Brain, 134, pp.3146–3166. https://doi.org/10.1093/brain/awr177

Moore, D.J., West, A.B., Dawson, V.L. and Dawson, T.M., 2005. Molecular pathophysiology of Parkinson’s disease. Annual Review of Neuroscience, 28, pp.57–87. https://doi.org/10.1146/annurev.neuro.28.061604.135718

Booth, T.C. et al., 2015. The role of functional dopamine transporter. AJNR: American Journal of Neuroradiology, 36, pp.229–235. https://doi.org/10.3174/ajnr.A3970

Bairactaris, C. et al., 2009. Impact of dopamine transporter single photon emission computed tomography imaging using I-123 ioflupane on diagnoses of patients with Parkinsonian syndromes. Journal of Clinical Neuroscience, 16, pp.246–252. https://doi.org/10.1016/j.jocn.2008.01.020

Marek, K. et al., 2011. The Parkinson Progression Marker Initiative (PPMI). Progress in Neurobiology, 95, pp.629–635. https://doi.org/10.1016/j.pneurobio.2011.09.005

Prashanth, R., Roy, S.D., Ghosh, S. and Mandal, K.P., 2013. Shape features as biomarkers in early Parkinson's disease. In: 6th International IEEE/EMBS Conference on Neural Engineering (NER). https://doi.org/10.1109/NER.2013.6695985

Anita, S. and Aruna Priya, P., 2020. Diagnosis of Parkinson’s disease at an early stage using volume rendering SPECT image slices. Arabian Journal for Science and Engineering, 45, pp.2799–2811. https://doi.org/10.1007/s13369-019-04152-7

Talpur, N. et al., 2022. A comprehensive review of deep neuro-fuzzy system architectures and their optimization methods. Neural Computing and Applications, 34(6), pp.1–39. https://doi.org/10.1007/s00521-021-06807-9

Rana, J., Raidah, S.A.L. and Khudeyer, S.A., 2024. Review: Deep learning and fuzzy logic applications. Engineering and Technology Journal, 9(6), pp.4231–4240. https://doi.org/10.47191/etj/v9i06.09

Honari, K., 2023. DCNFIS: Deep convolutional neuro-fuzzy inference system. arXiv [online]. Available at: https://doi.org/10.48550/arXiv.2308.06378

Vijay, K. et al., 2024. A survey on hybrid deep learning and neural fuzzy inference systems for early coronary heart disease detection. REST Journal on Data Analytics and Artificial Intelligence, 3(2), pp.152–161. https://doi.org/10.46632/jdaai/3/2/19

Aversano, L., Bernardi, M.L., Cimitile, M. and Pecori, R., 2020. Fuzzy neural networks to detect Parkinson disease. In: IEEE International Conference on Fuzzy Systems, pp.1–8. https://doi.org/10.1109/FUZZ48607.2020.9177948

Masood, S., Sharif, M., Masood, A. et al., 2015. A survey on medical image segmentation. Current Medical Imaging Reviews, 11(1), pp.3–14. https://doi.org/10.2174/157340561101150423103441

Djang, D.S. et al., 2012. SNM practice guideline for dopamine transporter imaging with 123I-ioflupane SPECT 1.0. Journal of Nuclear Medicine, 53, pp.154–163. https://doi.org/10.2967/jnumed.111.100784

Prashanth, R., 2015. Computer-aided early detection of Parkinson's disease through multimodal data analysis. Ph.D. thesis, Indian Institute of Technology, Delhi.

Zhang, M., 2009. Bilateral filter in image processing. Master’s Thesis, Louisiana State University.

Yang, C.H., Moi, S.H., Hou, M.F., Chuang, L.Y. and Lin, Y.D., 2020. Applications of deep learning and fuzzy systems to detect cancer mortality in next-generation genomic data. IEEE Transactions on Fuzzy Systems, 29(12), pp.3833–3844. https://doi.org/10.1109/TFUZZ.2020.3028909

Unal, Z. and Cetin, E.I., 2022. Fuzzy logic and deep learning integration in Likert type data. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 22(1), pp.112–125. https://doi.org/10.35414/akufemubid.1019671

Abiyev, R.H. and Abizade, S., 2016. Diagnosing Parkinson’s diseases using fuzzy neural system. Computational and Mathematical Methods in Medicine, 2016, Article ID 1267919, 9 pages. https://doi.org/10.1155/2016/1267919

Balasubramanian, K. and Ananthamoorthy, N.P., 2021. Improved adaptive neuro-fuzzy inference system based on modified glowworm swarm and differential evolution optimization algorithm for medical diagnosis. Neural Computing and Applications, 33(13), pp.7649–7660. https://doi.org/10.1007/s00521-020-05507-0

Georgiadis, P. et al., 2008. Computer aided discrimination between primary and secondary brain tumors on MRI: From 2D to 3D texture analysis. E-Journal of Science and Technology, 8, pp.9–18.

Sharma, N. et al., 2008. Segmentation and classification of medical images using texture-primitive features: Application of BAM-type artificial neural network. Journal of Medical Physics, 33, pp.119–126. https://doi.org/10.4103/0971-6203.42763




DOI: https://doi.org/10.31449/inf.v49i3.9121

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.