Advertisement

Detection of ataxia in low disability MS patients by hybrid convolutional neural networks based on images of plantar pressure distribution

Published:September 14, 2021DOI:https://doi.org/10.1016/j.msard.2021.103261

      Highlights

      • Using an image dataset containing dynamic plantar pressure distribution, ataxia can be detected in MS patients with low disability using the convolutional neural network (CNN) approach.
      • % 89.23 accuracy was achieved with the VGG19-SVM hybrid model.
      • By detecting ataxia in low disability MS patients, it is an alternative and objective method that supports physicians to make an early decision about the disease.

      Abstract

      Background

      This study aimed to detect ataxia in patients with multiple sclerosis (PwMS) with a deep learning-based approach based on images showing plantar pressure distribution of the patients. The secondary aim of the study was to investigate an alternative and objective method in the early diagnosis of ataxia in these patients.

      Methods

      A total of 105 images showing plantar pressure distribution of 43 ataxic PwMS and 62 healthy individuals were analyzed. The images were resized for the models including VGG16, VGG19, ResNet, DenseNet, MobileNet, NasNetMobile, and NasNetLarge. Feature vectors were extracted from the resized images and then classified using Support Vector Machines (SVM), K-Nearest Neighbors (K-NN), and Artificial Neural Network (ANN). A 10-fold cross-validation was applied to increase the validity of the classifiers.

      Results

      The VGG19-SVM hybrid model showed the highest accuracy, sensitivity, and specificity values (89.23%, 89.65%, and 88.88%, respectively).

      Conclusion

      The proposed method provided an automatic decision support system for detecting ataxia based on images showing plantar pressure distribution in patients with PwMS. The performance of the proposed method indicated that this method can be applied in clinical practice to establish a rapid diagnosis of ataxia that is asymptomatic or difficult to detect clinically and that it can be recommended as a useful aid for the physician in clinical practice.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Multiple Sclerosis and Related Disorders
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Kobelt G.
        • Thompson A.
        • Berg J.
        • Gannedahl M.
        • Eriksson J.
        • MSCOI Study Group
        European Multiple Sclerosis Platform. New insights into the burden and costs of multiple sclerosis in Europe.
        Mult. Scler. 2017 Jul; 23 (Epub 2017 Feb 1. PMID: 28273775; PMCID: PMC5476197): 1123-1136https://doi.org/10.1177/1352458517694432
        • Baecher-Allan C.
        • Kaskow B.J.
        • Weiner H.L.
        Multiple Sclerosis: mechanisms and Immunotherapy.
        Neuron. 2018 Feb 21; 97 (PMID: 29470968): 742-768https://doi.org/10.1016/j.neuron.2018.01.021
        • Compston A.
        • Coles A.
        Multiple sclerosis.
        Lancet. 2008 Oct 25; 372 (PMID: 18970977): 1502-1517https://doi.org/10.1016/S0140-6736(08)61620-7
      1. Ashizawa T., Xia G. Ataxia. Continuum (Minneap Minn). 2016 Aug;22(4 Movement Disorders):1208–26. doi: 10.1212/CON.0000000000000362. PMID: 27495205.

        • Mills R.J.
        • Yap L.
        • Young C.A.
        Treatment for ataxia in multiple sclerosis.
        Cochrane Database Syst. Rev. 2007 Jan 24; (PMID: 17253537)CD005029https://doi.org/10.1002/14651858.CD005029.pub2
        • Luo L.
        • Wang J.
        • Lo R.Y.
        • Figueroa K.P.
        • Pulst S.M.
        • Kuo P.H.
        • Perlman S.
        • Wilmot G.
        • Gomez C.M.
        • Schmahmann J.
        • Paulson H.
        • Shakkottai V.G.
        • Ying S.H.
        • Zesiewicz T.
        • Bushara K.
        • Geschwind M.
        • Xia G.
        • Subramony S.H.
        • Ashizawa T.
        • Kuo S.H.
        The Initial Symptom and Motor Progression in Spinocerebellar Ataxias.
        Cerebellum. 2017 Jun; 16 (PMID: 27848087): 615-622https://doi.org/10.1007/s12311-016-0836-3
        • Buckley E.
        • Mazzà C.
        • McNeill A.
        A systematic review of the gait characteristics associated with Cerebellar Ataxia.
        Gait Posture. 2018 Feb; 60 (Epub 2017 Dec 1. PMID: 29220753): 154-163https://doi.org/10.1016/j.gaitpost.2017.11.024
        • Matsushima A.
        • Yoshida K.
        • Genno H.
        • Ikeda S.I.
        Principal component analysis for ataxic gait using a triaxial accelerometer.
        J. Neuroeng. Rehabil. 2017 May 2; 14 (PMID: 28464831): 37https://doi.org/10.1186/s12984-017-0249-7
        • Terayama K.
        • Sakakibara R.
        • Ogawa A.
        Wearable gait sensors to measure ataxia due to spinocerebellar degeneration.
        Neurol. Clin. Neurosci. 2018; 6: 9-12
        • Givon U.
        • Zeilig G.
        • Achiron A.
        Gait analysis in multiple sclerosis: characterization of temporal-spatial parameters using GAITRite functional ambulation system.
        Gait Posture. 2009 Jan; 29 (Epub 2008 Oct 31. PMID: 18951800): 138-142https://doi.org/10.1016/j.gaitpost.2008.07.011
        • Comber L.
        • Galvin R.
        • Coote S.
        Gait deficits in people with multiple sclerosis: a systematic review and meta-analysis.
        Gait Posture. 2017 Jan; 51 (Epub 2016 Sep 26. PMID: 27693958): 25-35https://doi.org/10.1016/j.gaitpost.2016.09.026
        • Marquer A.
        • Barbieri G.
        • Pérennou D.
        The assessment and treatment of postural disorders in cerebellar ataxia: a systematic review.
        Ann. Phys. Rehabil. Med. 2014 Mar; 57 (Epub 2014 Feb 6. PMID: 24582474): 67-78https://doi.org/10.1016/j.rehab.2014.01.002
        • Bürk K.
        • Schulz S.R.
        • Schulz J.B.
        Monitoring progression in Friedreich ataxia (FRDA): the use of clinical scales.
        J. Neurochem. 2013 Aug; 126 (PMID: 23859347): 118-124https://doi.org/10.1111/jnc.12318
        • Schniepp R.
        • Schlick C.
        • Pradhan C.
        • Dieterich M.
        • Brandt T.
        • Jahn K.
        • Wuehr M.
        The interrelationship between disease severity, dynamic stability, and falls in cerebellar ataxia.
        J. Neurol. 2016 Jul; 263 (Epub 2016 May 9. PMID: 27159995): 1409-1417https://doi.org/10.1007/s00415-016-8142-z
        • Socie M.J.
        • Sosnoff J.J.
        Gait variability and multiple sclerosis.
        Mult Scler Int. 2013; (2013Epub 2013 Mar 3. PMID: 23533759)645197https://doi.org/10.1155/2013/645197
        • LeMoyne R.
        • Heerinckx F.
        • Aranca T.
        • De Jager R.
        • Zesiewicz T.
        • Saal H.J.
        Wearable body and wireless inertial sensors for machine learning classification of gait for people with Friedreich's ataxia.
        in: 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN). 2016 Jun: 147-151
        • Phan D.
        • Nguyen N.
        • Pathiran P.N.
        • Horne M.
        • Power L.
        • Szmulewicz D.
        A random forest approach for quantifying gait ataxia with truncal and peripheral measurements using multiple wearable sensors.
        IEEE Sens. J. 2019; 20: 723-734
        • Prochazka A.
        • Dostal O.
        • Cejnar P.
        • Mohamed H.I.
        • Pavelek Z.
        • Valis M.
        • Vysata O.
        Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring.
        IEEE Trans. Neural Syst. Rehabil. Eng. 2021; 29 (Epub 2021 Mar 2. PMID: 33434133): 360-367https://doi.org/10.1109/TNSRE.2021.3051093
        • Dostal O.
        • Tupa O.
        • Prochazka A.
        • Vysata O.
        • Pazdera L.
        • Valis M.
        The Best Motion Sensor Localization For Ataxic Gait Assessment (1924).
        Neurol. 2020; 94
        • Ramachandra P.
        • Maiya A.G.
        • Kumar P.
        Test-retest reliability of the Win-Track platform in analyzing the gait parameters and plantar pressures during barefoot walking in healthy adults.
        Foot Ankle Spec. 2012 Oct; 5 (Epub 2012 Sep 5. PMID: 22956663): 306-312https://doi.org/10.1177/1938640012457680
      2. Tan M., Le Q.V. (2020). Efficientnet: rethinking model scaling for convolutional neural networks. arXiv 2019. arXiv preprint arXiv:1905.11946.

        • Krizhevsky A.
        • Sutskever I.
        • Hinton G.E.
        ImageNet Classification with Deep Convolutional Neural Networks.
        Adv. Neural Inf. Process. Syst. 2012; 25: 1097-1105
        • Siuly S.
        • Li Y.
        • Zhang Y.
        EEG signal analysis and classification.
        IEEE Trans. Neural Syst. Rehabil. Eng. 2016; 11: 141-144https://doi.org/10.1007/978-3-319-47653-7
        • Pan S.J.
        • Yang Q
        A survey on transfer learning.
        IEEE Trans. Knowl. Data Eng. 2009; 22 (2009https://keras.io/api/applications/Accessed: 18.03.2021): 1345-1359
      3. Simonyan K., Zisserman A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

      4. Zagoruyko, Sergey, and Nikos Komodakis. "Wide residual networks." arXiv preprint arXiv:1605.07146 (2016), Narsi Reddy Comparison of Deep Learning Models for Biometric-based Mobile User Authentication).

      5. Huang G., Liu Z., van der Maaten, L., Weinberge K.Q. (2017). Densely Connected Convolutional Networks. 10.1109/CVPR.2017.243.

      6. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. (2017). Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.

        • Zoph B.
        • Vasudevan V.
        • Shlens J.
        • Le Q.V.
        Learning transferable architectures for scalable image recognition.
        in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 8697-8710
        • Vapnik V.
        The support vector method of function estimation.
        In Nonlinear Modeling. Springer, Boston, MA1998: 55-85
        • Daş B.
        • Toraman S.
        • Türkoğlu İ.
        A novel genome analysis method with the entropy-based numerical technique using pretrained convolutional neural networks.
        Turk. J. Elec. Eng. Comp. Sci. 2020; 28: 1932-1948https://doi.org/10.3906/elk-1909-119
        • He C.
        • Ma M.
        • Wang P.
        Extract Interpretability-Accuracy balanced Rules from Artificial Neural Networks: a Review.
        Neurocomputing. 2020; 387: 346-358https://doi.org/10.1016/j.neucom.2020.01.036
        • Arslan T.S.
        • Alkan A.
        A decision support system for detection of the renal cell cancer in the kidney.
        Measurement. 2018; 123: 298-303https://doi.org/10.1016/j.measurement.2018.04.002
        • Dursun Ö.O.
        • Toraman S.
        • Türkoğlu A.
        Comparison Of The Classification Performances Of Criminal Tendencies Of Schizophrenic Patients By Artificial Neural Networks And Support Vector Machine.
        Eur. J. Tech. 2017; 7: 177-185
        • Noseworthy J.H.
        • Vandervoort M.K.
        • Wong C.J.
        • Ebers G.C.
        Interrater variability with the Expanded Disability Status Scale (EDSS) and Functional Systems (FS) in a multiple sclerosis clinical trial. The Canadian Cooperation MS Study Group.
        Neurology. 1990 Jun; 40 (PMID: 2189084): 971-975https://doi.org/10.1212/wnl.40.6.971
        • Jin L.
        • Lv W.
        • Han G.
        • Ni L.
        • Sun D.
        • Hu X.
        • Cai H.
        Gait characteristics and clinical relevance of hereditary spinocerebellar ataxia on deep learning.
        Artif. Intell. Med. 2020 Mar; 103 (Epub 2020 Jan 7. PMID: 32143799)101794https://doi.org/10.1016/j.artmed.2020.101794
        • Pradhan C.
        • Wuehr M.
        • Akrami F.
        • Neuhaeusser M.
        • Huth S.
        • Brandt T.
        • Jahn K.
        • Schniepp R.
        Automated classification of neurological disorders of gait using spatio-temporal gait parameters.
        J. Electromyogr. Kinesiol. 2015 Apr; 25 (Epub 2015 Feb 7. PMID: 25725811): 413-422https://doi.org/10.1016/j.jelekin.2015.01.004
        • Phan D.
        • Nguyen N.
        • Pathirana P.N.
        • Horne M.
        • Power L.
        • Szmulewicz D.
        A random forest approach for quantifying gait ataxia with truncal and peripheral measurements using multiple wearable sensors.
        IEEE Sens. J. 2019; 20: 723-734https://doi.org/10.1109/JSEN.2019.2943879
        • Summa S.
        • Tartarisco G.
        • Favetta M.
        • Buzachis A.
        • Romano A.
        • Bernava G.M.
        • Sancesario A.
        • Vasco G.
        • Pioggia G.
        • Petrarca M.
        • Castelli E.
        • Bertini E.
        • Schirinzi T.
        Validation of low-cost system for gait assessment in children with ataxia.
        Comput. Methods Programs Biomed. 2020 Nov; 196 (Epub 2020 Aug 15. PMID: 32846316)105705https://doi.org/10.1016/j.cmpb.2020.105705