Abstract
Drawing-based tests are cost-effective, noninvasive screening methods, popularly employed by psychologists for the early detection and diagnosis of various neuropsychological disorders. Computerized analysis of such drawings is a complex task due to the high degree of deformations present in the responses and reliance on extensive clinical manifestations for their inferences. Traditional rule-based approaches employed in visual analysis-based systems prove insufficient to model all possible clinical deformations. Meanwhile, procedural analysis-based techniques may contradict with the standard test conduction and evaluation protocols. Leveraging on the increasing popularity of convolutional neural networks (CNNs), we propose an effective technique for modeling and classifying dysfunction indicating deformations in drawings without modifying clinical standards. Contrary to conventional sketch recognition applications where CNNs are trained to diminish intra-shape class variations, we employ deformation-specific augmentation to enhance the presence of specific deviations that are defined by clinical practitioners. The performance of our proposed technique is evaluated using Lacks’ scoring of the Bender-Gestalt test, as a case study. The results of our experimentation substantiate that our proposed approach can represent domain knowledge sufficiently without extensive heuristics and can effectively identify drawing-based biomarkers for various neuropsychological disorders.
Similar content being viewed by others
References
Mainland BJ, Shulman KI (2013) Clock drawing test. In: Larner AJ (ed) Cognitive screening instruments. Springer, New York, pp 79–109
Shin M-S, Park S-Y, Park S-R, Seol S-H, Kwon JS (2006) Clinical and empirical applications of the Rey–Osterrieth complex figure test. Nat Protoc 1(2):892–899
Bender L (1938) A visual motor gestalt test and its clinical use. Research monographs. American Orthopsychiatric Association, Chicago
Coates DR, Wagemans J, Sayim B (2017) Diagnosing the periphery: using the Rey–Osterrieth complex figure drawing test to characterize peripheral visual function. i-Perception 8(3):1–20
Price CC, Cunningham H, Coronado N, Freedland A, Cosentino S, Penney DL, Penisi A, Bowers D, Okun MS, Libon DJ (2011) Clock drawing in the montreal cognitive assessment: recommendations for dementia assessment. Dement Geriatr Cogn Disord 31(3):179–187
Moetesum M, Siddiqi I, Masroor U, Djeddi C (2015) Automated scoring of bender gestalt test using image analysis techniques. In: 13th international conference on document analysis and recognition (ICDAR). IEEE, pp 666–670
Lipsman N, Schwartz ML, Huang Y, Lee L, Sankar T, Chapman M, Hynynen K, Lozano AM (2013) MR-guided focused ultrasound thalamotomy for essential tremor: a proof-of-concept study. Lancet Neurol 12(5):462–468
Drotár P, Mekyska J, Rektorová I, Masarová L, Smékal Z, Faundez-Zanuy M (2015) Decision support framework for Parkinson’s disease based on novel handwriting markers. IEEE Trans Neural Syst Rehabil Eng 23(3):508–516
Moetesum M, Siddiqi I, Vincent N, Cloppet F (2018) Assessing visual attributes of handwriting for prediction of neurological disorders—a case study on Parkinson’s disease. Pattern Recognit Lett 121:19–27
Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L (1989) Handwritten digit recognition with a back-propagation network. In: Neural information processing systems (NIPS)
Yann Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Battiato S, Farinella GM, Giudice O, Puglisi G (2016) Aligning shapes for symbol classification and retrieval. Multimed Tools Appl 75:5513–5531
Plamondon R, Srihari SN (2000) Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63–84
Khalid PI, Yunus J, Adnan R (2010) Extraction of dynamic features from hand drawn data for the identification of children with handwriting difficulty. Res Dev Disabil 31(1):256–262
Rosenblum S, Samuel M, Zlotnik S, Erikh I, Schlesinger I (2013) Handwriting as an objective tool for Parkinson’s disease diagnosis. J Neurol 260(9):2357–2361
Likforman-Sulem L, Esposito A, Faundez-Zanuy M, Clémençon S, Cordasco G (2017) EMOTHAW: a novel database for emotional state recognition from handwriting and drawing. IEEE Trans Hum Mach Syst 47(2):273–284
Naseer A, Rani M, Naz S, Razzak MI, Imran M, Xu G (2019) Refining Parkinson’s neurological disorder identification through deep transfer learning. Neural Comput Appl. https://doi.org/10.1007/s00521-019-04069-0
Fairhurst MC, Linnell T, Glenat S, Guest R, Heutte L, Paquet T (2008) Developing a generic approach to online automated analysis of writing and drawing tests in clinical patient profiling. Behav Res Methods 40(1):290–303
Smith SL, Hiller DL (1996) Image analysis of neuropsychological test responses. In: Medical imaging 1996: image processing. International Society for Optics and Photonics, vol 2710, pp 904–916
Canham R, Smith S, Tyrrell A (2000) Automated scoring of a neuropsychological test: the Rey–Osterrieth complex figure. In: Proceedings of the 26th Euromicro conference. IEEE, vol 2, pp 406–413
Canham R, Smith S, Tyrrell A (2005) Location of structural sections from within a highly distorted complex line drawing. IEE Proc Vis Image Signal Process 152(6):741–749
Bennasar M, Setchi R, Hicks Y, Bayer A (2014) Cascade classification for diagnosing dementia. In: IEEE international conference on systems, man and cybernetics (SMC). IEEE, pp 2535–2540
Harbi Z, Hicks Y, Setchi R (2016) Clock drawing test digit recognition using static and dynamic features. Procedia Comput Sci 96:1221–1230
Harbi Z, Hicks Y, Setchi R (2017) Clock drawing test interpretation system. Procedia Comput Sci 112:1641–1650
Pullman SL (1998) Spiral analysis: a new technique for measuring tremor with a digitizing tablet. Mov Disord 13(S3):85–89
Pereira CR, Pereira DR, da Silva FA, Hook C, Weber SA, Pereira LA, Papa JP (2015) A step towards the automated diagnosis of parkinson’s disease: analyzing handwriting movements. In: IEEE 28th international symposium on computer-based medical systems (CBMS). IEEE, pp 171–176
Lacks P (1999) Bender Gestalt screening for brain dysfunction. Wiley, New York
Glenat S, Heutte L, Paquet T, Guest R, Fairhurst M, Linnell T (2008) The development of a computer-assisted tool for the assessment of neuropsychological drawing tasks. Int J Inf Technol Decis Mak 7(04):751–767
Song Y, Davis R, Ma K, Penney DL (2016) Balancing appearance and context in sketch interpretation. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence. AAAI Press, pp 2625–2632
Smith SL, Cervantes BR (1998) Dynamic feature analysis of vector-based images for neuropsychological testing. In: Medical imaging 1998: physiology and function from multidimensional images. International Society for Optics and Photonics, vol 3337, pp 304–314
Garbi A, Smith SL, Heseltine D, Thomson P (1999) Automated and enhanced assessment of unilateral visual neglect. In: IET conference proceedings, pp 382–386(4)
Kornmeier J, Bach M (2005) The Necker cube—an ambiguous figure disambiguated in early visual processing. Vis Res 45(8):955–960
Smith SL, Lones MA (2009) Implicit context representation Cartesian genetic programming for the assessment of visuo-spatial ability. In: IEEE congress on evolutionary computation, pp 1072–1078
Heinik J, Werner P, Dekel T, Gurevitz I, Rosenblum S (2010) Computerized kinematic analysis of the clock drawing task in elderly people with mild major depressive disorder: an exploratory study. Int Psychogeriatr 22(3):479–488
Werner P, Rosenblum S, Bar-On G, Heinik J, Korczyn A (2006) Handwriting process variables discriminating mild Alzheimer’s disease and mild cognitive impairment. J Gerontol Ser B Psychol Sci Soc Sci 61(4):P228–P236
Hazell A, Smith SL (2008) Towards an objective assessment of alzheimer’s disease: the application of a novel evolutionary algorithm in the analysis of figure copying tasks. In: Proceedings of the 10th annual conference companion on Genetic and evolutionary computation. ACM, pp 2073–2080
Garre-Olmo J, Faúndez-Zanuy M, López-de Ipiña K, Calvó-Perxas L, Turró-Garriga O (2017) Kinematic and pressure features of handwriting and drawing: preliminary results between patients with mild cognitive impairment, Alzheimer disease and healthy controls. Curr Alzheimer Res 14(9):960–968
El Yacoubi M, Garcia-Salicetti S, Kahindo C, Rigaud A-S, Cristancho-Lacroix V (2018) From aging to early-stage Alzheimer’s: Uncovering handwriting multimodal behaviors by semi-supervised learning and sequential representation learning. Pattern Recognit 86:08
Plamondon R, O’Reilly C, Ouellet-Plamondon C (2014) Strokes against stroke—strokes for strides. Pattern Recognit 47(3):929–944
O’Reilly C, Plamondon R, Lebrun L-H (2014) Linking brain stroke risk factors to human movement features for the development of preventive tools. Front Aging Neurosci 6:150
Drotár P, Mekyska J, Rektorová I, Masarová L, Smékal Z, Faundez-Zanuy M (2013) A new modality for quantitative evaluation of parkinson’s disease: in-air movement. In: 13th IEEE international conference on bioinformatics and bioengineering (BIBE). IEEE, pp 1–4
Drotár P, Mekyska J, Rektorová I, Masarová L, Smékal Z, Faundez-Zanuy M (2014) Analysis of in-air movement in handwriting: a novel marker for Parkinson’s disease. Comput Methods Programs Biomed 117(3):405–411
Drotár P, Mekyska J, Rektorová I, Masarová L, Smékal Z, Faundez-Zanuy M (2016) Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson’s disease. Artif Intell Med 67:39–46
Pereira CR, Weber SA, Hook C, Rosa GH, Papa JP (2016) Deep learning-aided Parkinson. In: 29th SIBGRAPI conference on graphics, patterns and images (SIBGRAPI). IEEE, pp 340–346
Taleb C, Khachab M, Mokbel C, Likforman-Sulem L (2017) Feature selection for an improved Parkinson’s disease identification based on handwriting. In: 1st international workshop on Arabic script analysis and recognition (ASAR). IEEE, pp 52–56
Mucha J, Zvoncak V, Galaz Z, Faundez-Zanuy M, Mekyska J, Kiska T, Smekal Z, Brabenec L, Rektorova I, Lopez-de Ipina K (2018) Fractional derivatives of online handwriting: a new approach of parkinsonic dysgraphia analysis. In: 41st international conference on telecommunications and signal processing (TSP). IEEE, pp 1–4
Rémi C, Frélicot C, Courtellemont P (2002) Automatic analysis of the structuring of children’s drawings and writing. Pattern Recognit 35(5):1059–1069
Chindaro S, Guest R, Fairhurst M, Potter J (2004) Assessing visuo-spatial neglect through feature selection from shape drawing performance and sequence analysis. Int J Pattern Recognit Artif Intell 18(07):1253–1266
Renau-Ferrer N, Rémi C (2010) A method for visuo-spatial classification of freehand shapes freely sketched. In: 14th international conference on image processing, computer vision, & pattern recognition, p 216
Beuvens F, Vanderdonckt J (may 2012) Usigesture: An environment for integrating pen-based interaction in user interface development. In: 6th International conference on research challenges in information science (RCIS), pp 1–12
De Pandis MF, Galli M, Vimercati S, Cimolin V, De Angelis MV, Albertini G (2010) A new approach for the quantitative evaluation of the clock drawing test: preliminary results on subjects with Parkinson’s disease. Neurol Res Int 2010:283890
Galli M, Vimercati SL, Stella G, Caiazzo G, Norveti F, Onnis F, Rigoldi C, Albertini G (2011) A new approach for the quantitative evaluation of drawings in children with learning disabilities. Res Dev Disabil 32(3):1004–1010
Vimercati S, Galli M, De Pandis M, Ancillao A, Stella G, Albertini G (2012) Quantitative evaluation of graphic gesture in subjects with Parkinson’s disease and in children with learning disabilities. Gait Posture 35:S23–S24
Tabatabaey-Mashadi N, Sudirman R, Guest RM, Khalid PI (2013) An evaluation of children’s structural drawing strategies. J Teknol [Sci Eng] 61(2):27–32
Tabatabaey-Mashadi N, Sudirman R, Guest RM, Khalid PI (2015) Analyses of pupils’ polygonal shape drawing strategy with respect to handwriting performance. Pattern Anal Appl 18(3):571–586
Khalid PI, Yunus J, Adnan R, Harun M, Sudirman R, Mahmood NH (2010) The use of graphic rules in grade one to help identify children at risk of handwriting difficulties. Res Dev Disabil 31(6):1685–1693
Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 807–814
Szarvas M, Yoshizawa A, Yamamoto M, Ogata J (2005) Pedestrian detection with convolutional neural networks. In: Proceedings of the IEEE intelligent vehicles symposium. IEEE, pp 224–229
Mori K, Matsugu M, Suzuki T (2005) Face recognition using SVM fed with intermediate output of CNN for face detection. In: MVA, pp 410–413
Lauer F, Suen CY, Bloch G (2007) A trainable feature extractor for handwritten digit recognition. Pattern Recognit 40(6):1816–1824
Sheikhi S (2007) Clinical use of bender-gestalt test in brain lesions diagnosis and its comparison with magnetic resonance imaging (MRI). J Urmia Nurs Midwifery Fac 5(1):15–21
Santos AA, Jorge LM (2007) Bender test with dyslexics: comparison of two systems of punctuation. Psico-USF 12(1):13–21
Allen RA, Decker SL (2008) Utility of the bender visual-motor gestalt test second edition in the assessment of attention-deficit/hyperactivity disorder 1. Percept Motor Skills 107(3):663–675
Ferreira RB, Feil CF, Nunes MLT (2009) Bender visual-motor gestalt test in the children’s clinical assessment. Psico-USF 14(2):185–192
Keppeke L, Cintra I, Schoen TH (2013) Bender visual-motor gestalt test in adolescents: relationship between visual-motor development and the tanner stages 1. Percept Motor Skills 117(1):257–275
Koppitz EM (1964) The bender gestalt test for young children. Grune & Stratton, New York
Cavanaugh JJ (1973) Preventing reading failure: prediction, diagnosis, intervention. Pediatrics 52(1):157–158
Hutt ML, Monheit S (1985) Effectiveness of the hutt adaptation of the bender-gestalt test configuration scale in differentiating emotionally disturbed adolescents. Psychol Rep 56(2):439–443
Brannigan GG, Decker SL, Madsen DH (2004) Innovative features of the Bender–Gestalt Ii and expanded guidelines for the use of the global scoring system. Bender visual-motor Gestalt test, second edition assessment service bulletin, 1
Moetesum M, Siddiqi I, Masroor U, Vincent N, Cloppet F (2016) Segmentation and classification of offline hand drawn images for the BGT neuropsychological screening test. In: 8th international conference on digital image processing (ICDIP 2016). International Society for Optics and Photonics
Nazar H, Moetesum M, Ehsan S, Siddiqi I, Khurshid K, Vincent N, McDonald-Maier KD (2017) Classification of graphomotor impressions using convolutional neural networks—an application to automated neuropsychological screening tests. In: 14th international conference on document analysis and recognition (ICDAR)
Niu X-X, Suen CY (2012) A novel hybrid CNN-SVM classifier for recognizing handwritten digits. Pattern Recognit 45(4):1318–1325
Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):60
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 248–255
Miles TR (1997) The Bangor dyslexia test. Learning Development Aids, Wisbech
Wilkinson GS, Robertson GJ (2006) Wide range achievement test (WRAT4). Psychological Assessment Resources, Lutz, FL
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and \(<\)0.5 mb model size. arXiv preprint arXiv:1602.07360
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1–9
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2818–2826
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778
Iandola F, Moskewicz M, Karayev S, Girshick R, Darrell T, Keutzer K (2014) DenseNet: implementing efficient ConvNet descriptor pyramids. arXiv preprint arXiv:1404.1869
Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Advances in neural information processing systems, pp 3320–3328
Agrawal P, Carreira J, Malik J (2015) Learning to see by moving. In: Proceedings of the IEEE international conference on computer vision, pp 37–45
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Moetesum, M., Siddiqi, I., Ehsan, S. et al. Deformation modeling and classification using deep convolutional neural networks for computerized analysis of neuropsychological drawings. Neural Comput & Applic 32, 12909–12933 (2020). https://doi.org/10.1007/s00521-020-04735-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-04735-8