DOI:
https://doi.org/10.14483/23448393.21091Published:
2024-11-27Issue:
Vol. 29 No. 3 (2024): September-DecemberSection:
Computational IntelligenceHand Tremor Characterization from a Spatiotemporal Convolutional Representation
Caracterización del temblor de manos a partir de una representación espaciotemporal de carácter convolucional
Keywords:
Tremor, Explainability maps, Volumetric convolution, Resting tremor, Postural tremor (en).Keywords:
Temblor, Mapas de explicabilidad, Convolución volumétrica, Temblor en reposo, Temblor postural (es).Downloads
Abstract (en)
Context: Parkinson’s Disease (PD) is a neurodegenerative disorder related to dopamine deficiency that mainly entails motor conditions such as slowness of movement, postural instability, limb tremor, rigidity, and a decreased range of motion. Tremor, defined as a rhythmic and uncontrolled movement of limbs, is the most prevalent symptom in PD. In the clinical routine, tremors are assessed and quantified by observing the hands following postural and resting patterns. These configurations include voluntary muscular contractions and tremor perception reduction, which leads to noisy signals. The assessments are also subjective and depend on the expertise of professionals to determine whether the tremor is associated with PD.
Method: This work introduces a deep volumetric representation that characterizes PD tremor patterns in resting and postural recording conditions. The strategy includes a convolutional architecture that extracts spatiotemporal patterns correlated with tremor, propagated through different layers until discrimination between PD and control subjects is achieved. Moreover, a set of explainability maps is computed by backpropagating output gradients into convolutionally learned spatio-temporal maps.
Results: The method was evaluated on 80 videos (five PD patients and five control subjects), reporting an average accuracy of 92.5% and a perfect sensitivity score in the postural configuration. As for the resting scheme, the proposed method obtained an average accuracy of 90% and sensitivity of 80%.
Conclusions: This approach showed efficacy regarding the localization of tremor patterns, recovering movement information while preserving the spatial and temporal representation. The strategy allows visualizing movement patterns from explainability maps of control subjects and PD patients.
Abstract (es)
Contexto: La enfermedad de Parkinson (EP) es un trastorno neurodegenerativo relacionado con la deficiencia de dopamina que conlleva principalmente afecciones motoras como lentitud de movimientos, inestabilidad postural, temblor de las extremidades, rigidez y disminución del rango de movimiento. El temblor, definido como un movimiento rítmico e incontrolado de las extremidades, es el síntoma más prevalente de la EP. En la rutina clínica, los temblores se evalúan y cuantifican observando las manos siguiendo patrones posturales y de reposo. Estas configuraciones incluyen contracciones musculares voluntarias y reducción de la percepción del temblor, lo que conduce a señales ruidosas. Las evaluaciones también son subjetivas y dependen de la experiencia de los profesionales para determinar si el temblor está asociado a la EP.
Método: Este trabajo introduce una representación volumétrica profunda que caracteriza los patrones de temblor en la EP en condiciones de registro en reposo y posturales. La estrategia incluye una arquitectura convolucional que extrae patrones espaciotemporales correlacionados con el temblor, los cuales se propagan a través de diferentes capas hasta lograr la discriminación entre sujetos con EP y sujetos control. Además, se calcula un conjunto de mapas de explicabilidad retropropagando los gradientes de salida hacia los mapas espaciotemporales aprendidos de forma convolucional.
Resultados: El método fue evaluado en 80 videos (cinco pacientes con EP y cinco sujetos control), reportando una precisión promedio del 92.5 % y una puntuación de sensibilidad perfecta en la configuración postural. En cuanto al esquema en reposo, el método propuesto obtuvo una precisión promedio del 90 % y una sensibilidad del 80 %.
Conclusiones: Este enfoque mostró eficacia en la localización de los patrones de temblor, recuperando información de movimiento mientras preservaba la representación espacial y temporal. La estrategia permite visualizar los patrones de movimiento a partir de mapas de explicabilidad tanto de sujetos control como de pacientes con EP.
References
Z. Ou, J. Pan, S. Tang, D. Duan, D. Yu, H. Nong, and Z. Wang, "Global trends in the incidence, prevalence, and years lived with disability of parkinson's disease in 204 countries/territories from 1990 to 2019," Front. Public Health, vol. 9, p. 776847, 2021.
https://doi.org/10.3389/fpubh.2021.776847
A. Castro Toro and O. F. Buritic'a, "Parkinson's disease: Diagnostic criteria, risk factors and progression, and assessment scales clinical stage," Acta. Neurol. Colomb., vol. 30, no. 4, pp. 300-306, 2014.
J. Pasquini, G. Deuschl, A. Pecori, S. Salvadori, R. Ceravolo, and N. Pavese, "The clinical profile of tremor in parkinson's disease," Mov. Disord. Clin. Pract., vol. 10, no. 10, pp. 1496-1506, 2023. https://doi.org/10.1002/mdc3.13845
B. Kilinc, N. Cetisli-Korkmaz, L. S. Bir, A. D. Marangoz, and H. Senol, "The quality of life in individuals with parkinson's disease: Is it related to functionality and tremor severity? A cross-sectional study," Physiother. Theory. Pract., pp. 1-10, 2023.
https://doi.org/10.1080/09593985.2023.2236691
K. P. Bhatia et al., "Consensus statement on the classification of tremors from the task force on tremor of the international parkinson and movement disorder society," Mov. Disord., vol. 33, no. 1, pp. 75-87, 2018. https://doi.org/10.1002/mds.27121
L. P. S'anchez-Fern'andez, L. A. S'anchez-P'erez, P. D. Concha-G'omez, and A. Shaout, "Kinetic tremor analysis using wearable sensors and fuzzy inference systems in parkinson's disease," Biomed. Signal Process Control, vol. 84, p. 104748, 2023.
https://doi.org/10.1016/j.bspc.2023.104748
C.-H. Lin, J.-X.Wu, J.-C. Hsu, P.-Y. Chen, N.-S. Pai, and H.-Y. Lai, "Tremor class scaling for parkinson disease patients using an array x-band microwave doppler-based upper limb movement quantizer," IEEE Sens. J., vol. 21, no. 19, pp. 21 473-21 485, 2021. https://doi.org/10.1109/JSEN.2021.3103803
X. Zheng, A. Vieira, S. L. Marcos, Y. Aladro, and J. Ordieres-Mer'e, "Activity-aware essential tremor evaluation using deep learning method based on acceleration data," Parkinsonism. Relat. Disord., vol. 58, pp. 17-22, 2019. https://doi.org/10.1016/j.parkreldis.2018.08.001
S.-H. Lee, D. Lee, J. Park, J.-M. Shim, and B. Kim, "Quantification of tremor dynamics via video-based analysis," Multimed. Tools Appl., pp. 1-19, 2024. https://doi.org/10.1007/s11042-024-18438-y
M. U. Friedrich et al., "Validation and application of computer vision algorithms for video-based tremor analysis," NPJ Digit. Med., vol. 7, no. 1, p. 165, 2024. https://doi.org/10.1038/s41746-024-01153-1
H. B. Kim et al., "Wrist sensor-based tremor severity quantification in parkinson's disease using convolutional neural network," Comput. Biol. Med., vol. 95, pp. 140-146, 2018. https://doi.org/10.1016/j.compbiomed.2018.02.007
H.-Y. Wu, M. Rubinstein, E. Shih, J. Guttag, F. Durand, and W. T. Freeman, "Eulerian video magnification for revealing subtle changes in the world," ACM Trans. Graph. (Proc. SIGGRAPH 2012), vol. 31, no. 4, 2012. https://doi.org/10.1145/2185520.2335416
A. Gironell, B. Pascual-Sedano, I. Aracil, J. Mar'ın-Lahoz, J. Pagonabarraga, and J. Kulisevsky, "Tremor types in parkinson disease: a descriptive study using a new classification," Parkinson's Dis., vol. 2018, no. 1, p. 4327597, 2018. https://doi.org/10.1155/2018/4327597
E. D. Louis, "Tremor," Continuum (Minneap. Minn.), vol. 25, no. 4, pp. 959-975, 2019. https://doi.org/10.1212/CON.0000000000000748
H. Zach, "Parkinson's tremor: Effects of dopamine and cognitive load," Ph.D. dissertation, Radboud Univ., 2023.
H. Zach, M. Dirkx, B. R. Bloem, and R. C. Helmich, "The clinical evaluation of parkinson's tremor," J. Parkinson's Dis., vol. 5, no. 3, pp. 471-474, 2015. https://doi.org/10.3233/JPD-150650
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2024 Jessica Pedraza Cadena, John Edinson Archila Valderrama, Franklin Sierra-Jerez, Alejandra Moreno Tarazona, Fabio Martínez Carrillo
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
From the edition of the V23N3 of year 2018 forward, the Creative Commons License "Attribution-Non-Commercial - No Derivative Works " is changed to the following:
Attribution - Non-Commercial - Share the same: this license allows others to distribute, remix, retouch, and create from your work in a non-commercial way, as long as they give you credit and license their new creations under the same conditions.