Document Type : Original/Review Paper
Author
Department of Biomedical Engineering, Meybod University, Meybod, Iran.
Abstract
Traditional Down syndrome identification often relies on professionals visually recognizing facial features, a method that can be subjective and inconsistent. This study introduces a hybrid deep learning (DL) model for automatically identifying Down syndrome in children's facial images, utilizing facial analysis techniques to enhance diagnostic accuracy and enable real-time detection. The model employs the MobileNetV2 architecture to address dataset bias and diversity issues while ensuring efficient feature extraction. The framework also integrates the structure with optimized Bidirectional Long Short-Term Memory (BiLSTM) to enhance feature classification. Trained and validated on facial images from children with Down syndrome and healthy controls from the Kaggle dataset, the model achieved 97.60% accuracy and 97.50% recall. The approach also integrates cloud and edge processing for efficient real-time analysis, offering adaptability to new images and conditions.
Keywords
Main Subjects
[1] M. E. Weijerman and J. P. de Winter, "The care of children with Down syndrome," Eur J Pediatr, vol. 169, pp. 1445–1452, 2010.
[2] P. Kruszka, A. R. Porras, A. K. Sobering, F. A. Ikolo, S. La Qua, V. Shotelersuk, B. H. Chung, G. T. Mok, A. Uwineza, L. Mutesa, et al., "Down syndrome in diverse populations," Am J Med Genet A, vol. 173, pp. 42–53, 2017.
[3] N. J. Roizen and D. Patterson, "Down’s syndrome," Lancet, vol. 361, pp. 1281–1289, 2003.
[4] Q. Zhao, K. Rosenbaum, R. Sze, D. Zand, M. Summar, and M. G. Linguraru, "Down syndrome detection from facial photographs using machine learning techniques," in Medical Imaging 2013: Computer-Aided Diagnosis, vol. 8670, pp. 9–15, SPIE, Feb. 28, 2013.
[5] B. Qin, et al., "Automatic identification of down syndrome using facial images with deep convolutional neural network," Diagnostics, vol. 10, no. 7, p. 487, Jul. 17, 2020.
[6] V. Dima, A. Ignat, and C. Rusu, "Identifying down syndrome cases by combined use of face recognition methods," in Soft Computing Applications: Proceedings of the 7th International Workshop Soft Computing Applications (SOFA 2016), vol. 2, pp. 472–482, Springer International Publishing, 2018.
[7] E. H. Pooch, T. A. Alva, and C. D. Becker, "A computational tool for automated detection of genetic syndrome using facial images," in Intelligent Systems: 9th Brazilian Conference, BRACIS 2020, Rio Grande, Brazil, Oct. 20–23, 2020, Proceedings, Part I, pp. 361–370, Springer International Publishing, 2020.
[8] B. Jin, L. Cruz, and N. Gonçalves, "Deep facial diagnosis: Deep transfer learning from face recognition to facial diagnosis," IEEE Access, vol. 8, pp. 123649–123661, Jun. 29, 2020.
[9] D. Shen, G. Wu, and H. I. Suk, "Deep learning in medical image analysis," Annual Review of Biomedical Engineering, vol. 19, no. 1, pp. 221–248, Jun. 21, 2017.
[10] R. Zaitoon and H. Syed, "RU-Net2+: A deep learning algorithm for accurate brain tumor segmentation and survival rate prediction," IEEE Access, Oct. 17, 2023.
[11] Q. Hennocq, et al., "An automatic facial landmarking for children with rare diseases," American Journal of Medical Genetics Part A, vol. 191, no. 5, pp. 1210–1221, May 2023.
[12] N. Paredes, E. Caicedo-Bravo, and B. Bacca, "Emotion recognition in individuals with down syndrome: A convolutional neural network-based algorithm proposal," Symmetry, vol. 15, no. 7, p. 1435, Jul. 17, 2023.
[13] H. Liu, et al., "Automatic facial recognition of Williams-Beuren syndrome based on deep convolutional neural networks," Frontiers in Pediatrics, vol. 9, p. 648255, May 19, 2021.
[14] X. Kong, Y. Yao, C. Wang, Y. Wang, J. Teng, and X. Qi, "Automatic identification of depression using facial images with deep convolutional neural network," Medical Science Monitor, vol. 28, e936409-1, 2022.
[15] Z. Pan, et al., "Clinical application of an automatic facial recognition system based on deep learning for diagnosis of Turner syndrome," Endocrine, vol. 72, pp. 865–873, Jun. 2021.
[16] M. Tavakolian and A. Hadid, "A spatiotemporal convolutional neural network for automatic pain intensity estimation from facial dynamics," International Journal of Computer Vision, vol. 127, pp. 1413–1425, Oct. 2019.
[17] A. Mittal, H. Gaur, and M. Mishra, "Detection of down syndrome using deep facial recognition," in Proceedings of 3rd International Conference on Computer Vision and Image Processing: CVIP 2018, vol. 1, pp. 119–130, Springer Singapore, 2020.
[18] S. S. Mahdi, et al., "Multi-scale part-based syndrome classification of 3D facial images," IEEE Access, vol. 10, pp. 23450–23462, Feb. 22, 2022.
[19] A. R. Porras, et al., "Development and evaluation of a machine learning-based point-of-care screening tool for genetic syndromes in children: A multinational retrospective study," Lancet Digital Health, vol. 3, no. 10, pp. e635–e643, Oct. 1, 2021.
[20] E. Setyati, S. Az, S. P. Hudiono, and F. Kurniawan, "CNN-based face recognition system for patients with down and William syndrome," Knowledge Engineering and Data Science, vol. 4, no. 2, pp. 138–144, 2021.
[21] H. Yang, et al., "Automated facial recognition for Noonan syndrome using novel deep convolutional neural network with additive angular margin loss," Frontiers in Genetics, vol. 12, p. 669841, Jun. 7, 2021.
[22] Y. Gurovich, et al., "Identifying facial phenotypes of genetic disorders using deep learning," Nature Medicine, vol. 25, no. 1, pp. 60–64, Jan. 2019.
[23] J. T. Pantel, et al., "Efficiency of computer-aided facial phenotyping (DeepGestalt) in individuals with and without a genetic syndrome: Diagnostic accuracy study," Journal of Medical Internet Research, vol. 22, no. 10, e19263, Oct. 22, 2020.
[24] T. C. Hsieh and P. M. Krawitz, "Computational facial analysis for rare Mendelian disorders," American Journal of Medical Genetics Part C: Seminars in Medical Genetics, vol. 193, no. 3, p. e32061, Hoboken, USA: John Wiley & Sons, Inc., Sep. 2023.
[25] Kaggle Dataset. Available: https://www.kaggle.com/datasets/mervecayli/detection-of-down-syndrome-in-children.
[26] Y. S. Ting, Y. F. Teng, and T. D. Chiueh, "Batch normalization processor design for convolution neural network training and inference," in 2021 IEEE International Symposium on Circuits and Systems (ISCAS), May 22, 2021, pp. 1–4.
[27] P. Thanapol, K. Lavangnananda, P. Bouvry, F. Pinel, and F. Leprévost, "Reducing overfitting and improving generalization in training convolutional neural network (CNN) under limited sample sizes in image recognition," in 2020 5th International Conference on Information Technology (InCIT), Oct. 21, 2020, pp. 300–305.
[28] N. Jacobsen, et al., "Analysis of intensity normalization for optimal segmentation performance of a fully convolutional neural network," Zeitschrift für Medizinische Physik, vol. 29, no. 2, pp. 128–138, May 1, 2019.
[29] G. Howard, et al, "Mobilenets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint, arXiv:1704.04861, Apr. 17, 2017.
[30] M. R. Fallahzadeh, F. Farokhi, A. Harimi, and R. Sabbaghi-Nadooshan, "Facial expression recognition based on image gradient and deep convolutional neural network," Journal of AI and Data Mining, vol. 9, no. 2, pp. 259–268, 2021.
)