Clasificación de imágenes de neumonía en dispositivos móviles con red neuronal cuantificada
DOI:
https://doi.org/10.33448/rsd-v9i10.8382Palabras clave:
Clasificación; Imágenes; Cuantización; Dispositivos móviles; Neumonía.Resumen
Este artículo presenta un enfoque para clasificar las imágenes de rayos X de tórax de los niños en dos clases: neumonía y normal. Usamos redes neuronales convolucionales, de redes pre-entrenadas junto con un proceso de cuantificación, utilizando el método de la plataforma TensorFlow Lite. Esto reduce los requisitos de procesamiento y el costo computacional. Los resultados mostraron una precisión de hasta 95,4% y 94,2% para MobileNetV1 y MobileNetV2, respectivamente. La aplicación móvil resultante también cuenta con una interfaz de usuario sencilla e intuitiva.
Citas
Abidin, A. Z., Deng, B., DSouza, A. M., Nagarajan, M. B., Coan, P., & Wismüller, A. (2018). Deep transfer learning for characterizing chondrocyte patterns in phase contrast X-Ray computed tomography images of the human patellar cartilage. Computers in Biology and Medicine, 95, 24-33. doi:https://doi.org/10.1016/j.compbiomed.2018.01.008
Baltruschat, I. M., Nickisch, H., Grass, M., Knopp, T., & Saalbach, A. (2018). Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification. CoRR, abs/1803.02315. Fonte: http://arxiv.org/abs/1803.02315
Bowers, A. J., & Zhou, X. (2019). Receiver operating characteristic (ROC) area under the curve (AUC): A diagnostic measure for evaluating the accuracy of predictors of education outcomes. Journal of Education for Students Placed at Risk (JESPAR), 24, 20–46.
Chen, C., Dou, Q., Chen, H., & Heng, P.-A. (2018). Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation. CoRR, abs/1806.00600. Fonte: http://arxiv.org/abs/1806.00600
Chen, X., Hu, X., Zhou, H., & Xu, N. (2017). Fxpnet: Training a deep convolutional neural network in fixed-point representation. 2017 International Joint Conference on Neural Networks (IJCNN), 2494–2501.
Choi, J., Chuang, P. I.-J., Wang, Z., Venkataramani, S., Srinivasan, V., & Gopalakrishnan, K. (2018). Bridging the accuracy gap for 2-bit quantized neural networks (QNN). arXiv preprint arXiv:1807.06964.
Dittimi, T. V., & Suen, C. Y. (2019). Mobile Phone based ensemble classification of Deep Learned Feature for Medical Image Analysis. IETE Technical Review, 1–12.
Douarre, C., Schielein, R., Frindel, C., Gerth, S., & Rousseau, D. (2018). Transfer Learning from Synthetic Data Applied to Soil–Root Segmentation in X-Ray Tomography Images. Journal of Imaging, 4. doi:10.3390/jimaging4050065
Gavai, N. R., Jakhade, Y. A., Tribhuvan, S. A., & Bhattad, R. (2017). MobileNets for flower classification using TensorFlow. 2017 International Conference on Big Data, IoT and Data Science (BID), 154–158.
He, K., Girshick, R. B., & Dollár, P. (2018). Rethinking ImageNet Pre-training. CoRR, abs/1811.08883. Fonte: http://arxiv.org/abs/1811.08883
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.
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., & Bengio, Y. (2017). Quantized neural networks: Training neural networks with low precision weights and activations. The Journal of Machine Learning Research, 18, 6869–6898.
Iorio, G., Capasso, M., Prisco, S., De Luca, G., Mancusi, C., Laganà, B., Comune, V. (2018). Lung Ultrasound Findings Undetectable by Chest Radiography in Children with Community-Acquired Pneumonia. Ultrasound in medicine & biology.
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Kalenichenko, D. (2018). Quantization and training of neural networks for efficient integer-arithmetic-only inference. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (pp. 2704–2713).
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., et al. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172, 1122–1131.
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., Zhang, K. (2018). Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell, 172, 1122 - 1131.e9. doi:https://doi.org/10.1016/j.cell.2018.02.010
Kermany, D., Zhang, K., & Goldbaum, M. (2018). Large Dataset of Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images. Mendeley Data V3. doi:http://dx.doi.org/10.17632/rscbjbr9sj.3
Khatami, A., Babaie, M., Tizhoosh, H. R., Khosravi, A., Nguyen, T., & Nahavandi, S. (2018). A sequential search-space shrinking using CNN transfer learning and a Radon projection pool for medical image retrieval. Expert Systems with Applications, 100, 224-233. doi:https://doi.org/10.1016/j.eswa.2018.01.056
Kunz, W. G., Patzig, M., Crispin, A., Stahl, R., Reiser, M. F., & Notohamiprodjo, M. (2018). The Value of Supine Chest X-Ray in the Diagnosis of Pneumonia in the Basal Lung Zones. Academic radiology.
Kurt, I. S., Unluer, E. E., Evrin, T., Katipoglu, B., & Eser, U. (2018). Urine Dipstick of Sputum for the Rapid Diagnosis of Community Acquired Pneumonia. Journal of the National Medical Association.
Malmir, B., Amini, M., & Chang, S. I. (2017). A medical decision support system for disease diagnosis under uncertainty. Expert Systems with Applications, 88, 95–108.
Manogaran, G., Varatharajan, R., & Priyan, M. K. (2018). Hybrid recommendation system for heart disease diagnosis based on multiple kernel learning with adaptive neuro-fuzzy inference system. Multimedia tools and applications, 77, 4379–4399.
Moons, B., Goetschalckx, K., Van Berckelaer, N., & Verhelst, M. (2017). Minimum energy quantized neural networks. 2017 51st Asilomar Conference on Signals, Systems, and Computers, 1921–1925.
Ramalingam, S., & Garzia, F. (10 de 2018). Facial Expression Recognition using Transfer Learning. 2018 International Carnahan Conference on Security Technology (ICCST), (pp. 1-5). doi:10.1109/CCST.2018.8585504
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510–4520.
Saraiva, A., Melo, R. T., Filipe, V., Sousa, J. V., Ferreira, N. F., & Valente, A. (2018). Mobile multirobot manipulation by image recognition.
Saraiva., A. A., Ferreira., N. M., de Sousa., L. L., Costa., N. J., Sousa., J. V., Santos., D. B., Soares., S. (2019). Classification of Images of Childhood Pneumonia using Convolutional Neural Networks. Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies. 2, 112-119. SciTePress. doi:10.5220/0007404301120119
Saraiva., A. A., Santos., D. B., Costa., N. J., Sousa., J. V., Ferreira., N. M., Valente., A., & Soares., S. (2019). Models of Learning to Classify X-ray Images for the Detection of Pneumonia using Neural Networks. Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies. 2, 76-83. SciTePress. doi:10.5220/0007346600760083
Shallu, & Mehra, R. (2018). Breast cancer histology images classification: Training from scratch or transfer learning? ICT Express, 4, 247-254. doi:https://doi.org/10.1016/j.icte.2018.10.007
Ting, K. M. (2017). Confusion Matrix. Em C. Sammut, G. I. Webb (Eds.), Encyclopedia of Machine Learning and Data Mining (pp. 260–260). Boston, MA: Springer US. doi:10.1007/978-1-4899-7687-1_50
World, O. (2016). World, Health, Organization pneumonia. Retrieved from https://www.who.int/en/news-room/fact-sheets/detail/pneumonia
Wu, L. (2019). Biomedical Image Segmentation and Object Detection Using Deep Convolutional Neural Networks. Ph.D. dissertation, figshare.
Wu, Y., Qin, X., Pan, Y., & Yuan, C. (7 de 2018). Convolution Neural Network based Transfer Learning for Classification of Flowers. 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP), (pp. 562-566). doi:10.1109/SIPROCESS.2018.8600536
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018). Learning transferable architectures for scalable image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 8697–8710.
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2020 Jose Vigno Moura Sousa; Vilson Rosa de Almeida; Aratã Andrade Saraiva; Domingos Bruno Sousa Santos; Pedro Mateus Cunha Pimentel; Luciano Lopes de Sousa
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Los autores que publican en esta revista concuerdan con los siguientes términos:
1) Los autores mantienen los derechos de autor y conceden a la revista el derecho de primera publicación, con el trabajo simultáneamente licenciado bajo la Licencia Creative Commons Attribution que permite el compartir el trabajo con reconocimiento de la autoría y publicación inicial en esta revista.
2) Los autores tienen autorización para asumir contratos adicionales por separado, para distribución no exclusiva de la versión del trabajo publicada en esta revista (por ejemplo, publicar en repositorio institucional o como capítulo de libro), con reconocimiento de autoría y publicación inicial en esta revista.
3) Los autores tienen permiso y son estimulados a publicar y distribuir su trabajo en línea (por ejemplo, en repositorios institucionales o en su página personal) a cualquier punto antes o durante el proceso editorial, ya que esto puede generar cambios productivos, así como aumentar el impacto y la cita del trabajo publicado.
