Pemodelan Klasifikasi Tuberkulosis dengan Convolutional Neural Network

Windha Hardjanto Achmad, Nia Saurina, Nur Chamidah, Riries Rulaningtyas

Abstract


Tuberculosis is an airborne disease caused by a bacterium known as mycobacterium tuberculosis which is a rod-shaped microbe with a length ranging from 1-10 m. This research was conducted to create a tuberculosis (tb) image classification model using a convolutional neural network. The classification model in this study aims to classify or group positive tb images and negative tb images. The data in this study were obtained from the gdc of the clinical pathology installation totaling 356 units. Adam optimizer is used to improve the accuracy of the model that has been made. Adam optimizer is an adaptive learning optimization. The model in this study has been implemented into test data with an accuracy rate of 88%. Positive tb images are classified correctly as many as 38 data and there are 5 errors, for negative tb images, the model is able to classify 37 data correctly and 6 errors.


Keywords


Tuberculosis; adam optimizer; convolutional neural network

Full Text:

PDF

References


Abdullahi Umar Ibrahim, Emrah Guler, Meryem Guvenir, Kaya Suer, Sertan Serte, Mehmet Ozsoz. 2021. Automated detection of Mycobacterium tuberculosis using transfer learning. The Journal of Infection in Developing Countries.

WHO.World Health Organization Global Tuberculosis Report 2020. 2020. Available online: http://apps.who.int/iris (Diakses terakhir pada tanggal 06 Januari 2023).

Melendez, J.; Sánchez, C.I.; Philipsen, R.H.H.M.; Maduskar, P.; Dawson, R.; Theron, G.; Dheda, K.; Van Ginneken, B. 2016. An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information. Science Report.

M. Nur et al., “Evaluation of Novel Integrated Dielectric Barrier Discharge Plasma as Ozone Generator,” Bull. Chem. React. Eng. Catal., vol. 12, no. 1, p. 24, Apr. 2017.

A. Yahiaoui, O. Er, and N. Yumusak, “A new method of automatic recognition for tuberculosis disease diagnosis using support vector machines,” Biomed. Res., vol. 28, no. 9, pp. 4208-4212, 2017.

I. Hammen, “Respiratory Medicine Case Reports Tuberculosis mimicking lung cancer,” Respir. Med. Case Reports, vol. 16, pp. 45-47, 2015.

J. Melendez, C. I. Sánchez, R. H. H. M. Philipsen, P. Maduskar, R. Dawson, G. Theron, K. Dheda, B. Ginneken, “An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information,” Sci. Rep., October 2015, pp. 1-8, 2016.

Nada Hussain Ali, Matheel E. Abdulmunim, Akbas Ezaldeen Ali. 2021. Constructed model for micro-content recognition in lip reading based deep learning. Bulletin of Electrical Engineering and Informatics

F.-F. Li, J. Johnson dan S. Yeung, Class Lecture, Topic: “CS231n Convolutional Neural Networks for Visual Recognition,” College of Computer Science, Stanford University, Stanford, 2019.

Ovy Rochmawanti, Fitri Utaminingrum, Fitra A. Bachtiar. 2021. Analisis Performa Pre-Trained Model Convolutional Neural Network Dalam Mendeteksi Penyakit Tuberkulosis. Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK).

A. Saravia, N. M. Fonseca, L. Sousa, N. J. Costa, J. V. Sousa, D. B. Santos, S. Soares and A. Valente, "Classification of Images of Childhood Pneumonia using Convolutional NeuralNetworks," in 12th International Joint Conference on Biomedical Engineering Systems and Technologies, Prague, 2019.

Chang Liu, Yu Cao, Marlon Alcantara, Benyuan Liu, Maria Brunette, Jesus Peinadoy, Walter Curios. 2019. TX-CNN: Detecting Tuberculosis In Chest X-Ray Images Using Convolutional Neural Network. International Conference on Image Processing.

Akosua Adom Agyeman, Richard Ofori-Asenso. 2017. Tuberculosis—an overview. Journal of Public Health and Emergency.

Rasouli MR, Mirkoohi M, Vaccaro AR, et al. 2012. Spinal tuberculosis: diagnosis and management. Asian Spine Journal.

Roman Belavkin, Panos Pardalos, Jose Principe. 2022. Value of Information in the Binary Case and Confusion Matrix. MDPI Journal.

S.Ruder, 2016. An overview of gradient descent optimization algorithms, https://arxiv.org/abs/1609.04747.

T. Dozat, 2016. Incorporating nesterov momentum into adam, Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico.

J. Zhang and F. B. Gouza, 2018. GADAM: Genetic-evolutionary adam for deep neural network optimization. https://arxiv.org/abs/1805.07500.

S. J. Reddi, S. Kale, and S. Kumar, 2019. On the convergence of adam and beyond. https://arxiv.org/abs/1904.09237.

N. Shazeer and M. Stern, 2018. Adafactor: Adaptive learning rates with sublinear memory cost. Proceedings of the International Conference on Machine Learning ICML, pp. 4596–4604, Stockholm, Sweden.

M. Zaheer, S. J. Reddi, and D. S. Sachan. 2018. Adaptive methods for nonconvex optimization. Proceedings of the Neural Information Processing Systems, Curran Associates, Inc, Montreal, Canada.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Windha Hardjanto Achmad

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.