Analisis Performa Pre-Trained Model Convolutional Neural Network dalam Mendeteksi Penyakit Tuberkulosis

Penulis

Ovy Rochmawanti, Fitri Utaminingrum, Fitra A. Bachtiar

Abstrak

Tuberkulosis (TB) merupakan salah satu penyakit berbahaya yang dapat menular lewat udara dan sering menyebabkan kematian apabila tidak cepat ditangani. Penyakit TB bisa disembuhkan dengan deteksi dini sehingga penderita dapat segera mendapatkan pengobatan yang tepat. Metode Convolutional Neural Network (CNN) digunakan untuk mendeteksi penyakit TB melalui foto rontgen dada. Penelitian ini bertujuan untuk menentukan model CNN yang mampu menghasilkan performa paling baik dalam mendeteksi penyakit TB. Pengujian dilakukan dengan menggunakan lima pre-trained model yang telah disediakan oleh Keras yaitu ResNet50, DenseNet121, MobileNet, Xception, InceptionV3, dan InceptionResNetV2. Perbedaan ukuran gambar yag digunakan pada saat pelatihan dan pengujian juga akan dianalisis pengaruhnya terhadap nilai akurasi yang dihasilkan dan waktu komputasinya. Hasil pengujian menunjukkan bahwa model DenseNet121 mampu menghasilkan nilai akurasi tertinggi dalam mendeteksi penyakit TB, yaitu 91,57%. Sedangkan model MobileNet merupakan model dengan waktu komputasi tercepat untuk semua ukuran gambar yang diuji. Semakin besar ukuran citra maka semakin tinggi nilai akurasinya, namun di sisi lain waktu komputasi juga akan semakin lama. 

 

Abstract

 

Tuberculosis (TB) is one of the dangerous disease that can be transmitted through the air and often causes death if not treated quickly. This illness can be cured with early detection, so that sufferers can immediately get the right treatment. The Convolutional Neural Network (CNN) method is used to detect TB disease through chest X-rays. This study aims to determine which CNN model is able to produce the best performance in detecting TB disease. Testing was carried out using five pre-trained models provided by Keras namely ResNet50, DenseNet121, MobileNet, Xception, InceptionV3, and InceptionResNetV2. The difference in image size used during training and testing will also be analyzed for its effect on the resulting accuracy value and its computation time. The test results showed that the DenseNet121 model was able to produce the highest accuracy value in detecting TB disease, namely 91.57%. Meanwhile, the MobileNet model is the model with the fastest computation time for all image sizes tested. The bigger the image size, the higher the accuracy value, but on the other hand the computation time will also be longer.

Teks Lengkap:

PDF

Referensi


BISWAS, B., GHOSH, S. K., BHATTACHARYYA, S., PLATOS, J., SNASEL, V., & CHAKRABARTI, A. 2020. Chest X-ray enhancement to interpret pneumonia malformation based on fuzzy soft set and Dempster–Shafer theory of evidence. Applied Soft Computing Journal, 86, 105889.

CHAN, Y. H., ZENG, Y. Z., WU, H. C., WU, M. C., & SUN, H. M. 2018. Effective pneumothorax detection for chest X-ray images using local binary pattern and support vector machine. Journal of Healthcare Engineering, 2018.

CHAVES, E., GONÇALVES, C. B., ALBERTINI, M. K., LEE, S., JEON, G., & FERNANDES, H. C. 2020. Evaluation of transfer learning of pre-trained CNNs applied to breast cancer detection on infrared images. Applied Optics, 59(17), E23.

CHOLLET, F. 2017. Xception: Deep learning with depthwise separable convolutions. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017-Janua, 1800–1807.

GOODFELLOW, I., BENGIO, Y., dan COURVILLE, A. 2016. Deep Learning. MIT Press.

HAN, J. dan KAMBER, M. 2001. Data Mining: Concepts and Techniques Tutorial. Morgan Kaufman Publisher. San Francisco.

HE, K., ZHANG, X., REN, S., & SUN, J. 2016. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-Decem, 770–778.

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.

HUANG, G., LIU, Z., VAN DER MAATEN, L., & WEINBERGER, K. Q. 2017. Densely connected convolutional networks. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017-Janua, 2261–2269.

JAEGER, S., KARARGYRIS, A., CANDEMIR, S., FOLIO, L., SIEGELMAN, J., CALLAGHAN, F., & MCDONALD, C. J. 2013. Automatic Tuberculosis Screening Using Chest Radiographs. IEEE Trans Med Imaging. 2014 Feb;33(2):233-45.

JAEGER, S., CANDEMIR, S., ANTANI, S., WÁNG, Y. J., LU, P., & THOMA, G. 2014. Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quantitative Imaging in Medicine and Surgery, 4(6), 475–477.

KAUSHAL, C., BHAT, S., KOUNDAL, D., & SINGLA, A. 2019. Recent Trends in Computer Assisted Diagnosis (CAD) System for Breast Cancer Diagnosis Using Histopathological Images. Irbm, 40(4), 211–227.

MAHMUD, K. H., ADIWIJAYA, & FARABY, S. AL. 2019. Klasifikasi Citra Multi-Kelas Menggunakan Convolutional Neural Network. E-Proceeding of Engineering, 6(1), 2127–2136.

NITHYA, A., APPATHURAI, A., VENKATADRI, N., RAMJI, D. R., & ANNA PALAGAN, C. 2020. Kidney disease detection and segmentation using artificial neural network and multi-kernel k-means clustering for ultrasound images. Measurement: Journal of the International Measurement Confederation, 149, 106952.

PEREZ, L., & WANG, J. 2017. The Effectiveness of Data Augmentation in Image Classification using Deep Learning.

PURNAMA, I. K. E., HERNANDA, A. K., RATNA, A. A. P., NURTANIO, I., HIDAYATI, A. N., PURNOMO, M. H., RACHMADI, R. F. 2019. Disease Classification based on Dermoscopic Skin Images Using Convolutional Neural Network in Teledermatology System. 2019 International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019 - Proceeding, 2019-November, 1–5.

RAJAN, P. G., & SUNDAR, C. 2019. Brain Tumor Detection and Segmentation by Intensity Adjustment. Journal of Medical Systems, 43(8), 1–13.

RAJPURKAR, P., IRVIN, J., ZHU, K., YANG, B., MEHTA, H., DUAN, T., & Ng, A. Y. 2017. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning. 3–9.

SANTOSH, K. C., VAJDA, S., ANTANI, S., & THOMA, G. R. 2016. Edge map analysis in chest X-rays for automatic pulmonary abnormality screening. International Journal of Computer Assisted Radiology and Surgery, 11(9), 1637–1646.

SANTOSO, A., & ARIYANTO, G. 2018. Implementasi Deep Learning Berbasis Keras untuk Pengenalan Wajah. Emitor: Jurnal Teknik Elektro, 18(01), 15–21.

SAVERA, T. R., SURYAWAN, W. H., & SETIAWAN, A. W. 2020. Deteksi Dini Kanker Kulit Menggunakan K-NN dan Convolutional Neural Network. Akurasi. 7(2), 373–378. Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) Vol. 7, No. 2, April 2020, hlm. 373-378.

SIMONYAN, K., & ZISSERMAN, A. 2015. Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 1–14.

SAXENA, P., MAHESHWARI, A., TAYAL, S., & MAHESHWARI, S. 2019. Predictive modeling of brain tumor: A Deep learning approach.

SZEGEDY, C., VANHOUCKE, V., IOFFE, S., SHLENS, J., & WOJNA, Z. 2016. Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-Decem, 2818–2826.

SZEGEDY, C., IOFFE, S., VANHOUCKE, V., & ALEMI, A. A. 2017. Inception-v4, inception-ResNet and the impact of residual connections on learning. 31st AAAI Conference on Artificial Intelligence, AAAI 2017, 4278–4284.

TALO, M. 2019. Convolutional Neural Networks for Multi-class Histopathology Image Classification.

VARSHNI, D., THAKRAL, K., AGARWAL, L., NIJHAWAN, R., & MITTAL, A. 2019. Pneumonia Detection Using CNN based Feature Extraction. Proceedings of 2019 3rd IEEE International Conference on Electrical, Computer and Communication Technologies, ICECCT 2019, 1–7.

WHO. 2019. Global Tuberculosis report country profile 2019. Publication, 63(10), 476.

ZHANG, C., SARGENT, I., PAN, X., GARDINER, A., HARE, J., & ATKINSON, P. M. 2018. VPRS-Based regional decision fusion of CNN and MRF classifications for very fine resolution remotely sensed images. IEEE Transactions on Geoscience and Remote Sensing, 56(8), 4507–4521.




DOI: http://dx.doi.org/10.25126/jtiik.2021844441