Electronic Theses and Dissertation

Pneumonia merupakan penyakit infeksi saluran pernapasan akut yang menyerang paru- paru. Penyakit ini menyebabkan peradangan pada kantong udara (alveoli) paru-paru, sehingga penderitanya mengalami sesak napas, batuk berdahak, demam, dan menggigil. Pneumonia dapat dideteksi melalui pemeriksaan chest X-ray. Pemeriksaan citra chest X- ray umumnya dilakukan oleh dokter ahli radiologi. Namun demikian, ketersediaan dokter ahli radiologi tentu saja terbatas. Oleh karena itu dibutuhkan program komputer berupa metode pembelajaran mesin (machine learning) yang secara otomatis dapat mengklasifikasi chest X-ray, sehingga membantu pemeriksaan pneumonia pada citra chest X-ray. Metode yang digunakan dalam penelitian ini yaitu metode klasifikasi hybrid Convolutional Neural Network (CNN)-Extreme Gradient Boosting (XGBoost) dan Convolutional Neural Network (CNN)-Light Gradient Boosting (LightGBM). Metode CNN merupakan metode klasifikasi dasar yang digunakan kedua metode tersebut sebelum dilanjutkan ke metode klasifikasi utama. Metode klasifikasi utama untuk masing-masing metode klasifikasi yaitu XGBoost dan LightGBM. Sebelum klasifikasi, data citra chest X- ray diproses terlebih dahulu melalui image preprocessing. Image preprocessing yang diterapkan yaitu image grayscaling, image resizing, image stretching, dan thresholding. Berdasarkan hasil pengujian metode klasifikasi CNN-XGBoost didapatkan nilai akurasi 97,60%. Sedangkan pengujian metode klasifikasi CNN-LightGBM menghasilkan nilai akurasi 97,45%.

Pneumonia is an acute respiratory infection that affects the lungs. Pneumonia causes inflammation of the air sacs (alveoli) of the lungs, so the individual who has pneumonia experiences shortness of breath, coughing up phlegm, fever, and chills. Pneumonia can be detected through chest X-ray examination. A radiologist generally performs the acquisition of chest X-ray images. However, the availability of radiologists is limited. Therefore, a computer program in the form of machine learning is needed that can automatically classify chest X-rays, thus helping to check for pneumonia on chest X-ray images. The classification method used in this study is the hybrid Convolutional Neural Network (CNN)-Extreme Gradient Boosting (XGBoost) and Convolutional Neural Network (CNN)-Light Gradient Boosting (LightGBM). CNN is the primary classification method before proceeding to the main classification. The main classification methods for each classification method are XGBoost and LightGBM. Before classification, the chest X-ray image is processed through image preprocessing. Image preprocessing applied in this study includes grayscaling, image resizing, image stretching, and thresholding. The results of testing for the CNN-XGBoost classification obtained an accuracy value of 97.60%. While the results of testing for the CNN-LightGBM classification produced an accuracy value of 97.45%.