Pleural Effusion Classification Based on Chest X-Ray Images using Convolutional Neural Network

  • Ahmad Rafiansyah Fauzan Fakultas Teknologi Komunikasi dan Informatika - Universitas Nasional
  • Mohammad Iwan Wahyuddin Fakultas Teknologi Komunikasi dan Informatika - Universitas Nasional
  • Sari Ningsih Fakultas Teknologi Komunikasi dan Informatika - Universitas Nasional
Keywords: Computer Vision, Image Classification, Convolutional Neural Network, Pleural Effusion


Pleural effusion is a respiratory infection characterized by a buildup of fluid between the two layers of pleura, which causes specific symptoms such as chest pain and shortness of breath. In Indonesia, pleural effusion cases alone account for 2.7% of other respiratory infections, with an estimated number of sufferers in general at more than 3000 people per 1 million population annually. Pleural effusion is a severe case and can cause death if not treated immediately. Based on a study, as many as 15% of 104 patients diagnosed with pleural effusion died within 30 days. In this paper, we present a model that can detect pleural effusion based on chest x-ray images automatically using a Machine Learning algorithm. The machine learning algorithm used is Convolutional Neural Network (CNN), with the dataset used from ChestX-ray14. The number of data used was 2500 in the form of x-ray images, based on two different classes, x-ray with pleural effusion and x-ray with normal condition. The evaluation result shows that the CNN model can classify data with an accuracy of 95% of the test set data; thus, we hope it can be an alternative to assist medical diagnosis in pleural effusion detection.