Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

A Good Evaluation Based on Confusion Matrix for Lung Diseases Classification Using Convolutional Neural Networks

Rektorat UDINUS 2024 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2024
Goals
Record
a88c8aa8-9a88-4057-8e6c-e58e3ca9ea36
Published
2026-10-30

Universitas Dian Nuswantoro conducted a study using Convolutional Neural Networks (CNN) for classification analysis related to the detection of lung abnormalities in chest X-ray images. The activity involved Kamila, Izza Putri Sari, Christy Atika Sari, Eko Hari Rachmawanto, and Nur Ryan Dwi Cahyo as participants from UDINUS. The study addressed the use of CNN to identify patterns through image classification and focused on three categories of lung imagery: Normal, representing no abnormalities; Pneumonia; and Tuberculosis.

The dataset consisted of 5,732 two-dimensional images with dimensions of 200 x 200 x 1. The images were divided into training data comprising 85% and testing data comprising 15%. The preprocessing process included image resizing, enhancement to increase contrast and reduce image complexity, and filtering to improve visibility and reduce noise. Following preprocessing, CNN was used to classify the chest X-ray imagery into the three specified categories.

The results showed an accuracy value of 97.79%. The study also reported a continuously high accuracy value of 100% in six trials. These findings provide insights into the detection of lung disorders and encourage further exploration in medical diagnosis. In relation to the stated goal, the activity contributes to health-related research through the analysis of chest X-ray images and the application of CNN classification. The activity represents an institutional research contribution by Universitas Dian Nuswantoro in the study of lung abnormality detection using image-based computational analysis.

Reference https://www.scopus.com/pages/publications/85199625179?origin=resultslist