Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

GLCM Feature Extraction for Tuberculosis Detection with Neural Network

Rektorat UDINUS 2022 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2022
Goals
Record
3bfe7454-d95d-4a40-bbd8-c7d145112b15
Published
2026-10-30

Universitas Dian Nuswantoro conducted an activity on automatic tuberculosis recognition using medical images. The activity involved UDINUS researchers Alfa Farah, M. Nafis; Hayyin Suristiyanti, Wiwiek; Ibad, Sholihul; Pramunendar, Ricardus Anggi; and Fajar Shidik, Guruh. The activity addressed automatic recognition in medical image processing, a field in which X-rays, CT, MRI, and other modalities provide medical pictures for diagnostic purposes.

The activity focused on tuberculosis detection as an important stage before further treatment. The source states that human interpretation of a vast array of X-ray pictures can result in detection mistakes. An automatic recognition system was therefore used to detect tuberculosis disease. The activity used a dataset with two classes. GLCM-based texture features were extracted from each class and applied to a two-layer feed-forward neural network. The resulting classification rate was 99%.

The stated scope covered texture-feature extraction from two classes and classification through a neural network. The reported finding was the classification rate produced by this process. The source does not provide further information about the dataset, image acquisition, evaluation design, or implementation setting. The activity relates to the stated goal concerning this health-related research because it addresses tuberculosis detection through automatic recognition of medical images. This evidence presents UDINUS as conducting research focused on a medical image processing approach for tuberculosis recognition.

Reference https://www.scopus.com/pages/publications/85141458253?origin=resultslist