Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Simplification of Mycobacterium Tuberculosis Segmenting Algorithm in Sputum Images Based of Auto-Thresholding

Rektorat UDINUS 2021 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2021
Goals
Record
98e4bbbd-adbb-4a6f-9853-c7a71049e1ac
Published
2026-10-30

Universitas Dian Nuswantoro conducted an activity in medical image analysis concerning the segmentation of Mycobacterium tuberculosis in sputum images. The activity involved Wulandari, Sari Ayu; Mayasari, Dita Ayu; Kurniatie, Menik Dwi; and Tjahyono, Rudi as participants. The activity addressed image segmentation as a critical task in medical image analysis, particularly for calculating the number of bacteria from images of acid-fast bacilli smears.

The activity focused on a serious problem in segmentation algorithms studied in sputum culture, namely determining the number of bacteria. UDINUS used an automatic algorithm for detecting Mycobacterium tuberculosis from images of acid-fast bacilli smears. The method applied was auto-thresholding segmentation. Based on the source, this method was intended to minimize calculation errors during bacterial counting. The source also describes the method as simple, fast, and effective for bacterial counting.

The activity therefore relates to the stated goal through health-focused research addressing bacterial detection and counting in medical images. Its scope was limited to the automatic detection and counting context described in the source, without further information about the implementation setting, sample size, evaluation design, or institutional partners. This activity represents UDINUS's engagement in health research through the development and description of an image-segmentation approach for Mycobacterium tuberculosis detection.

Reference https://www.scopus.com/pages/publications/85118945415?origin=resultslist