Work

Image processing techniques for identifying Mycobacterium tuberculosis in Ziehl-Neelsen stains.

Year: 2008

Type: article

Abstract: Worldwide, laboratory technicians tediously read sputum smears for tuberculosis (TB) diagnosis. We demonstrate proof of principle of an innovative computational algorithm that successfully recognizes Ziehl-Neelsen (ZN) stained acid-fast bacilli (AFB) in digital images. Automated, multi-stage, color-based Bayesian segmentation identified possible 'TB objects', removed artifacts by shape comparison and color-labeled objects as 'definite', 'possible' or 'non-TB', bypassing photomicrographic calibration. Superimposed AFB clusters, extreme stain variation and low depth of field were challenges. Our novel method facilitates electronic diagnosis of TB, permitting wider application in developing countries where fluorescent microscopy is currently inaccessible and unaffordable. We plan refinement and validation in the future.

Source: PubMed

Authors: P Sadaphal, J Rao, G W Comstock, M F Beg

Institution: Johns Hopkins University

Language: English

Topic: Image Processing Techniques and Applications

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: green

Funder: Fogarty International Center

Award: Fogarty AIDS International Training and Research Program (AITRP)