Airborne asbestos fibers detection in microscope images using re-initialization free active contours

Area of Science:

• Environmental Health
• Occupational Safety
• Biomedical Engineering

Background:

• Asbestos fiber inhalation causes serious lung diseases.
• Current visual counting methods (phase contrast microscopy) lack objectivity and reproducibility.
• Automated asbestos fiber detection is needed for accurate exposure assessment.

Purpose of the Study:

• To develop an automated method for detecting carcinogenic asbestos fibers.
• To overcome limitations of manual counting, including skill requirements and poor reproducibility.
• To provide a more objective and efficient approach to atmospheric asbestos monitoring.

Main Methods:

• Proposed an automated fiber detection method using geometric active contours.
• Employed a variational formulation to keep the level set function close to the signed distance function.
• Eliminated the need for costly re-initialization procedures in the counting process.

Main Results:

• The automated method was evaluated against a ground truth of 29 manually annotated images.
• Initial results demonstrated the potential of the proposed automated detection technique.
• The method showed encouraging performance for further development in asbestos monitoring.

Conclusions:

• The developed automated method shows promise for accurate asbestos fiber detection.
• This approach can lead to more objective and reproducible measurements of airborne asbestos.
• Further development is warranted to enhance its application in occupational health and safety.