Image enhancement variational methods for enabling strong cost reduction in OLED-based point-of-care...

Area of Science:

• Biomedical Engineering
• Medical Diagnostics
• Image Processing

Background:

• Immunofluorescence diagnostic systems often rely on expensive CCD cameras.
• High costs limit the accessibility of advanced diagnostic tools.

Purpose of the Study:

• To investigate the use of low-cost CMOS sensors for point-of-care immunofluorescence Dengue virus diagnostics.
• To develop and validate a novel software pipeline for image enhancement and automated diagnosis.
• To assess the cost-effectiveness and diagnostic accuracy compared to traditional CCD systems.

Main Methods:

• A 2-phase postprocessing software pipeline involving joint super-resolution and segmentation.
• A novel variational coupled model and an innovative automatic image analysis for diagnosis.
• Implementation on a prototype CMOS camera system with a low-cost OLED light source.

Main Results:

• The CMOS system achieved up to 99% cost reduction compared to CCD systems.
• The developed software pipeline enabled accurate detection and discrimination of 4 Dengue virus serotypes.
• Diagnostic accuracy was acceptable, with results confirmed by RT-PCR and ELISA.

Conclusions:

• Low-cost CMOS sensors coupled with advanced image processing offer a viable alternative for immunofluorescence diagnostics.
• This approach significantly reduces the cost of Dengue virus serotyping, improving accessibility.
• The automated system provides reliable detection and discrimination of Dengue serotypes at the point-of-care.