Silicosis and Tuberculosis

Silicosis is an occupational lung disease caused by chronic exposure to silica dust, primarily affecting current and former miners. As silicosis is irreversible and can be fatal, early and timely diagnosis is crucial. While there is no specific diagnostic test for silicosis, radiological abnormalities on chest X-rays, occupational history, and physical examinations can help confirm the diagnosis.

Individuals with silica dust exposure are at an increased risk for Tuberculosis (TB): the TB incidence among silicosis patients can be significantly higher than in the general population. Moreover, some develop Silicotuberculosis, being affected by both silicosis and TB at the same time.

Routine screening for silicosis and TB is essential for those exposed to silica dust. However, challenges persist due to a shortage of medical experts to assess chest X-rays accurately.

CAD4Silicosis

Leveraging our expertise in AI-powered CAD4TB, we developed Computer-Aided Detection for Silicosis (CAD4Silicosis). This novel AI software automatically interprets chest X-ray images to detect silicosis and/or Tuberculosis, enhancing diagnostic accuracy and efficiency.

Scientific Studies

CAD4Silicosis has been assessed by academic research and shows promising results. A study in South Africa (Ehrlich, R. et al. Int. J. Environ. Res. Public Health 2022) compared the performance of CAD4TB and CAD4Silicosis against the readings of occupational medicine specialists with extensive experience in interpreting chest X-rays from a gold mining population.

The study found that both CAD4TB and CAD4Silicosis met the WHO’s Target Product Profile criteria, achieving over 90% sensitivity and over 70% specificity in detecting both silicosis and TB compared to one of the specialists. Delft’s CAD systems demonstrated an ability to accurately detect silicosis and/or TB, with a high AUC (area under the curve) of >0.85 against both expert readers and a specificity of >70% in most comparisons.

The study concludes that CAD technology has the potential to come close to human expert readers in identifying TB and silicosis among miners. This suggests a significant potential for CAD4Silicosis to enhance the accuracy and efficiency of detecting silicosis in high-risk populations.

Mode of Deployment

CAD4Silicosis is available online (cloud), offline (a mini-computer called CAD4Silicosis box), or hybrid.

The offline solution enables rapid and stable screening in settings without internet access. It is highly relevant for settings with high daily throughput, limited or no internet connectivity, or programs coping with restrained budgets for data exchange over the mobile phone network.

AI-Powered Integrated TB and Silicosis Screening

CAD4Silicosis and our CAD4TB software ca be integrated into a single “box”. These AI algorithms can detect presumptive TB, silicosis, other pulmonary abnormalities, and cardiomegaly from a single chest X-ray image.

This combined approach further increases the diagnostic value of chest radiographs in TB/Silicosis screening and supports the people-centred approach with a multi-disease impact.

Total Solution for TB & Lung Health Screening

Training, Support and Maintenance

We ensure uninterrupted operations, maximum uptime, and efficiency with a predictable total cost of ownership. Our qualified expert teams offer training, installation and reliable services & maintenance. This includes a 24/7 helpdesk with experienced engineers across time zones.

Single Point of Contact for Integrated Services

Procuring Delft’s X-ray systems and CAD software together simplifies project management with integrated training, installation, and support. Clients have a single point of contact for streamlined delivery, after-sales, and maintenance for implementation support. This will contribute to reduced total cost of ownership and enhance productivity and impact.