Summary:
UCLA researchers in the Department of Radiology have developed an innovation algorithm that measures lung damage associated with COVID-19 using computed tomography (CT) data.
Background:
Computed tomography (CT) scans are essential in diagnosing and monitoring different types of lung damage. At present, radiologist manually inspect CT scans and provide non-standardized qualitative estimates. High resolution-computed tomography (HR-CT) scans with a quantitative aspect (QHR-CT) are being adopted to monitor the progression and recovery from respiratory diseases.
The ongoing COVID-19 pandemic demonstrated the devastating effects acute respiratory distress syndrome (ARDS) can have on patients. ARDS is a severe type of lung injury commonly seen in patients suffering from pneumonia and COVID-19. By some estimates, ARDS is responsible for up to 10% of all ICU admissions and carries a mortality rate above 30%. While QHR-CT have improved the quantitative analysis of pulmonary health, more sophisticated algorithms are needed to study and eventually predict the progression of chronically critically ill patients. There is a need for rapid and accurate technology to quantify lung capacity and damage in critical patients as well as track the recovery process.
Innovation:
UCLA researchers in the Department of Radiology, led by Dr. Grace Kim, have created a machine-learning algorithm that uses visual patterns from COVID-19 CT scans to determine the extent of lung damage caused by pulmonary disease. This innovative method includes two new markers of disease that other algorithms do not consider, resulting in a more accurate representation of pulmonary health. The invention may enable medical professionals to assess a patient’s pulmonary health quantitatively and provide more tailored remedies. It also offers a means of studying the respiratory condition of chronically critically ill patients who cannot undergo traditional respiratory tests.
Potential Applications:
• Diagnosis and monitoring of disease
• Medical teaching
• Lung CT scans
Advantages:
• Patient specific
• Machine learning
• Quantifiable tracking of disease progression and recovery
Development-To-Date:
Invention has been successfully demonstrated in two clinical studies.
Related Papers:
Dolinay, T.; Jun, D.; Maller, A.; Chung, A.; Grimes, B.; Hsu, L.; Nelson, D.; Villagas, B.; Kim, G.; Goldin, J.; Quantitative image analysis in COVID-19 acute respiratory distress syndrome: a cohort observational study. F1000 Research 10:1266 (2022). https://doi.org/10.12688/f1000research.75311.1
Reference: UCLA Case No. 2022-255
Lead Inventor: Hyun (Grace) Kim