CT Based Semi-Automated Method for Pneumonia Severity in Mice
Community-acquired pneumonia is an important clinical problem, with high rates of misdiagnosis and mortality. Diagnoses are typically conducted using two-dimensional chest x-rays, which have shown to be generally time-consuming and inaccurate, so current diagnostic methods should be improved. The goal of this research was to utilize Micro-Computed Tomography (MicroCT) and image analysis software to develop a diagnostic algorithm to quantitatively assess the severity of pneumonia in mice. This method provides immediate, more precise, and more accurate diagnoses as opposed to the qualitative assessments done by radiologists at present. MicroCT provides opportunities for non-invasive radiographic endpoints for pneumonia studies. A quantitative scoring of previously obtained Computed Tomography (CT) scans of pneumonia infected and control mice lungs was developed with a semi-automated image segmentation algorithm. At the endpoint of 168 hours, each of the mice was categorized as either a) a Saline (control)-injected mouse (total=13), a Pneumonia-injected Survivor (total=11), or a Pneumonia-injected Non-survivor (total=11). The scores demonstrated that the semi-automated algorithm was better able to distinguish certain pneumonia groups than could radiologists. The three comparison tests that were performed were Saline vs. All Pneumonia Injected Mice, Pneumonia Survivors vs. Pneumonia Non-survivors, and All Survivors (both Saline & Pneumonia) vs. Pneumonia Non-survivors. In all three comparisons, the semi-automated method did a better job discerning these groups than did the radiologists, with p-values of 0.001, 0.039, and 0.001 for the semi-automated algorithm, and 0.004, 0.581, 0.058 for the radiologists, respectively. The newly developed algorithm using CT scans and imaging techniques to assess early pneumonia in this pilot study shows promise and merits further testing.