A model for classification of invasive fungal rhinosinusitis by computed tomography

Our purpose was to classify acute invasive fungal rhinosinusitis (AIFR) caused by Mucor versus Aspergillus species by evaluating computed tomography radiological findings. Two blinded readers retrospectively graded radiological abnormalities of the craniofacial region observed on craniofacial CT examinations obtained during initial evaluation of 38 patients with eventually pathology-proven AIFR (13:25, Mucor:Aspergillus). Binomial logistic regression was used to analyze correlation between variables and type of fungi. Score-based models were implemented for analyzing differences in laterality of findings, including the 'unilateral presence' and 'bilateral mean' models. Binary logistic regression was used, with Score as the only predictor and Group (Mucor vs Aspergillus) as the only outcome. Specificity, sensitivity, positive predictive value, negative predictive value and accuracy were determined for the evaluated models. Given the low predictive value of any single evaluated anatomical site, a 'bilateral mean' score-based model including the nasal cavity, maxillary sinuses, ethmoid air cells, sphenoid sinus and frontal sinuses yielded the highest prediction accuracy, with Mucor induced AIFR correlating with higher prevalence of bilateral findings. The odds ratio for the model while integrating the above anatomical sites was 12.3 (p<0.001). PPV, NPV, sensitivity, specificity and accuracy were 0.85, 0.82, 0.92, 0.69 and 0.84 respectively. The abnormal radiological findings on craniofacial CT scans of Mucor and Aspergillus induced AIFR could be differentiated based on laterality, with Mucor induced AIFR associated with higher prevalence of bilateral findings.