No abstract

Mucormycosis, commonly known as the “black fungus” is recently emerging as a deadly complication in COVID patients in the Indian subcontinent. A growing number of cases are being reported from all over the country, with a majority of the patients either undergoing treatment or having recovered from COVID. Here, we report three cases of multisystem mucormycosis in COVID positive patients showing, rhino-orbital, cerebral, pulmonary, and genitourinary involvement. The first is a case of a 41-year-old male patient who during his treatment developed left periorbital swelling with ecchymosis and headache. CT and CE-MRI of the paranasal sinuses and brain revealed features of pan fungal sinusitis and subsequent invasion into the left orbit. The second case is of a 52-year-old male patient who after complaining of a severe left-sided hemicranial headache was diagnosed with cavernous sinus thrombosis. The third is of a 57-year-old male patient who presented with left flank pain and dysuria. HRCT (High-resolution CT) chest revealed a thick-walled cavitary lesion, and NCCT KUB (Non-contrast CT of Kidneys, ureters, and bladder) revealed left-sided pyelonephritis. A cystoscopic and microbiological evaluation revealed fungal growth. In all three patients, a biopsy from the involved area revealed broad aseptate filamentous fungal hyphae suggestive of mucormycosis, which was confirmed on culture. These are all unusual cases and physicians should be aware of the possibility of secondary invasive fungal infections in patients with COVID-19 infection.

Purpose: Manual interpretation of chest radiographs is a challenging task and is prone to errors. An automated system capable of categorizing chest radiographs based on the pathologies identified could aid in the timely and efficient diagnosis of chest pathologies. Method: For this retrospective study, 4476 chest radiographs were collected between January and April 2021 from two tertiary care hospitals. Three expert radiologists established the ground truth, and all radiographs were analyzed using a deep-learning AI model to detect suspicious ROIs in the lungs, pleura, and cardiac regions. Three test readers (different from the radiologists who established the ground truth) independently reviewed all radiographs in two sessions (unaided and AI-aided mode) with a washout period of one month. Results: The model demonstrated an aggregate AUROC of 91.2% and a sensitivity of 88.4% in detecting suspicious ROIs in the lungs, pleura, and cardiac regions. These results outperform unaided human readers, who achieved an aggregate AUROC of 84.2% and sensitivity of 74.5% for the same task. When using AI, the aided readers obtained an aggregate AUROC of 87.9% and a sensitivity of 85.1%. The average time taken by the test readers to read a chest radiograph decreased by 21% (p < 0.01) when using AI. Conclusion: The model outperformed all three human readers and demonstrated high AUROC and sensitivity across two independent datasets. When compared to unaided interpretations, AI-aided interpretations were associated with significant improvements in reader performance and chest radiograph interpretation time.

No abstract