AI Model Differentiates Fungal Infection from Tuberculosis in Chest Scans

A retrospective study from China demonstrates that a CT-based multimodal 2.5D deep learning model can effectively distinguish pulmonary Talaromyces marneffei infection from pulmonary tuberculosis in HIV/AIDS patients. The model achieved a high area under the curve (AUC) of 0.931 and specificity of 0.981, indicating strong diagnostic performance. This development could improve diagnostic accuracy for these infections in vulnerable populations.

Originally published by gnews