DSFNet: Dual-source and spatiotemporal-feature fusion network for bedside diagnosis of lung injuries with electrical impedance tomography

Key Points

• Bedside diagnosis of lung injuries demonstrates notable accuracy improvement with electrical impedance tomography—key applications in clinical settings.
• The study reports a 30% increase in diagnosis accuracy using the DSFNet model, highlighting its potential impact.
• Assessment using a dual-source and spatiotemporal-feature fusion approach reveals higher sensitivity and specificity for lung injury detection.
• These findings highlight the potential of advanced diagnostic algorithms in enhancing bedside clinical assessments of lung function.