Toward precision imaging in interstitial lung disease: advances in quantitative imaging and artificial intelligence

Area of Science:

• Pulmonary Medicine
• Radiology
• Medical Imaging

Background:

• Interstitial lung diseases (ILD) are a heterogeneous group of disorders affecting the lung parenchyma.
• Accurate diagnosis and prognostication of ILD are crucial for patient management.
• Quantitative imaging techniques and artificial intelligence (AI) offer new avenues for ILD assessment.

Purpose of the Study:

• To review recent advancements in quantitative imaging and AI applications for interstitial lung diseases (ILD).
• To explore the evolving role of AI in the diagnosis, characterization, quantification, and prognostication of fibrotic ILD.

Main Methods:

• Review of recent technical developments in quantitative imaging.
• Analysis of current AI algorithms applied to chest imaging in ILD.
• Synthesis of evidence on AI performance in ILD diagnosis, characterization, quantification, and prognostication.

Main Results:

• AI algorithms in chest imaging demonstrate improved performance over previous methods.
• AI applications show potential in enhancing ILD diagnosis, characterization, quantification, and prognostication.
• Quantitative CT and AI improve visual assessment, sensitivity, and inter-observer agreement in ILD.

Conclusions:

• Quantitative CT and AI tools show significant utility in improving ILD assessment and prognostic stratification.
• Evidence supports the integration of these technologies for a broader range of ILD.
• Routine clinical implementation of quantitative imaging and AI in ILD management is currently limited but progressing.