Enhancing Interstitial Lung Disease Diagnoses Through Multimodal AI Integration of Histopathological and CT Image Data.

Abstract

Background and objective: The diagnosis of interstitial lung diseases (ILDs) often relies on the integration of various clinical, radiological, and histopathological data. Achieving high diagnostic accuracy in ILDs, particularly for distinguishing usual interstitial pneumonia (UIP), is challenging and requires a multidisciplinary approach. Therefore, this study aimed to develop a multimodal artificial intelligence (AI) algorithm that combines computed tomography (CT) and histopathological images to improve the accuracy and consistency of UIP diagnosis.

Methods: A dataset of CT and pathological images from 324 patients with ILD between 2009 and 2021 was collected. The CT component of the model was trained to identify 28 different radiological features. The pathological counterpart was developed in our previous study. A total of 114 samples were selected and used for testing the multimodal AI model. The performance of the multimodal AI was assessed through comparisons with expert pathologists and general pathologists.

Results: The developed multimodal AI demonstrated a substantial improvement in distinguishing UIP from non-UIP, achieving an AUC of 0.92. When applied by general pathologists, the diagnostic agreement rate improved significantly, with a post-model κ score of 0.737 compared to 0.273 pre-model integration. Additionally, the diagnostic consensus rate with expert pulmonary pathologists increased from κ scores of 0.278-0.53 to 0.474-0.602 post-model integration. The model also increased diagnostic confidence among general pathologists.

Conclusion: Combining CT and histopathological images, the multimodal AI algorithm enhances pathologists' diagnostic accuracy, consistency, and confidence in identifying UIP, even in cases where specialised expertise is limited.