EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Kris Lami iD, Mutsumi Ozasa, Xiangqian Che, Wataru Uegami, Yoshihiro Kato, Yoshiaki Zaizen iD, Naoko Tsuyama, Ichiro Mori, Shin Ichihara, Han-Seung Yoon, Ryoko Egashira iD, Kensuke Kataoka und 14 weitere

Respirology · 2025-08 · 30 (8) · 726-735

DOI: 10.1111/resp.70036 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Respirology, online erschienen am 02.04.2025. Verfasst von Kris Lami und 25 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Artificial Intelligence, Lung Diseases, Interstitial, Lung. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: New Energy and Industrial Technology Development Organization, Ministry of Health, Labour and Welfare.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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. image

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedArtificial IntelligenceLung Diseases, InterstitialLungHumansMaleFemaleMiddle AgedAgedAlgorithms

Stichwörter der Autor:innen

CTUIPhistopathologyinterstitial lung diseasemultimodal AI

Autor:innen und Institutionen

  • Department of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan.
  • Department of Respiratory Medicine, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan.
  • Strategic AI Group, Future Corporation, Tokyo, Japan.
  • Department of Pathology, Kameda Medical Center, Kamogawa, Japan.
  • Division of Respirology, Neurology and Rheumatology, Department of Medicine, Kurume University School of Medicine, Kurume, Japan.
  • Division of Pathology, Cancer Institute, Japanese Foundation for Cancer Research, Tokyo, Japan.

ORCID-Profile: Kris Lami, Yoshiaki Zaizen, Ryoko Egashira, Alexandre Todorovic Fabro

Förderung

  • New Energy and Industrial Technology Development Organization
  • Ministry of Health, Labour and Welfare

Zitieren

APA

Lami, K., Ozasa, M., Che, X., Uegami, W., Kato, Y., Zaizen, Y., Tsuyama, N., Mori, I., Ichihara, S., Yoon, H. S., Egashira, R., Kataoka, K., Johkoh, T., Kondo, Y., Attanoos, R., Cavazza, A., Marchevsky, A. M., Schneider, F., Augustyniak, J. W., …, & Fukuoka, J. (2025). Enhancing Interstitial Lung Disease Diagnoses Through Multimodal AI Integration of Histopathological and CT Image Data. Respirology, 30(8), 726-735. https://doi.org/10.1111/resp.70036

Vancouver

Lami K, Ozasa M, Che X, Uegami W, Kato Y, Zaizen Y, et al. Enhancing Interstitial Lung Disease Diagnoses Through Multimodal AI Integration of Histopathological and CT Image Data. Respirology. 2025;30(8):726-735. doi:10.1111/resp.70036

BibTeX
@article{Lami2025,
  author = {Lami, Kris and Ozasa, Mutsumi and Che, Xiangqian and Uegami, Wataru and Kato, Yoshihiro and Zaizen, Yoshiaki and Tsuyama, Naoko and Mori, Ichiro and Ichihara, Shin and Yoon, Han-Seung and Egashira, Ryoko and Kataoka, Kensuke and Johkoh, Takeshi and Kondo, Yasuhiro and Attanoos, Richard and Cavazza, Alberto and Marchevsky, Alberto M and Schneider, Frank and Augustyniak, Jaroslaw Wojciech and Almutrafi, Amna and Fabro, Alexandre Todorovic and Brcic, Luka and Roden, Anja C and Smith, Maxwell and Moreira, Andre and Fukuoka, Junya},
  title = {Enhancing Interstitial Lung Disease Diagnoses Through Multimodal AI Integration of Histopathological and CT Image Data},
  journal = {Respirology},
  year = {2025},
  volume = {30},
  number = {8},
  pages = {726--735},
  doi = {10.1111/resp.70036}
}
Kostenlos starten →