EUVIMEDEUVIMED entdecken
Crossref

Generation of chest CT pulmonary nodule images by latent diffusion models using the LIDC-IDRI dataset

Kaito Urata, Maiko Nagao, Atsushi Teramoto, Kazuyoshi Imaizumi, Masashi Kondo, Hiroshi Fujita

International Journal of Computer Assisted Radiology and Surgery · 31.07.2026 · 21 (11) · 2295-2300

DOI: 10.1007/s11548-026-03754-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, online erschienen am 31.07.2026. Verfasst von Kaito Urata und 5 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Science and Engineering, Meijo University, 1-501 Shiogamaguchi, Tempaku-Ku, Nagoya City, Aichi, 468-8502, Japan. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Lung Neoplasms, Solitary Pulmonary Nodule, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit nennt 19 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Lung cancer is the leading cause of cancer-related deaths. Recently, computer-aided diagnosis (CAD) systems have been developed to support diagnosis, but their performance depends heavily on the quality and quantity of training data. However, in clinical practice, it is difficult to collect a large amount of CT images for specific cases, such as small-cell carcinoma with low epidemiological incidence or benign tumors that are difficult to distinguish from malignant ones. This leads to the challenge of data imbalance. In this study, we propose a method to automatically generate chest CT nodule images that capture target features using latent diffusion models (LDM), and verify its effectiveness.

Methods

Using the LIDC-IDRI dataset, we created pairs of nodule images and findings based on physician evaluations. For the image-generation models, we used Stable Diffusion version 1.5 (SDv1) and 2.0 (SDv2), which are types of LDM. Each model was fine-tuned using the created dataset. During the generation process, we adjusted the guidance scale (GS) to indicate the fidelity of the input text. Quantitative evaluation used metrics to measure image quality, diversity, and consistency with the text. Subjective evaluation consisted of visual assessments conducted by three radiological technologists.

Results

Quantitative and subjective evaluations showed that SDv2 (GS = 5) achieved the best performance in terms of image quality, diversity, and text consistency. In the subjective evaluation, no statistically significant differences were observed between the generated and real images, no statistically significant differences were detected between SDv2-generated and real ROI images across the evaluated categories.

Conclusion

We propose a method for generating chest CT nodule images based on input text using LDM. The evaluation results demonstrate that the proposed method can generate high-quality images that can successfully capture specific medical features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedLung NeoplasmsSolitary Pulmonary NoduleRadiographic Image Interpretation, Computer-AssistedDiagnosis, Computer-AssistedHumansAlgorithms

Stichwörter der Autor:innen

LIDC-IDRILatent diffusion modelsPulmonary noduleStable diffusionText-to-image

Autor:innen und Institutionen

  • Graduate School of Science and Engineering, Meijo University, 1-501 Shiogamaguchi, Tempaku-Ku, Nagoya City, Aichi, 468-8502, Japan.
  • Graduate School of Science and Engineering, Meijo University, 1-501 Shiogamaguchi, Tempaku-Ku, Nagoya City, Aichi, 468-8502, Japan. teramoto@meijo-u.ac.jp.
  • Fujita Health University, 1-98 Dengakugakubo, Kutsukake Cho, Toyoake City, Aichi, 470-1192, Japan.
  • Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan.

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Urata, K., Nagao, M., Teramoto, A., Imaizumi, K., Kondo, M., & Fujita, H. (2026). Generation of chest CT pulmonary nodule images by latent diffusion models using the LIDC-IDRI dataset. International Journal of Computer Assisted Radiology and Surgery, 21(11), 2295-2300. https://doi.org/10.1007/s11548-026-03754-5

Vancouver

Urata K, Nagao M, Teramoto A, Imaizumi K, Kondo M, Fujita H. Generation of chest CT pulmonary nodule images by latent diffusion models using the LIDC-IDRI dataset. International Journal of Computer Assisted Radiology and Surgery. 2026;21(11):2295-2300. doi:10.1007/s11548-026-03754-5

BibTeX
@article{Urata2026,
  author = {Urata, Kaito and Nagao, Maiko and Teramoto, Atsushi and Imaizumi, Kazuyoshi and Kondo, Masashi and Fujita, Hiroshi},
  title = {Generation of chest CT pulmonary nodule images by latent diffusion models using the LIDC-IDRI dataset},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {2295--2300},
  doi = {10.1007/s11548-026-03754-5}
}
Kostenlos starten →