EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detection of pulmonary nodules in chest radiographs: novel cost function for effective network training with purely synthesized datasets

Shouhei Hanaoka, Yukihiro Nomura, Takeharu Yoshikawa, Takahiro Nakao, Tomomi Takenaga, Hirotaka Matsuzaki, Nobutake Yamamichi, Osamu Abe

International Journal of Computer Assisted Radiology and Surgery · 2024

DOI: 10.1007/s11548-024-03227-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2024. Verfasst von Shouhei Hanaoka und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan. hanaoka-tky@g.ecc.u-tokyo.ac.jp. Hauptthemen laut MEDLINE: Lung Neoplasms, Solitary Pulmonary Nodule. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS Kakenhi, Japan, JST, CREST, Japan, The University of Tokyo.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Many large radiographic datasets of lung nodules are available, but the small and hard-to-detect nodules are rarely validated by computed tomography. Such difficult nodules are crucial for training nodule detection methods. This lack of difficult nodules for training can be addressed by artificial nodule synthesis algorithms, which can create artificially embedded nodules. This study aimed to develop and evaluate a novel cost function for training networks to detect such lesions. Embedding artificial lesions in healthy medical images is effective when positive cases are insufficient for network training. Although this approach provides both positive (lesion-embedded) images and the corresponding negative (lesion-free) images, no known methods effectively use these pairs for training. This paper presents a novel cost function for segmentation-based detection networks when positive–negative pairs are available.

Methods

Based on the classic U-Net, new terms were added to the original Dice loss for reducing false positives and the contrastive learning of diseased regions in the image pairs. The experimental network was trained and evaluated, respectively, on 131,072 fully synthesized pairs of images simulating lung cancer and real chest X-ray images from the Japanese Society of Radiological Technology dataset.

Results

The proposed method outperformed RetinaNet and a single-shot multibox detector. The sensitivities were 0.688 and 0.507 when the number of false positives per image was 0.2, respectively, with and without fine-tuning under the leave-one-case-out setting.

Conclusion

To our knowledge, this is the first study in which a method for detecting pulmonary nodules in chest X-ray images was evaluated on a real clinical dataset after being trained on fully synthesized images. The synthesized dataset is available at https://zenodo.org/records/10648433 .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsSolitary Pulmonary NoduleHumansRadiographic Image Interpretation, Computer-AssistedTomography, X-Ray ComputedRadiography, ThoracicAlgorithmsMultiple Pulmonary NodulesNeural Networks, Computer

Stichwörter der Autor:innen

Artificial lesion synthesisChest radiographLung cancerLung nodule detectionU-Net

Autor:innen und Institutionen

  • Department of Radiology, University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan. hanaoka-tky@g.ecc.u-tokyo.ac.jp.
  • Center for Frontier Medical Engineering, Chiba University, 1-33 Yayoi-cho, Inage-ku, Chiba, Japan.
  • Department of Computational Diagnostic Radiology and Preventive Medicine, University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan.
  • Department of Radiology, University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan.
  • Center for Epidemiology and Preventive Medicine, University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan.

Förderung

  • JSPS Kakenhi, Japan
  • JST, CREST, Japan
  • The University of Tokyo

Zitieren

APA

Hanaoka, S., Nomura, Y., Yoshikawa, T., Nakao, T., Takenaga, T., Matsuzaki, H., Yamamichi, N., & Abe, O. (2024). Detection of pulmonary nodules in chest radiographs: novel cost function for effective network training with purely synthesized datasets. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-024-03227-7

Vancouver

Hanaoka S, Nomura Y, Yoshikawa T, Nakao T, Takenaga T, Matsuzaki H, et al. Detection of pulmonary nodules in chest radiographs: novel cost function for effective network training with purely synthesized datasets. International Journal of Computer Assisted Radiology and Surgery. 2024. doi:10.1007/s11548-024-03227-7

BibTeX
@article{Hanaoka2024,
  author = {Hanaoka, Shouhei and Nomura, Yukihiro and Yoshikawa, Takeharu and Nakao, Takahiro and Takenaga, Tomomi and Matsuzaki, Hirotaka and Yamamichi, Nobutake and Abe, Osamu},
  title = {Detection of pulmonary nodules in chest radiographs: novel cost function for effective network training with purely synthesized datasets},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2024},
  doi = {10.1007/s11548-024-03227-7}
}
Kostenlos starten →