EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Artificial intelligence-based non-invasive tumor segmentation, grade stratification and prognosis prediction for clear-cell renal-cell carcinoma

Siteng Chen, Dandan Song, Lei Chen, Tuanjie Guo, Beibei Jiang, Aie Liu, Xianpan Pan, Tao Wang, Heting Tang, Guihua Chen, Zhong Xue, Xiang Wang und 2 weitere

Precision Clinical Medicine · 14.07.2023 · 6 (3)

DOI: 10.1093/pcmedi/pbad019 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Precision Clinical Medicine, online erschienen am 17.08.2023. Verfasst von Siteng Chen und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200001, China. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, National Cancer Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the complicated histopathological characteristics of clear-cell renal-cell carcinoma (ccRCC), non-invasive prognosis before operative treatment is crucial in selecting the appropriate treatment. A total of 126 345 computerized tomography (CT) images from four independent patient cohorts were included for analysis in this study. We propose a V Bottleneck multi-resolution and focus-organ network (VB-MrFo-Net) using a cascade framework for deep learning analysis. The VB-MrFo-Net achieved better performance than VB-Net in tumor segmentation, with a Dice score of 0.87. The nuclear-grade prediction model performed best in the logistic regression classifier, with area under curve values from 0.782 to 0.746. Survival analysis revealed that our prediction model could significantly distinguish patients with high survival risk, with a hazard ratio (HR) of 2.49 [95% confidence interval (CI): 1.13–5.45, P = 0.023] in the General cohort. Excellent performance had also been verified in the Cancer Genome Atlas cohort, the Clinical Proteomic Tumor Analysis Consortium cohort, and the Kidney Tumor Segmentation Challenge cohort, with HRs of 2.77 (95%CI: 1.58–4.84, P = 0.0019), 3.83 (95%CI: 1.22–11.96, P = 0.029), and 2.80 (95%CI: 1.05–7.47, P = 0.025), respectively. In conclusion, we propose a novel VB-MrFo-Net for the renal tumor segmentation and automatic diagnosis of ccRCC. The risk stratification model could accurately distinguish patients with high tumor grade and high survival risk based on non-invasive CT images before surgical treatments, which could provide practical advice for deciding treatment options.

Schlagwörter

Stichwörter der Autor:innen

clear-cell renal-cell carcinomadeep learningdiagnosisnon-invasivepredictionprognosis

Autor:innen und Institutionen

  • Department of Urology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200001, China.
  • Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200011, China.
  • Shanghai United Imaging Intelligence Co., Ltd., Shanghai 201807, China.
  • Department of Urology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200080, China.
  • Department of Radiology, Erasmus University Medical Center, Rotterdam, P.O. Box 2040, 3000 CA, The Netherlands.
  • Department of Urology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China.

Förderung

  • National Natural Science Foundation of China
  • National Cancer Institute

Zitieren

APA

Chen, S., Song, D., Chen, L., Guo, T., Jiang, B., Liu, A., Pan, X., Wang, T., Tang, H., Chen, G., Xue, Z., Wang, X., Zhang, N., & Zheng, J. (2023). Artificial intelligence-based non-invasive tumor segmentation, grade stratification and prognosis prediction for clear-cell renal-cell carcinoma. Precision Clinical Medicine, 6(3). https://doi.org/10.1093/pcmedi/pbad019

Vancouver

Chen S, Song D, Chen L, Guo T, Jiang B, Liu A, et al. Artificial intelligence-based non-invasive tumor segmentation, grade stratification and prognosis prediction for clear-cell renal-cell carcinoma. Precision Clinical Medicine. 2023;6(3). doi:10.1093/pcmedi/pbad019

BibTeX
@article{Chen2023,
  author = {Chen, Siteng and Song, Dandan and Chen, Lei and Guo, Tuanjie and Jiang, Beibei and Liu, Aie and Pan, Xianpan and Wang, Tao and Tang, Heting and Chen, Guihua and Xue, Zhong and Wang, Xiang and Zhang, Ning and Zheng, Junhua},
  title = {Artificial intelligence-based non-invasive tumor segmentation, grade stratification and prognosis prediction for clear-cell renal-cell carcinoma},
  journal = {Precision Clinical Medicine},
  year = {2023},
  volume = {6},
  number = {3},
  doi = {10.1093/pcmedi/pbad019}
}
Kostenlos starten →