EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Kidney Tumor Segmentation in CT Images Using Deep Learning: A Multi-Stage Approach

Hung-Cheng Kan, Geng-Ming Fan, Ming-Hao Wei, Po-Hung Lin, I-Hung Shao, Kai-Jie Yu, Ti-Hsuan Chien, See-Tong Pang, Chun-Te Wu, Syu-Jyun Peng

Academic Radiology · 2025

DOI: 10.1016/j.acra.2025.08.020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Radiology, 2025. Verfasst von Hung-Cheng Kan und 9 weiteren Autor:innen. Beteiligte Einrichtung: In-Service Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan (H.-C.K., S.-J.P.); …. Hauptthemen laut MEDLINE: Kidney Neoplasms, Deep Learning, Tomography, X-Ray Computed, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RATIONALE AND OBJECTIVES: Computed tomography (CT) remains the primary modality for assessing renal tumors; however, tumor identification and segmentation rely heavily on manual interpretation by clinicians, which is time-consuming and subject to inter-observer variability. The heterogeneity of tumor appearance and indistinct margins further complicate accurate delineation, impacting histopathological classification, treatment planning, and prognostic assessment. There is a pressing clinical need for an automated segmentation tool to enhance diagnostic workflows and support clinical decision-making with results that are reliable, accurate, and reproducible. MATERIALS AND METHODS: This study developed a fully automated pipeline based on the DeepMedic 3D convolutional neural network for the segmentation of kidneys and renal tumors through multi-scale feature extraction. The model was trained and evaluated using 5-fold cross-validation on a dataset of 382 contrast-enhanced CT scans manually annotated by experienced physicians. Image preprocessing included Hounsfield unit conversion, windowing, 3D reconstruction, and voxel resampling. Post-processing was also employed to refine output masks and improve model generalizability. RESULTS: The proposed model achieved high performance in kidney segmentation, with an average Dice coefficient of 93.82 ± 1.38%, precision of 94.86 ± 1.59%, and recall of 93.66 ± 1.77%. In renal tumor segmentation, the model attained a Dice coefficient of 88.19 ± 1.24%, precision of 90.36 ± 1.90%, and recall of 88.23 ± 2.02%. Visual comparisons with ground truth annotations confirmed the clinical relevance and accuracy of the predictions. CONCLUSION: The proposed DeepMedic-based framework demonstrates robust, accurate segmentation of kidneys and renal tumors on CT images. With its potential for real-time application, this model could enhance diagnostic efficiency and treatment planning in renal oncology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Kidney NeoplasmsDeep LearningTomography, X-Ray ComputedRadiographic Image Interpretation, Computer-AssistedHumansReproducibility of ResultsImaging, Three-DimensionalFemale

Stichwörter der Autor:innen

Computed TomographyDeep LearningRenal TumorSegmentation

Autor:innen und Institutionen

  • In-Service Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan (H.-C.K., S.-J.P.); Division of Urology, Department of Surgery, Linkou Chang Gung Memorial…
  • Department of General Medicine, Chang-Geng Medical Foundation Keelung Chang-Geng Memorial Hospital, Keelung, Taiwan (G.-M.F.); Department of Medicine, Taipei Medical University, Taipei, Taiwan (G.-M.F.).
  • Department of Electrical Engineering, National Central University, Taoyuan, Taiwan (M.-H.W.).
  • Division of Urology, Department of Surgery, Linkou Chang Gung Memorial Hospital, Taoyuan, Taiwan (H.-C.K., P-H.L., I.-H.S., K.-J.Y., S.-T.P., T.W.); College of Medicine, Chang Gung University, Taoyuan, Taiwan (H.-C.K.,…
  • Department of General Surgery, Keelung Chang Gung Memorial Hospital, Keelung, Taiwan (T.-H.C.).
  • In-Service Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan (H.-C.K., S.-J.P.); Clinical Big Data Research Center, Taipei Medical University Hospital,…

Förderung

  • National Science and Technology Council

Zitieren

APA

Kan, H. C., Fan, G. M., Wei, M. H., Lin, P. H., Shao, I. H., Yu, K. J., Chien, T. H., Pang, S. T., Wu, C. T., & Peng, S. J. (2025). Automated Kidney Tumor Segmentation in CT Images Using Deep Learning: A Multi-Stage Approach. Academic Radiology. https://doi.org/10.1016/j.acra.2025.08.020

Vancouver

Kan HC, Fan GM, Wei MH, Lin PH, Shao IH, Yu KJ, et al. Automated Kidney Tumor Segmentation in CT Images Using Deep Learning: A Multi-Stage Approach. Academic Radiology. 2025. doi:10.1016/j.acra.2025.08.020

BibTeX
@article{Kan2025,
  author = {Kan, Hung-Cheng and Fan, Geng-Ming and Wei, Ming-Hao and Lin, Po-Hung and Shao, I-Hung and Yu, Kai-Jie and Chien, Ti-Hsuan and Pang, See-Tong and Wu, Chun-Te and Peng, Syu-Jyun},
  title = {Automated Kidney Tumor Segmentation in CT Images Using Deep Learning: A Multi-Stage Approach},
  journal = {Academic Radiology},
  year = {2025},
  doi = {10.1016/j.acra.2025.08.020}
}
Kostenlos starten →