Back to all papers

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

Authors

Kan HC,Fan GM,Wei MH,Lin PH,Shao IH,Yu KJ,Chien TH,Pang ST,Wu CT,Peng SJ

Affiliations (6)

  • 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 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., P-H.L., I.-H.S., K.-J.Y., S.-T.P., T.W.).
  • 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., P-H.L., I.-H.S., K.-J.Y., S.-T.P., T.W.).
  • 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, Taipei Medical University, Taipei, Taiwan (S.-J.P.). Electronic address: [email protected].

Abstract

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. 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. 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. 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.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.