Abstract
Accurate kidney cortex and medulla segmentation enables compartment-specific
assessment of renal pathology that cannot be captured by whole-kidney analysis, including cortical changes in chronic kidney disease, corticomedullary alterations in diabetic kidney disease, and compartment-specific fibrosis.
However, most existing medical image segmentation methods focus on whole-kidney segmentation, with relatively few studies addressing cortex and medulla
segmentation. Furthermore, these studies rarely consider pathological
kidneys containing lesions. In this work, we present a stratified iterative learning framework for kidney cortex and medulla segmentation on contrast-enhanced
CT scans. The framework progressively incorporates increasingly challenging cases,
beginning with healthy kidneys and subsequently adding pathological kidneys with lesions. By leveraging model predictions from simpler cases to facilitate the annotation and refinement of more complex cases, the proposed strategy provides a practical approach for constructing training data across progressively challenging pathological cases. Validation on two external datasets demonstrated robust performance, achieving Dice similarity coefficients exceeding 97.2% for cortex segmentation and 94.7% for medulla segmentation, even in kidneys containing lesions. These results demonstrate the potential of the proposed framework for compartment-specific analysis of renal diseases.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/AMAI_047.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=NEJd8CljVm
BibTex
@InProceedings{LiuJia_Stratified_MICCAISAT2026,
author = { Liu, Jianfei AND Mathai, Tejas S. AND Summers, Ronald M.},
title = { { Stratified Iterative Learning for Kidney Cortex and Medulla Segmentation Across Healthy and Pathological Kidneys on Contrast-Enhanced CT } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17273},
month = {pending},
page = {pending}
}