EUVIMEDDescoperă EUVIMED
Open access

Automated Renal Tumor Segmentation in Computed Tomography Images Using a Global Attention–Based DeepLabV3+ Model: Algorithm Development and Validation

Yueyan Zhao, Jianqiang Liu, Lingyu Shao, Lin Li, Zhaoqing Liu, Yujie Liu, Jiaxin Wen, Xinyao Hao, Shuyan Li, Jianhong Zhao, Boming Song

JMIR Medical Informatics · 2026-09-15 · 14 · e78523-e78523

DOI: 10.2196/78523 ↗

At a glance

Journal article in JMIR Medical Informatics, published online on 2026-09-15. Written by Yueyan Zhao and 10 co-authors. Institution: School of Medical Information and Engineering, Xuzhou Medical University, KJL_E202 Room, 209 Tongshan Road, Yunlong District, Xuzhou, Jiangsu, 221004…. Major MEDLINE topics: Kidney Neoplasms, Tomography, X-Ray Computed, Algorithms, Image Processing, Computer-Assisted. 51 references. The full text is freely available in PubMed Central.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Background

The rising global incidence of renal tumors necessitates precise diagnostic interventions. Accurate segmentation of computed tomography (CT) scans is essential for nephron-sparing surgery and radiotherapy. However, conventional manual delineation is labor-intensive and prone to significant interobserver variability due to tumor morphological heterogeneity. There is an urgent clinical demand for robust, automated segmentation solutions.

Objective

This study aims to develop and validate GAM-DeepLabV3+, an automated framework designed to address boundary ambiguity and high false-positive rates in complex renal imaging scenarios.

Methods

We propose an optimized encoder-decoder architecture specifically tailored for renal mass detection. The framework incorporates three key innovations: (1) a lightweight MobileNetV2 backbone to minimize computational overhead for clinical deployment; (2) an Atrous Spatial Pyramid Pooling (ASPP) module to capture multiscale contextual information; and (3) a Global Attention Mechanism (GAM) in the decoder to enhance channel-spatial interactions, thereby refining boundary delineation by suppressing background noise. The model was rigorously evaluated on a private clinical dataset (n=218) and the KiTS19 benchmark (n=210).

Results

GAM-DeepLabV3+ consistently outperformed state-of-the-art baselines. On the private dataset, the model achieved a mean Dice similarity coefficient (DSC) of 0.939 (SD 0.008), significantly surpassing feature pyramid network (FPN; mean 0.893, SD 0.008; P

Subjects

MeSH terms (MEDLINE)

Kidney NeoplasmsTomography, X-Ray ComputedAlgorithmsImage Processing, Computer-AssistedHumans

Author keywords

CT imagesDeepLabV3+KiTS19deep learningglobal attention mechanismkidney tumor segmentation

Authors and institutions

  • School of Medical Information and Engineering, Xuzhou Medical University, KJL_E202 Room, 209 Tongshan Road, Yunlong District, Xuzhou, Jiangsu, 221004, China, 86 15852036109.
  • Department of Radiology, The Second Hospital & Clinical Medical School, Lanzhou University, Lanzhou, Gansu, China.

Cite

APA

Zhao, Y., Liu, J., Shao, L., Li, L., Liu, Z., Liu, Y., Wen, J., Hao, X., Li, S., Zhao, J., & Song, B. (2026). Automated Renal Tumor Segmentation in Computed Tomography Images Using a Global Attention–Based DeepLabV3+ Model: Algorithm Development and Validation. JMIR Medical Informatics, 14, e78523-e78523. https://doi.org/10.2196/78523

Vancouver

Zhao Y, Liu J, Shao L, Li L, Liu Z, Liu Y, et al. Automated Renal Tumor Segmentation in Computed Tomography Images Using a Global Attention–Based DeepLabV3+ Model: Algorithm Development and Validation. JMIR Medical Informatics. 2026;14:e78523-e78523. doi:10.2196/78523

BibTeX
@article{Zhao2026,
  author = {Zhao, Yueyan and Liu, Jianqiang and Shao, Lingyu and Li, Lin and Liu, Zhaoqing and Liu, Yujie and Wen, Jiaxin and Hao, Xinyao and Li, Shuyan and Zhao, Jianhong and Song, Boming},
  title = {Automated Renal Tumor Segmentation in Computed Tomography Images Using a Global Attention–Based DeepLabV3+ Model: Algorithm Development and Validation},
  journal = {JMIR Medical Informatics},
  year = {2026},
  volume = {14},
  pages = {e78523--e78523},
  doi = {10.2196/78523}
}
Start for free →