Research Article | Open Access | Download Full Text
Volume 4 | Issue 2 | Year 2025 | Article Id: DST-V4I2P105 DOI: https://doi.org/10.59232/DST-V4I2P105
Identification and Segmentation of Renal Cancer Using MSRNet-3D and SAS Optimization in 3D-CT Imaging
Swapna J, Roselin Kiruba R
| Received | Revised | Accepted | Published |
|---|---|---|---|
| 10 Apr 2025 | 15 May 2025 | 10 Jun 2025 | 30 Jun 2025 |
Citation
Swapna J, Roselin Kiruba R. “Identification and Segmentation of Renal Cancer Using MSRNet-3D and SAS Optimization in 3D-CT Imaging.” DS Journal of Digital Science and Technology, vol. 4, no. 2, pp. 69-86, 2025.
Abstract
Since renal cancer is a major worldwide health concern, lowering mortality and hospitalization rates necessitates early detection and identification. By providing physicians with comprehensive anatomical information essential for tumour location and characterisation, the enlargement of Three-Dimensional Computed Tomography (3D-CT) has completely changed the diagnosis of renal malignancies. In order to improve overall diagnostics precision and effectiveness, sophisticated deep learning tactics are currently being developed to take into account the intricate forms of tumours and the artifacts created throughout imaging. However, there are many drawbacks to the present techniques for renal carcinoma classification, such as their high computing requirements, noise sensitivity, and unpredictability in tumour form. Introduce a new deep learning approach called Multi-Scale RenalNet 3D (MSRNet-3D) to address these issues and improve the classification of renal cancer in 3D-CT scans. To improve segmentation accuracy and resilience, MSRNet-3D incorporates multi-scale along with multi-level convolutional networks into its framework. The Seahorse Adaptive Search Optimization (SAAO) methodology, which adjusts model variables to promote rapid convergence and solve training-related issues, is an important invention of this work. The outcomes show notable gains in computational effectiveness, robustness against tumour variance, and segmentation accuracy. The crucial distinction between the establishment of Artificial Intelligence (AI)-based techniques for accurate renal cancer diagnosis and treatment planning and recent advances in imaging technology is addressed in the current research. When it came to the segmentation of renal carcinoma from 3D-CT scans, the MSRNet-3D model proposed in this research performed well. According to experimental results, the model's unmatched capacity for tumour detection and delineation to an exceptionally high level of precision is established by its 99% accuracy rate, 98.9% accuracy, and 99% recall. MSRNet-3D's F1-score, which gauges performance in terms of recall and accuracy, was 98.8%.
Keywords
3D image segmentation, Renal cancer, Cancer identification, Medical imaging, 3D Computed Tomography (3D-CT), Deep Learning (DL).
References
[1] Zhuo Chen et al., “Comprehensive 3D Analysis of the Renal System and Stones: Segmenting and Registering Non-Contrast and Contrast Computed Tomography Images,” Information Systems Frontiers, vol. 27, no. 1, pp. 97-111, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Vinitkumar Vasantbhai Patel et al., “A Systematic Renal Tumor Segmentation and Classification Framework using Adaptive and Attentive-based Deep Learning Networks with Improved Crayfish Optimization Algorithm,” IEEE Access, vol. 12, pp. 85635-85660, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Marie-France Bellin et al., “Update on Renal Cell Carcinoma Diagnosis with Novel Imaging Approaches,” Cancers, vol. 16, no. 10, pp. 1-33, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Xun Zhao et al., “The Application of CT Radiomics in the Diagnosis of Vein Wall Invasion in Patients with Renal Cell Carcinoma Combined with Tumor Thrombus,” The Oncologist, vol. 29, no. 2, pp. 151-158, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[5] ChengWei Fu et al., “Using Three-Dimensional Model-Based Tumour Volume Change to Predict the Symptom Improvement in Patients with Renal Cell Cancer,” 3 Biotech, vol. 14, no. 5, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Suping Yanget al., “Radiomics Analysis Based on Single Phase and Different Phase Combinations of Radiomics Features from Tri-Phasic CT to Distinguish Renal Oncocytoma from Chromophobe Renal Cell Carcinoma,” Abdominal Radiology, vol. 49, no. 1, pp. 182-191, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Alex G. Raman et al., “Radiomics and Artificial Intelligence: Renal Cell Carcinoma,” Urologic Clinics, vol. 51, no. 1, pp. 35-45, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] R. Rajkumaret al., “DARKNET-53 Convolutional Neural Network-Based Image Processing for Breast Cancer Detection,” Mesopotamian Journal of Artificial Intelligence in Healthcare, vol. 2024, pp. 59-68, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Maryamalsadat Mahootiha et al., “Multimodal Deep Learning for Personalized Renal Cell Carcinoma Prognosis: Integrating CT Imaging and Clinical Data,” Computer Methods and Programs in Biomedicine, vol. 244, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Kwang-Hyun Uhm et al., “Lesion-Aware Cross-Phase Attention Network for Renal Tumor Subtype Classification on Multi-Phase CT Scans,” Computers in Biology and Medicine, vol. 178, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Abeer J. Alhussaini et al., “Radiomics Machine Learning Analysis of Clear Cell Renal Cell Carcinoma for Tumour Grade Prediction Based on Intra-Tumoural Sub-Region Heterogeneity,” Cancers, vol. 16, no. 4, pp. 1-35, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] P. Suman Prakash et al., “Decoupled Sculptor GAN Framework for 3D Reconstruction and Enhanced Segmentation of Renal Tumors in CT Images,” IEEE Access, vol. 12, pp. 62189-62198, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] MM. Yaodan Zhang et al., “Preoperative Prediction of Renal Fibrous Capsule Invasion in Clear Cell Renal Cell Carcinoma Using CT-Based Radiomics Model,” British Journal of Radiology, vol. 97, no. 1161, pp. 1557-1567, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Venkatesan Rajinikanth et al., “A Framework to Distinguish Healthy/Cancer Renal CT Images Using the Fused Deep Features,” Frontiers Public Health, vol. 11, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] G. Maheswari, and S. Gopalakrishnan, “Dynamic Channel Attention for Enhanced Spatial Feature Extraction in Medical Image Analysis using Advanced Attention Capsule Network,” 2024 International Conference on Integrated Circuits and Communication Systems (ICICACS), Raichur, India, pp. 1-7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Kai Wu et al., “A Comprehensive Texture Feature Analysis Framework of Renal Cell Carcinoma: Pathological, Prognostic, and Genomic Evaluation Based on CT Images,” European Radiology, vol. 32, no. 4 pp. 2255-2265, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Jingya Liu et al., “AI-Driven Robust Renal and Renal Mass Segmentation and Classification on 3D CT Images,” Bioengineering, vol. 10, no. 1, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Huancheng Yang et al., “An Automated Surgical Decision-Making Framework for Partial or Radical Nephrectomy Based on 3d-CT Multi-Level Anatomical Features in Renal Cell Carcinoma,” European Radiology, vol. 33, no. 11, pp. 7532-7541, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Dhuha Abdalredha Kadhim, and Mazin Abed Mohammed, “A Comprehensive Review of Artificial Intelligence Approaches in Renal Cancer Medical Images Diagnosis, Datasets, Challenges and Issues and Future Directions,” International Journal of Mathematics, Statistics, and Computer Science, vol. 2, pp. 199-243, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Kwang-Hyun Uhm et al., “Deep Learning for End-to-End kidney Cancer Diagnosis on Multi-Phase Abdominal Computed Tomography,” NPJ Precision Oncology, vol. 5, no. 1, pp. 1-6, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Dalia Alzu’bi et al., “kidney Tumor Detection and Classification Based on Deep Learning Approaches: A New Dataset in CT Scans,” Journal of Healthcare Engineering, vol. 2022, pp. 1-22, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Zhanlin Ji et al., “ASD-Net: A Novel U-Net Based Asymmetric Spatial-Channel Convolution Network for Precise kidney and kidney Tumor Image Segmentation,” Medical and Biological Engineering and Computing, vol. 62, no. 6, pp. 1673-1687, 2024. [CrossRef] [Google Scholar] [Publisher Link]
[23] Maryamalsadat Mahootiha et al., “Deep Learning-Assisted Survival Prognosis in Renal Cancer: A CT Scan-Based Personalized Approach,” Heliyon, vol. 10, no. 2, pp.1-15, 2024.
[Google Scholar] [Publisher Link]
[24] Minpeng Jiang et al., “MDSK‐Net: Multi‐Scale Dynamic Segmentation Kernel Network for Renal Tumour Endoscopic Image Segmentation,” IET Image Processing, vol. 18, no. 11, pp. 2855-2868, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Yu-Ning Feng et al., “Predictive Value of Computed Tomography Radiomics Combined with Traditional Imaging Features in WHO/ISUP Grading of Clear Cell Renal Carcinoma,” International Journal of Imaging Systems and Technology, vol. 34, no. 3, 2024.