Hybrid 3D Mesh Reconstruction Models of CT Images for Deep Learning Based Classification of Kidney Tumors
Year: 2025
Type: conference-paper
Abstract: We present a comparative analysis of three hybrid methodologies for transforming 3D kidney tumor segmentations of volumetric NIfTI data into highly accurate network representations. Exploiting the KiTS23 dataset, we evaluate edge-preserving reconstruction pipelines integrating anisotropic diffusion, multiscale Gaussian filtering and KNN-based network optimisation. Model 1 uses Gaussian smoothing with Marching Cubes, while Model 2 uses spline interpolation and Perona-Malik filtering for improved resolution. Model 3 extends this structure with normal sensitive vertex smoothing to preserve critical anatomical interfaces. Quantitative metrics (Dice score, HD95) demonstrated the advantage of Model 3, which achieved a 22% reduction in the Hausdorff distance error rate compared to conventional methods while maintaining segmentation accuracy (Dice > 0.92). The proposed unsupervised pipeline bridges the gap between clinical interpretability and computational accuracy, providing a robust infrastructure for further applications in surgical planning and deep learning-based classification.
Institutions: Muş Alparslan University, Kocaeli Üniversitesi
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4414024607