Synthetic DICOM Slices for 3D Reconstruction Benchmarking

Read full text Summarise with VIRAT
Authors: M. Komada
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This dataset was created in order to compare the performance of various methods of 3D reconstruction from CT images. It contains 3 different 3D models in .obj format and their slices in DICOM standard. For each model there are two series of images - before and after introducing noise. Each model is provided in two versions - original and transformed (scaled and rotated; suffix "_SR") so that they fit in the common bounding box. The models contain certain features that can be problematic during mesh generation (for example thin walls or concave areas).

Fields of Study & Subjects

3D Shape Modeling and Analysis Medical Image Segmentation Techniques Anatomy and Medical Technology

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
21 March 2026
Language
EN
Document type
Dataset