Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Explicit and Implicit Representations in AI-based 3D Reconstruction for Radiology: A Systematic Review

Yuezhe Yang, Boyu Yang, Yaqian Wang, Yang He, Xingbo Dong, Zhe Jin

TL;DR

This systematic review surveys AI-based 3D reconstruction in radiology, framing the landscape through explicit and implicit representations. It catalogs datasets and evaluation metrics, and analyzes methods across slice-based, volume-based, Gaussian, and implicit approaches such as Implicit Prior Embedding and Neural Radiance Fields. The review highlights tradeoffs between accuracy, efficiency, adaptability, and interpretability, noting real-time potential for Gaussian-based methods and high-fidelity benefits from NeRF-based approaches, alongside computational and data-availability challenges. It provides guidance for future research toward clinically translatable, privacy-preserving, and interpretable reconstruction pipelines with broad multimodal applicability.

Abstract

The demand for high-quality medical imaging in clinical practice and assisted diagnosis has made 3D reconstruction in radiological imaging a key research focus. Artificial intelligence (AI) has emerged as a promising approach to enhancing reconstruction accuracy while reducing acquisition and processing time, thereby minimizing patient radiation exposure and discomfort and ultimately benefiting clinical diagnosis. This review explores state-of-the-art AI-based 3D reconstruction algorithms in radiological imaging, categorizing them into explicit and implicit approaches based on their underlying principles. Explicit methods include point-based, volume-based, and Gaussian representations, while implicit methods encompass implicit prior embedding and neural radiance fields. Additionally, we examine commonly used evaluation metrics and benchmark datasets. Finally, we discuss the current state of development, key challenges, and future research directions in this evolving field. Our project available on: https://github.com/Bean-Young/AI4Radiology.

Explicit and Implicit Representations in AI-based 3D Reconstruction for Radiology: A Systematic Review

TL;DR

This systematic review surveys AI-based 3D reconstruction in radiology, framing the landscape through explicit and implicit representations. It catalogs datasets and evaluation metrics, and analyzes methods across slice-based, volume-based, Gaussian, and implicit approaches such as Implicit Prior Embedding and Neural Radiance Fields. The review highlights tradeoffs between accuracy, efficiency, adaptability, and interpretability, noting real-time potential for Gaussian-based methods and high-fidelity benefits from NeRF-based approaches, alongside computational and data-availability challenges. It provides guidance for future research toward clinically translatable, privacy-preserving, and interpretable reconstruction pipelines with broad multimodal applicability.

Abstract

The demand for high-quality medical imaging in clinical practice and assisted diagnosis has made 3D reconstruction in radiological imaging a key research focus. Artificial intelligence (AI) has emerged as a promising approach to enhancing reconstruction accuracy while reducing acquisition and processing time, thereby minimizing patient radiation exposure and discomfort and ultimately benefiting clinical diagnosis. This review explores state-of-the-art AI-based 3D reconstruction algorithms in radiological imaging, categorizing them into explicit and implicit approaches based on their underlying principles. Explicit methods include point-based, volume-based, and Gaussian representations, while implicit methods encompass implicit prior embedding and neural radiance fields. Additionally, we examine commonly used evaluation metrics and benchmark datasets. Finally, we discuss the current state of development, key challenges, and future research directions in this evolving field. Our project available on: https://github.com/Bean-Young/AI4Radiology.

Paper Structure

This paper contains 25 sections, 5 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Development of Reconstruction Algorithms
  3. Advent of Neural Networks
  4. Rise of Generative Models
  5. Emergence of Novel Representations
  6. Methods
  7. Literature Review
  8. Literature Classification
  9. Datasets and metrics
  10. Datasets
  11. Metrics
  12. Explicit reconstruction methods
  13. Slice-base Representation
  14. Volume-base Representation
  15. Gaussian Representation
  16. ...and 10 more sections

Figures (5)

  • Figure 1: A brief chronology of the development of techniques related to radiological image reconstruction in literature.
  • Figure 2: Five different forms of reconstruction representations in radiological imaging, with the first row showing explicit representations and the second row implicit ones.
  • Figure 3: Flowchart of the literature review.
  • Figure 4: Three distinct types of tasks in radiological image reconstruction.
  • Figure 5: Categorization results of the reviewed literature, including: (a) classification based on imaging modalities, (b) publication year, and (c) representation forms used in reconstruction methods.