Awesome-Implicit-Neural-Representations-in-Medical-imaging

Awesome-Implicit-Neural-Representations-in-Medical-imaging

隐式神经表示在医学影像中的应用研究综述

该项目汇集了86篇关于隐式神经表示在医学影像领域应用的研究论文,时间跨度从2021年至2023年。涵盖图像重建、分割、配准和神经渲染等多个方向。项目提供论文列表、代码链接及相关资源,便于研究者快速获取信息。同时收录了一篇发表于arXiv的综述文章,对医学影像中隐式神经表示的应用进行了全面对比分析。

医学成像神经隐式表示图像重建分割配准Github开源项目

Implicit Neural Representation in Medical Imaging: A Comparative Survey <br> <span style="float: right"><sub><sup>ICCV 2023 CVAMD Workshop</sup></sub></span>

Awesome License: MIT PRs Welcome

:fire::fire: This is a collection of awesome articles about Implicit Neural Representation networks in medical imaging:fire::fire:

:loudspeaker: Our review paper published on arXiv: Implicit Neural Representation in Medical Imaging: A Comparative Survey :heart:

Citation

[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]

Introduction

Implicitly representing image signals has gained popularity in recent years for a broad range of medical imaging applications. The most motivating reasons are the following:

  • Memory efficiency: The amount of memory demanded to represent the signal is not restricted by the signal's resolution.
  • Unlimited Resolution: They take values in the continuous domain, meaning they can generate values for coordinates in-between the pixel or voxel-wise grid
  • Effective data usage: They can learn to handle reconstruction and synthesis tasks without high-cost external annotation.

Which all are significantly important for developing an automatic medical system.<br> With the aim of providing easier access for researchers, this repo contains a comprehensive paper list of Implicit Neural Representations in Medical Imaging, including papers, codes, and related websites.<br> We considered a sum of <u>86</u> research papers spanning from 2021 to 2023.


papers

<img src="Figures/Taxonomy.png" alt="Taxonomy" width="816"> Here, we taxonomize studies that integrate implicit representations into building medical analysis models.<br>

<a name="return-to-list"></a>

(Each section is ordered by the publication dates) <img src="Figures/Reconstruction.jpg" alt="reconstruction" width="1000" height="5"><br>

Image Reconstruction


Tomography and CT

  1. 📜 IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction

    • 🗓️ Publication Date: 9th Feb. 2021
    • 📖 Proceedings: IEEE/CVF International Conference on Computer Vision, 2021
    • 🧑‍🔬 Authors: Guangming Zang, Ramzi Idoughi, Rui Li, Peter Wonka, Wolfgang Heidrich
    • 📄 PDF
    • 📌 Highlight: Uses coordinate-based neural representations for CT reconstructions, capturing details often overlooked by standard deep learning. It's self-supervised, using the scanned object's own projections as training data, and further refined with geometric techniques.
  2. 📜 CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems

    • 🗓️ Publication Date: 9th Feb. 2021
    • 📖 Journal: IEEE Transactions on Computational Imaging, 2021
    • 🧑‍🔬 Authors: Yu Sun, Jiaming Liu, Mingyang Xie, Brendt Wohlberg, Ulugbek S. Kamilov
    • 📄 PDF
    • 💻 GitHub
    • 📌 Highlight: Takes measurement coordinates, such as view angle θ and spatial location l in CT scans, as its input, then outputs the corresponding sensor responses for these coordinates, creating an implicit neural representation of the measurement field.
  3. 📜 Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields

    • 🗓️ Publication Date: 23th Apr. 2021
    • 📖 Proceedings: IEEE/CVF International Conference on Computer Vision, 2021
    • 🧑‍🔬 Authors: Albert W. Reed, Hyojin Kim, Rushil Anirudh, K. Aditya Mohan, Kyle Champley, Jingu Kang, Suren Jayasuriya
    • 📄 PDF
    • 📌 Highlight: Uses implicit neural representations (INRs) for 4D-CT reconstruction. Paired with a parametric motion field, they estimate evolving 3D objects. Using a differentiable Radon transform, reconstructions are synthesized and compared with x-ray data, improving reconstruciton quality without training data.
  4. 📜 Neural Computed Tomography

    • 🗓️ Publication Date: 17th Jan. 2022
    • 📖 Preprint: arXiv, 2022
    • 🧑‍🔬 Authors: Kunal Gupta, Brendan Colvert, Francisco Contijoch
    • 📄 PDF
    • 💻 GitHub
  5. 📜 Streak artifacts reduction algorithm using an implicit neural representation in sparse-view CT

    • 🗓️ Publication Date: 4th Apr. 2022
    • 📖 Conference: Medical Imaging 2022: Physics of Medical Imaging, 2022
    • 🧑‍🔬 Authors: Byeongjoon Kim, Hyunjung Shim, Jongduk Baek
    • 📄 PDF
  6. 📜 Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography

    • 🗓️ Publication Date: 12th Sep. 2022
    • 📖 Journal: IEEE Transactions on Computational Imaging, 2023
    • 🧑‍🔬 Authors: Qing Wu, Ruimin Feng, Hongjiang Wei, Jingyi Yu, Yuyao Zhang
    • 📄 PDF
    • 💻 GitHub
  7. 📜 OReX: Object Reconstruction from Planar Cross-sections Using Neural Fields

    • 🗓️ Publication Date: 23th Nov. 2022
    • 📖 Conference: CVPR, 2023
    • 🧑‍🔬 Authors: Haim Sawdayee, Amir Vaxman, Amit H. Bermano
    • 📄 PDF
    • 💻 GitHub
  8. 📜 NeuRec: Incorporating Interpatient prior to Sparse-View Image Reconstruction for Neurorehabilitation

    • 🗓️ Publication Date: 21th Feb. 2022
    • 📖 Journal: BioMed Research International, 2022
    • 🧑‍🔬 Authors: Cong Liu, Qingbin Wang, Jing Zhang
    • 📄 PDF
  9. 📜 MEPNet: A Model-Driven Equivariant Proximal Network for Joint Sparse-View Reconstruction and Metal Artifact Reduction in CT Images.

    • 🗓️ Publication Date: 25th Jun. 2023
    • 📖 Preprint: arXiv
    • 🧑‍🔬 Authors: Hong Wang, Minghao Zhou, Dong Wei, Yuexiang Li, Yefeng Zheng
    • 📄 PDF
    • 🖥️ GitHub
  10. 📜 UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography

    • 🗓️ Publication Date: 3rd Jun. 2022
    • 📖 Authors: Francisca Vasconcelos, Bobby He, Nalini Singh, Yee Whye Teh
    • 📄 PDF
    • 💻 GitHub
  11. 📜 Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction

    • 🗓️ Publication Date: 27th Jun. 2023
    • 📖 Preprint: arXiv
    • 🧑‍🔬 Authors: Qing Wu, Lixuan Chen, Ce Wang, Hongjiang Wei, S. Kevin Zhou, Jingyi Yu, Yuyao Zhang
    • 📄 PDF
  12. 📜 NAISR: A 3D Neural Additive Model for Interpretable Shape Representation

    • 🗓️ Publication Date: 16th Mar. 2023
    • 📖 Preprint: arXiv
    • 🧑‍🔬 Authors: Yining Jiao, Carlton Zdanski, Julia Kimbell, Andrew Prince, Cameron Worden, Samuel Kirse, Christopher Rutter, Benjamin Shields, William Dunn
    • 📄 PDF
    • 💻 GitHub

<sub>Return to List</sub>


MRI

  1. 📜 An Arbitrary Scale Super-Resolution Approach for 3-Dimensional Magnetic Resonance Image using Implicit Neural Representation

    • 🗓️ Publication Date: 29th Oct. 2021
    • 🧑‍🔬 Authors: Qing Wu, Yuwei Li, Yawen Sun, Yan Zhou, Hongjiang Wei, Jingyi Yu, Yuyao Zhang
    • 📄 PDF
    • 💻 GitHub
  2. 📜 IREM: High-Resolution Magnetic Resonance (MR) Image Reconstruction via Implicit Neural Representation

    • 🗓️ Publication Date: 29th Jun. 2021
    • 🧑‍🔬 Authors: Qing Wu, Yuwei Li, Lan Xu, Ruiming Feng, Hongjiang Wei, Qing Yang, Boliang Yu, Xiaozhao Liu, Jingyi Yu, Yuyao Zhang
    • 📄 PDF
  3. 📜 MRI Super-Resolution using Implicit Neural Representation with Frequency Domain Enhancement

    • 🗓️ Publication Date: Aug. 2022
    • 🧑‍🔬 Authors: Shuangming Mao, Seiichiro Kamata
    • 📄 PDF
  4. 📜 NeSVoR: Implicit Neural Representation for Slice-to-Volume Reconstruction in MRI

    • 🗓️ Publication Date: IEEE TRANSACTIONS ON MEDICAL IMAGING, 2022
    • 🧑‍🔬 Authors: Junshen Xu, Daniel Moyer, Borjan Gagoski, Juan Eugenio Iglesias, P. Ellen Grant, Polina Golland, Elfar Adalsteinsson
    • 📄 PDF
    • 💻 GitHub
  5. 📜 Spatiotemporal implicit neural representation for unsupervised dynamic MRI reconstruction

    • 🗓️ Publication Date: 31th Dec. 2022
    • 🧑‍🔬 Authors: Jie Feng, Ruimin Feng, Qing Wu, Zhiyong Zhang, Yuyao Zhang, Hongjiang Wei
    • 📄 [PDF](Link to PDF)
  6. 📜 Neural Implicit k-Space for Binning-free Non-Cartesian Cardiac MR Imaging

    • 🗓️ Publication Date: 16th Dec. 2022
    • 📖 Conference: International Conference on Information Processing in Medical Imaging, 2023
    • 🧑‍🔬 Authors: Wenqi Huang, Hongwei Li, Jiazhen Pan, Gastao Cruz, Daniel Rueckert, Kerstin Hammernik
    • 📄 PDF
  7. 📜 Continuous longitudinal fetus brain atlas construction via implicit neural representation

    • 🗓️ Publication Date: 14th Sep. 2022
    • 🧑‍🔬 Authors: Lixuan Chen, Jiangjie Wu, Qing Wu, Hongjiang Wei, Yuyao Zhang
    • 📄 PDF
  8. 📜 Multi-contrast MRI Super-resolution via Implicit Neural Representations

    • 🗓️ Publication Date: 27th Mar. 2023
    • 📖 Conference: MICCAI, 2023
    • 🧑‍🔬 Authors: Julian McGinnis, Suprosanna Shit, Hongwei Bran Li, Vasiliki Sideri-Lampretsa, Robert Graf, Maik Dannecker, Jiazhen Pan, Nil Stolt Ansö, Mark Mühlau, Jan S. Kirschke, Daniel Rueckert, Benedikt Wiestler
    • 📄 PDF
    • 💻 GitHub
  9. 📜 Streak artifacts reduction algorithm using an implicit neural representation in sparse-view CT.

    • 📅 Publication Date: 4th Apr., 2022

    • 📖 Journal: Medical Imaging 2022: Physics of Medical Imaging, 2022

    • 🧑‍🔬 Authors: Byeongjoon Kim, Hyunjung Shim, Jongduk Baek.

    • 📄 PDF

  10. 📜 Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing

    • 🗓️ Publication Date: 23rd May. 2022
    • 🧑‍🔬 Authors: Xin Wang, Sheng Wang,

编辑推荐精选

openai-agents-python

openai-agents-python

OpenAI Agents SDK,助力开发者便捷使用 OpenAI 相关功能。

openai-agents-python 是 OpenAI 推出的一款强大 Python SDK,它为开发者提供了与 OpenAI 模型交互的高效工具,支持工具调用、结果处理、追踪等功能,涵盖多种应用场景,如研究助手、财务研究等,能显著提升开发效率,让开发者更轻松地利用 OpenAI 的技术优势。

Hunyuan3D-2

Hunyuan3D-2

高分辨率纹理 3D 资产生成

Hunyuan3D-2 是腾讯开发的用于 3D 资产生成的强大工具,支持从文本描述、单张图片或多视角图片生成 3D 模型,具备快速形状生成能力,可生成带纹理的高质量 3D 模型,适用于多个领域,为 3D 创作提供了高效解决方案。

3FS

3FS

一个具备存储、管理和客户端操作等多种功能的分布式文件系统相关项目。

3FS 是一个功能强大的分布式文件系统项目,涵盖了存储引擎、元数据管理、客户端工具等多个模块。它支持多种文件操作,如创建文件和目录、设置布局等,同时具备高效的事件循环、节点选择和协程池管理等特性。适用于需要大规模数据存储和管理的场景,能够提高系统的性能和可靠性,是分布式存储领域的优质解决方案。

TRELLIS

TRELLIS

用于可扩展和多功能 3D 生成的结构化 3D 潜在表示

TRELLIS 是一个专注于 3D 生成的项目,它利用结构化 3D 潜在表示技术,实现了可扩展且多功能的 3D 生成。项目提供了多种 3D 生成的方法和工具,包括文本到 3D、图像到 3D 等,并且支持多种输出格式,如 3D 高斯、辐射场和网格等。通过 TRELLIS,用户可以根据文本描述或图像输入快速生成高质量的 3D 资产,适用于游戏开发、动画制作、虚拟现实等多个领域。

ai-agents-for-beginners

ai-agents-for-beginners

10 节课教你开启构建 AI 代理所需的一切知识

AI Agents for Beginners 是一个专为初学者打造的课程项目,提供 10 节课程,涵盖构建 AI 代理的必备知识,支持多种语言,包含规划设计、工具使用、多代理等丰富内容,助您快速入门 AI 代理领域。

AEE

AEE

AI Excel全自动制表工具

AEE 在线 AI 全自动 Excel 编辑器,提供智能录入、自动公式、数据整理、图表生成等功能,高效处理 Excel 任务,提升办公效率。支持自动高亮数据、批量计算、不规则数据录入,适用于企业、教育、金融等多场景。

UI-TARS-desktop

UI-TARS-desktop

基于 UI-TARS 视觉语言模型的桌面应用,可通过自然语言控制计算机进行多模态操作。

UI-TARS-desktop 是一款功能强大的桌面应用,基于 UI-TARS(视觉语言模型)构建。它具备自然语言控制、截图与视觉识别、精确的鼠标键盘控制等功能,支持跨平台使用(Windows/MacOS),能提供实时反馈和状态显示,且数据完全本地处理,保障隐私安全。该应用集成了多种大语言模型和搜索方式,还可进行文件系统操作。适用于需要智能交互和自动化任务的场景,如信息检索、文件管理等。其提供了详细的文档,包括快速启动、部署、贡献指南和 SDK 使用说明等,方便开发者使用和扩展。

Wan2.1

Wan2.1

开源且先进的大规模视频生成模型项目

Wan2.1 是一个开源且先进的大规模视频生成模型项目,支持文本到图像、文本到视频、图像到视频等多种生成任务。它具备丰富的配置选项,可调整分辨率、扩散步数等参数,还能对提示词进行增强。使用了多种先进技术和工具,在视频和图像生成领域具有广泛应用前景,适合研究人员和开发者使用。

爱图表

爱图表

全流程 AI 驱动的数据可视化工具,助力用户轻松创作高颜值图表

爱图表(aitubiao.com)就是AI图表,是由镝数科技推出的一款创新型智能数据可视化平台,专注于为用户提供便捷的图表生成、数据分析和报告撰写服务。爱图表是中国首个在图表场景接入DeepSeek的产品。通过接入前沿的DeepSeek系列AI模型,爱图表结合强大的数据处理能力与智能化功能,致力于帮助职场人士高效处理和表达数据,提升工作效率和报告质量。

Qwen2.5-VL

Qwen2.5-VL

一款强大的视觉语言模型,支持图像和视频输入

Qwen2.5-VL 是一款强大的视觉语言模型,支持图像和视频输入,可用于多种场景,如商品特点总结、图像文字识别等。项目提供了 OpenAI API 服务、Web UI 示例等部署方式,还包含了视觉处理工具,有助于开发者快速集成和使用,提升工作效率。

下拉加载更多