π₯π₯ This is a collection of awesome articles about Implicit Neural Representation networks in medical imagingπ₯π₯
π’ Our review paper published on arXiv: Implicit Neural Representation in Medical Imaging: A Comparative Survey β€οΈ
@inproceedings{molaei2023implicit,
title={Implicit neural representation in medical imaging: A comparative survey},
author={Molaei, Amirali and Aminimehr, Amirhossein and Tavakoli, Armin and Kazerouni, Amirhossein and Azad, Bobby and Azad, Reza and Merhof, Dorit},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={2381--2391},
year={2023}
}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.
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.
We considered a sum of 86 research papers spanning from 2021 to 2023.
- Image Reconstruction
- Image Segmentation
- Image Registration
- Neural Rendering
- Image Compression
- Image Synthesis
(Each section is ordered by the publication dates)
-
π IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction
- ποΈ Publication Date: 9th Feb. 2021
- π Proceedings: IEEE/CVF International Conference on Computer Vision, 2021
- π§βπ¬ Authors: Guangming Zang, Ramzi Idoughi, Rui Li, Peter Wonka, Wolfgang Heidrich
- π PDF
- π 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.
-
π CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
- ποΈ Publication Date: 9th Feb. 2021
- π Journal: IEEE Transactions on Computational Imaging, 2021
- π§βπ¬ Authors: Yu Sun, Jiaming Liu, Mingyang Xie, Brendt Wohlberg, Ulugbek S. Kamilov
- π PDF
- π» GitHub
- π Highlight: Takes measurement coordinates, such as view angle ΞΈ 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.
-
π Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields
- ποΈ Publication Date: 23th Apr. 2021
- π Proceedings: IEEE/CVF International Conference on Computer Vision, 2021
- π§βπ¬ Authors: Albert W. Reed, Hyojin Kim, Rushil Anirudh, K. Aditya Mohan, Kyle Champley, Jingu Kang, Suren Jayasuriya
- π PDF
- π 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.
-
π Neural Computed Tomography
-
π Streak artifacts reduction algorithm using an implicit neural representation in sparse-view CT
- ποΈ Publication Date: 4th Apr. 2022
- π Conference: Medical Imaging 2022: Physics of Medical Imaging, 2022
- π§βπ¬ Authors: Byeongjoon Kim, Hyunjung Shim, Jongduk Baek
- π PDF
-
π Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography
-
π OReX: Object Reconstruction from Planar Cross-sections Using Neural Fields
-
π NeuRec: Incorporating Interpatient prior to Sparse-View Image Reconstruction for Neurorehabilitation
- ποΈ Publication Date: 21th Feb. 2022
- π Journal: BioMed Research International, 2022
- π§βπ¬ Authors: Cong Liu, Qingbin Wang, Jing Zhang
- π PDF
-
π MEPNet: A Model-Driven Equivariant Proximal Network for Joint Sparse-View Reconstruction and Metal Artifact Reduction in CT Images.
-
π UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography
-
π Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction
- ποΈ Publication Date: 27th Jun. 2023
- π Preprint: arXiv
- π§βπ¬ Authors: Qing Wu, Lixuan Chen, Ce Wang, Hongjiang Wei, S. Kevin Zhou, Jingyi Yu, Yuyao Zhang
- π PDF
-
π NAISR: A 3D Neural Additive Model for Interpretable Shape Representation
-
π An Arbitrary Scale Super-Resolution Approach for 3-Dimensional Magnetic Resonance Image using Implicit Neural Representation
-
π IREM: High-Resolution Magnetic Resonance (MR) Image Reconstruction via Implicit Neural Representation
- ποΈ Publication Date: 29th Jun. 2021
- π§βπ¬ Authors: Qing Wu, Yuwei Li, Lan Xu, Ruiming Feng, Hongjiang Wei, Qing Yang, Boliang Yu, Xiaozhao Liu, Jingyi Yu, Yuyao Zhang
- π PDF
-
π MRI Super-Resolution using Implicit Neural Representation with Frequency Domain Enhancement
- ποΈ Publication Date: Aug. 2022
- π§βπ¬ Authors: Shuangming Mao, Seiichiro Kamata
- π PDF
-
π NeSVoR: Implicit Neural Representation for Slice-to-Volume Reconstruction in MRI
-
π Spatiotemporal implicit neural representation for unsupervised dynamic MRI reconstruction
- ποΈ Publication Date: 31th Dec. 2022
- π§βπ¬ Authors: Jie Feng, Ruimin Feng, Qing Wu, Zhiyong Zhang, Yuyao Zhang, Hongjiang Wei
- π [PDF](Link to PDF)
-
π Neural Implicit k-Space for Binning-free Non-Cartesian Cardiac MR Imaging
- ποΈ Publication Date: 16th Dec. 2022
- π Conference: International Conference on Information Processing in Medical Imaging, 2023
- π§βπ¬ Authors: Wenqi Huang, Hongwei Li, Jiazhen Pan, Gastao Cruz, Daniel Rueckert, Kerstin Hammernik
- π PDF
-
π Continuous longitudinal fetus brain atlas construction via implicit neural representation
- ποΈ Publication Date: 14th Sep. 2022
- π§βπ¬ Authors: Lixuan Chen, Jiangjie Wu, Qing Wu, Hongjiang Wei, Yuyao Zhang
- π PDF
-
π Multi-contrast MRI Super-resolution via Implicit Neural Representations
- ποΈ Publication Date: 27th Mar. 2023
- π Conference: MICCAI, 2023
- π§βπ¬ Authors: Julian McGinnis, Suprosanna Shit, Hongwei Bran Li, Vasiliki Sideri-Lampretsa, Robert Graf, Maik Dannecker, Jiazhen Pan, Nil Stolt AnsΓΆ, Mark MΓΌhlau, Jan S. Kirschke, Daniel Rueckert, Benedikt Wiestler
- π PDF
- π» GitHub
-
π Streak artifacts reduction algorithm using an implicit neural representation in sparse-view CT.
- π Publication Date: 4th Apr., 2022
- π Journal: Medical Imaging 2022: Physics of Medical Imaging, 2022
- π§βπ¬ Authors: Byeongjoon Kim, Hyunjung Shim, Jongduk Baek.
- π PDF
-
π Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing
-
π A scan-specific unsupervised method for parallel MRI reconstruction via implicit neural representation
- ποΈ Publication Date: 19th Oct. 2022
- π§βπ¬ Authors: Ruimin Feng, Qing Wu, Yuyao Zhang, Hongjiang Wei
- π PDF
-
π Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI
-
π Unsupervised reconstruction of accelerated cardiac cine MRI using Neural Fields
- ποΈ Publication Date: 24th Jul. 2023
- π Preprint: arxiv
- π§βπ¬ Authors: Tabita CatalΓ‘n, MatΓas Courdurier, Axel Osses, RenΓ© Botnar, Francisco Sahli Costabal, Claudia Prieto
- π PDF
- π» GitHub
- π Highlight: An unsupervised INR approach that uses the spatio-temporal Fourier Features of the heart's motion.
-
π Self-supervised arbitrary scale super-resolution framework for anisotropic MRI
- ποΈ Publication Date: 2th May. 2023
- π§βπ¬ Authors: Haonan Zhang, Yuhan Zhang, Qing Wu, Jiangjie Wu, Zhiming Zhen, Feng Shi, Jianmin Yuan, Hongjiang Wei, Chen Liu, Yuyao Zhang
- π PDF
-
π Implicit Neural Networks with Fourier-Feature Inputs for Free-breathing Cardiac MRI Reconstruction
-
π Implicit neural representations for unsupervised super-resolution and denoising of 4D flow MRI
- ποΈ Publication Date: 24th Feb. 2023
- π§βπ¬ Authors: Simone Saitta, Marcello Carioni, Subhadip Mukherjee, Carola-Bibiane SchΓΆnlieb, Alberto Redaelli
- π PDF
-
π CoNeS: Conditional neural fields with shift modulation for multi-sequence MRI translation.
-
π Batch Implicit Neural Representation for MRI Parallel Reconstruction.
- π Publication Date: 13th Sep., 2023
- π Preprint: arxiv
- π§βπ¬ Authors: Hao Li, Yusheng Zhou, Jianan Liu, Xiling Liu, Tao Huang, Zhihan Lv.
- π PDF
- π Highlight: Uses INR to parametrize fully-sampled MRI images as continuous functions, enhanced by a scale-embedded encoder for scale-independent feature production.
-
π 3D cine-magnetic resonance imaging using spatial and temporal implicit neural representation learning (STINR-MR).
- π Publication Date: 13th Sep., 2023
- π Preprint: arxiv
- π§βπ¬ Authors: Hua-Chieh Shao, Tielige Mengke, Jie Deng, and You Zhang.
- π PDF
- π Highlight: The spatial implicit neural representation network maps 3D spatial coordinates to MR values, while the temporal implicit neural representation encodes time points to create dynamic motion fields
-
π NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstruction
-
π CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution
- ποΈ Publication Date: 28th Mar. 2023
- π Conference: ICCV, 2023
- π§βπ¬ Authors: Zixuan Chen, Jianhuang Lai, Lingxiao Yang, Xiaohua Xie
- π PDF
-
π ImplicitVol: Sensorless 3D Ultrasound Reconstruction with Deep Implicit Representation
- ποΈ Publication Date: 24th Sep. 2021
- π Preprint: arXiv
- π§βπ¬ Authors: Pak-Hei Yeung, Linde Hesse, Moska Aliasi, Monique Haak, the INTERGROWTH-21st Consortium, Weidi Xie, Ana I.L. Namburete
- π PDF
-
π Representing 3D Ultrasound with Neural Fields
- ποΈ Publication Date: 21st Apr. 2022
- π Conference: Medical Imaging with Deep Learning, 2022
- π§βπ¬ Authors: Ang Nan Gu, Purang Abolmaesumi, Christina Luong, Kwang Moo Yi
- π PDF
-
π Going Off-Grid: Continuous Implicit Neural Representations for 3D Vascular Modeling
- ποΈ Publication Date: 16th Sep. 2022
- π Preprint: arXiv
- π§βπ¬ Authors: Dieuwertje Alblas, Christoph Brune, Kak Khee Yeung, Jelmer M. Wolterink
- π PDF
-
π Implicit Neural Representations for Breathing-compensated Volume Reconstruction in Robotic Ultrasound Aorta Screening
- ποΈ Publication Date: 8th Nov. 2023
- π Preprint: arXiv
- π§βπ¬ Authors: Yordanka Velikova, Mohammad Farid Azampour, Walter Simson, Marco Esposito, Nassir Navab
- π PDF
-
π Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow.
-
π Dynamic Cone-beam CT Reconstruction using Spatial and Temporal Implicit Neural Representation Learning (STINR).
- π Publication Date: Sep., 2022
- π Journal: Physics in Medicine and Biology, 2023
- π§βπ¬ Authors: You Zhang, Hua-Chieh Shao, Tinsu Pan, Tielige Mengke.
- π PDF
-
π Learning Deep Intensity Field for Extremely Sparse-View CBCT Reconstruction.
-
π A Memory-Efficient Dynamic Image Reconstruction Method using Neural Fields.
- ποΈ Publication Date: 11th May. 2022
- π§βπ¬ Authors: Luke Lozenski, Mark A. Anastasio, Umberto Villa
- π PDF
- π Highlight: The "Partition of Unity Network" (POUnet) is employed as a specialized neural field architecture to reconstruct dynamic biomedical images, which allows it to optimize against indirect and possibly noisy measurements, ensuring enhanced accuracy in dynamically evolving imaging scenarios.
-
π Going Off-Grid: Continuous Implicit Neural Representations for 3D Vascular Modeling
- ποΈ Publication Date: 16th Sep. 2022
- π§βπ¬ Authors: Dieuwertje Alblas, Christoph Brune, Kak Khee Yeung, Jelmer M. Wolterink
- π PDF
-
π Implicitatlas: learning deformable shape templates in medical imaging
- ποΈ Publication Date: CVPR, 2022
- π§βπ¬ Authors: Jiancheng Yang, Udaranga Wickramasinghe, Bingbing Ni, Pascal Fua
- π PDF
-
π MiShape: 3D Shape Modelling of Mitochondria in Microscopy
- ποΈ Publication Date: 2nd Mar. 2023
- π§βπ¬ Authors: Abhinanda R. Punnakkal, Suyog S Jadhav, Alexander Horsch, Krishna Agarwal, Dilip K. Prasad
- π PDF
-
π Hybrid Neural Diffeomorphic Flow for Shape Representation and Generation via Triplane
- ποΈ Publication Date: 4th Jul. 2023
- π§βπ¬ Authors: Kun Han, Shanlin Sun, Xiaohui Xie
- π PDF
-
π Hybrid-CSR: Coupling Explicit and Implicit Shape Representation for Cortical Surface Reconstruction
- ποΈ Publication Date: 23rd Jul. 2023
- π§βπ¬ Authors: Shanlin Sun, Thanh-Tung Le, Chenyu You, Hao Tang, Kun Han, Haoyu Ma, Deying Kong, Xiangyi Yan, Xiaohui Xie
- π PDF
-
π A self-supervised learning approach for high-resolution diffuse optical tomography using neural fields.
- ποΈ Publication Date: 28th Jul. 2023
- π Conference: Proc. SPIE 12753, Second Conference on Biomedical Photonics and Cross-Fusion (BPC 2023)
- π§βπ¬ Authors: Linlin Li, Siyuan Shen, Shengyu Gao, Yuehan Wang, Liangtao Gu, Shiying Li, Xingjun Zhu, Jiahua Jiang, Jingyi Yu, Wuwei Ren
- π PDF
- π Highlight: A diffuse optical tomography (DOT) reconstructio approach where it translates spatial coordinates to the optical absorption coefficients they correspond to.
-
π INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings.
- ποΈ Publication Date: 28th Oct. 2023
- π Conference: WACV, 2024
- π§βπ¬ Authors: Amirhossein Kazerouni, Reza Azad, Alireza Hosseini, Dorit Merhof, Ulas Bagci
- π PDF
-
π NeRD: Neural Representation of Distribution for Medical Image Segmentation
- π Publication Date: 6th Mar., 2021
- π Preprint: arXiv, 2021
- π§βπ¬ Authors: Hang Zhang, Rongguang Wang, Jinwei Zhang, Chao Li, Gufeng Yang, Pascal Spincemaille, Thanh Nguyen, Yi Wang
- π PDF
- π Highlight: Addresses white matter lesion segmentation and left atrial segmentation.
-
π Implicit field learning for unsupervised anomaly detection in medical images
- π Publication Date: 9th Jun., 2021
- π Conference: MICCAI 2021
- π§βπ¬ Authors: Sergio Naval Marimont, Giacomo Tarroni
- π PDF
- π Highlight: Aims to localize gliomas on brain MR images using an unsupervised out-of-distribution detection method.
-
π Direct localization and delineation of human pedunculopontine nucleus based on a self-supervised magnetic resonance image super-resolution method
- π Publication Date: 25th Apr., 2023
- π Journal: Human Brain Mapping, 2023
- π§βπ¬ Authors: Jun Li, Xiaojun Guan, Qing Wu, Chenyu He, Weimin Zhang, Xiyue Lin, Chunlei Liu, Hongjiang Wei, Xiaojun Xu, Yuyao Zhang
- π PDF
- π Highlight: Focuses on delineating the pedunculopontine nucleus (PPN).
-
π Binary segmentation of medical images using implicit spline representations and deep learning
- π Publication Date: 19th Mar., 2021
- π Journal: Computer Aided Geometric Design, 2021
- π§βπ¬ Authors: Oliver J.D. Barrowclough, Georg Muntingh, Varatharajan Nainamalai, Ivar Stangeby
- π PDF
- π Highlight: Tackles image segmentation for a congenital heart disease computed tomography medical imaging dataset.
-
π NISF: Neural Implicit Segmentation Functions
- π Retinal vessel segmentation based on self-distillation and implicit neural representation
- π Publication Date: 8th Nov., 2022
- π Journal: Applied Intelligence, 2022
- π§βπ¬ Authors: Jia Gu, Fangzheng Tian & Il-Seok Oh
- π PDF
- π Highlight: Concentrates on segmenting retinal blood vessels from retinal images.
-
π Deep Implicit Statistical Shape Models for 3D Medical Image Delineation
- π Publication Date: 28th Jun., 2022
- π Conference: AAAI, 2022
- π§βπ¬ Authors: Ashwin Raju, Shun Miao, Dakai Jin, Le Lu, Junzhou Huang, Adam P. Harrison
- π PDF
- π₯οΈ GitHub
- π Highlight: Presents a methodology that emphasizes 3D delineation of anatomical structures using deep implicit statistical shape models.
-
π Implicit Neural Representations for Medical Imaging Segmentation
- π Publication Date: 16th Sep., 2022
- π Conference: International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022
- π§βπ¬ Authors: Muhammad Osama Khan & Yi Fang
- π PDF
- π Highlight: Specifically mentions 3D signals in medical imaging, hinting at 3D anatomical structures.
-
π Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts
-
π I-MedSAM: Implicit Medical Image Segmentation with Segment Anything
- π Publication Date: 28th Nov., 2023
- π Preprint: arXiv, 2023
- π§βπ¬ Authors: Xiaobao Wei, Jiajun Cao, Yizhu Jin, Ming Lu, Guangyu Wang, Shanghang Zhang
- π PDF
- π SwIPE: Efficient and Robust Medical Image Segmentation with Implicit Patch Embeddings
- π Publication Date: 23rd Jul., 2023
- π Conference: MICCAI 2023
- π§βπ¬ Authors: Yejia Zhang, Pengfei Gu, Nishchal Sapkota, Danny Z. Chen
- π PDF
- π Highlight: Uses implicit neural representations to predict shapes at the patch level, balancing both local boundary delineation and global shape coherence.
-
π Implicit Neural Representations for Deformable Image Registration
- π Publication Date: 22th Jun., 2022
- π Conference: Medical Imaging with Deep Learning, 2022
- π§βπ¬ Authors: Jelmer M. Wolterink, Jesse C. Zwienenberg, Christoph Brune
- π PDF
- π₯οΈ GitHub
- π Highlight: Implicit deformable image registration using a neural network to represent continuous transformations
-
π Learning Homeomorphic Image Registration via Conformal-Invariant Hyperelastic Regularisation
- π Publication Date: 30th Jun., 2023
- π Preprint: arXiv, 2023
- π§βπ¬ Authors: Jing Zou, NoΓ©mie Debroux, Lihao Liu, Jing Qin, Carola-Bibiane SchΓΆnlieb, Angelica I Aviles-Rivero
- π PDF
- π Highlight: Topology-preserving deformable image registration. It discusses a novel regularizer based on conformal-invariant properties.
-
π Deformable Image Registration with Geometry-informed Implicit Neural Representations
- π Publication Date: 13th Apr., 2023
- π Conference: Medical Imaging with Deep Learning, 2023
- π§βπ¬ Authors: Louis van Harten, Rudolf Leonardus Mirjam Van Herten, Jaap Stoker, Ivana Isgum
- π PDF
- π Highlight: Parameterizes the deformation field by incorporating the geometry encoding of anatomical structures to guide the deformation process.
-
π Implicit neural representations for joint decomposition and registration of gene expression images in the marmoset brain.
- π Publication Date: 8th Aug., 2023
- π Preprint: arXiv
- π§βπ¬ Authors: Michal Byra, Charissa Poon, Tomomi Shimogori, Henrik Skibbe
- π PDF
- π Highlight: Addresses the registration of brain images with added features or artifacts by emphasizing the decomposition of images into support and residual components.
-
π INR-LDDMM: Fluid-based Medical Image Registration Integrating Implicit Neural Representation and Large Deformation Diffeomorphic Metric Mapping.
- π Publication Date: 18th Aug., 2023
- π Preprint: arXiv
- π§βπ¬ Authors: Chulong Zhang, Xiaokun Liang
- π PDF
- π Highlight: Combines implicit neural representation with Large Deformable Diffeomorphic Metric Mapping (LDDMM) in a coarse-to-fine approach.
-
π Medical Image Registration via Neural Fields
- π Publication Date: 22th Jun., 2022
- π Preprint: arXiv, 2022
- π§βπ¬ Authors: Shanlin Sun, Kun Han, Hao Tang, Deying Kong, Junayed Naushad, Xiangyi Yan, Xiaohui Xie
- π PDF
- π Highlight: Introduces a distinction between general deformable registration and diffeomorphic image registration using neural fields.
-
π Diffeomorphic Image Registration with Neural Velocity Field
- π Publication Date: 2023
- π Conference: IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
- π§βπ¬ Authors: Kun Han, Shanlin Sun, Xiangyi Yan, Chenyu You, Hao Tang, Junayed Naushad, Haoyu Ma, Deying Kong, Xiaohui Xie
- π PDF
- π Highlight: Introduces a cascaded framework for diffeomorphic Image Registration with Neural Velocity Field (DNVF) by modeling the space of transformations.
-
π NePhi: Neural Deformation Fields for Approximately Diffeomorphic Medical Image Registration
- π Publication Date: 13th Sep., 2023
- π Preprint: arXiv
- π§βπ¬ Authors: Lin Tian, Soumyadip Sengupta, Hastings Greer, RaΓΊl San JosΓ© EstΓ©par, Marc Niethammer
- π PDF
-
π Exploring the performance of implicit neural representations for brain image registration
- π Publication Date: 13th Oct., 2023
- π Journal: Scientific Reports
- π§βπ¬ Authors: Michal Byra, Charissa Poon, Muhammad Febrian Rachmadi, Matthias Schlachter, Henrik Skibbe
- π PDF
- π Highlight: Investigated the effectiveness of INRs in enhancing brain image registration within MRI settings
-
π Dynamic Neural Fields for Learning Atlases of 4D Fetal MRI Time-series
- π Publication Date: 6th Nov., 2023
- π Conference: Medical Imaging Meets NeurIPS 2023
- π§βπ¬ Authors: Zeen Chi, Zhongxiao Cong, Clinton J. Wang, Yingcheng Liu, Esra Abaci Turk, P. Ellen Grant, S. Mazdak Abulnaga, Polina Golland, Neel Dey
- π PDF
- π Highlight: The method is primarily focused on registration to enable motion stabilization, but it also uses a form of reconstruction to build the atlas itself from the registered data.
- π MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray.
- π Publication Date: 2nd Feb., 2022
- π Conference: IEEE EMBC, 2022
- π§βπ¬ Authors: Abril Corona-Figueroa, Jonathan Frawley, Sam Bond-Taylor, Sarath Bethapudi, Hubert P. H. Shum, Chris G. Willcocks.
- π PDF
- π₯οΈ Github
- π Highlight: Reconstruct CT projections from a few or a single-view X-ray, based on neural radiance fields. The proposed technique minimizes patients' exposure to ionizing radiation.
-
π NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction.
- π Publication Date: 29th Sep., 2022
- π Conference: MICCAI, 2022
- π§βπ¬ Authors: Ruyi Zha, Yanhao Zhang, Hongdong Li.
- π PDF
- π₯οΈ Github
- π Highlight: A self-supervised approach for CBCT reconstruction that requires no external training data, using a deep neural network to represent attenuation coefficients.
-
π SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields.
- π Publication Date: 30th Nov., 2022
- π Preprint: arXiv
- π§βπ¬ Authors: Yu Fang, Lanzhuju Mei, Changjian Li, Yuan Liu, Wenping Wang, Zhiming Cui, Dinggang Shen.
- π PDF
- π Highlight: Can reconstruct high-quality CBCT images from limited 2D projections, addressing concerns about radiation dose and image quality in dental applications.
- π 3D reconstructions of brain from MRI scans using neural radiance fields.
- π Publication Date: 24th Apr., 2023
- π Preprint: arXiv
- π§βπ¬ Authors: Khadija Iddrisu, Sylwia Malec, Alessandro Crimi.
- π PDF
- π Highlight: Uses neural radiance fields to reconstruct 3D MRI images from 2D MRI slices, aiming to reduce scan acquisition times and potential motion artifacts.
- π TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction.
- π Publication Date: 5th Sep., 2023
- π Preprint: arXiv
- π§βπ¬ Authors: Zhenghong Zhou, Huangxuan Zhao, Jiemin Fang, Dongqiao Xiang, Lei Chen, Lingxia Wu, Feihong Wu, Wenyu Liu, Chuansheng Zheng, Xinggang Wang.
- π PDF
- π Highlight: A method for high-quality sparse-view 4D DSA reconstruction, reducing the required radiation dose and increasing the efficiency of 4D imaging in diagnosing vascular diseases.
-
π Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery.
-
π EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos.
- π Publication Date: 21st Jul., 2023
- π Conference: MICCAI 2023
- π§βπ¬ Authors: Ruyi Zha, Xuelian Cheng, Hongdong Li, Mehrtash Harandi, Zongyuan Ge.
- π PDF
- π₯οΈ Github
- π Highlight: Learns and represents a deforming surface from RGBD sequences captured via endoscope, offering improvements in high-fidelity shape reconstructions.
- π Ultra-NeRF: Neural Radiance Fields for Ultrasound Imaging.
- π Publication Date: 25th Jan., 2023
- π Conference: MIDL, 2023
- π§βπ¬ Authors: Magdalena Wysocki, Mohammad Farid Azampour, Christine Eilers, Benjamin Busam, Mehrdad Salehi, Nassir Navab.
- π PDF
- π Highlight: Introduces a physics-enhanced implicit neural representation for ultrasound imaging which accounts for view-dependent changes in appearance and geometry, improving the quality of synthesized ultrasound images.
- π Oral-NeXF: 3D Oral Reconstruction with Neural X-ray Field from Panoramic Imaging.
- π Publication Date: 21st Mar., 2023
- π Preprint: arxiv
- π§βπ¬ Authors: Weinan Song, Haoxin Zheng, Jiawei Yang, Chengwen Liang, Lei He.
- π PDF
- π Highlight: Proposes a solution for 3D reconstruction of oral structures using a single panoramic X-ray, with a model that learns to represent the 3D oral structure implicitly
- π Robust Single-view Cone-beam X-ray Pose Estimation with Neural Tuned Tomography (NeTT) and Masked Neural Radiance Fields (mNeRF).
- π Publication Date: 1st Aug., 2023
- π Preprint: arxiv
- π§βπ¬ Authors: Chaochao Zhou, Syed Hasib Akhter Faruqui, Abhinav Patel, Ramez N. Abdalla, Michael C. Hurley, Ali Shaibani, Matthew B. Potts, Babak S. Jahromi, Leon Cho, Sameer A. Ansari, Donald R. Cantrell.
- π PDF
- π Highlight: A method for pose estimation of radiolucent objects via X-ray projections. Two high-fidelity view synthesis methods (NeTT and mNeRF) are introduced, with NeTT being highlighted for its computational efficiency and generalization capabilities.
-
π SCI: A Spectrum Concentrated Implicit Neural Compression for Biomedical Data.
- π Publication Date: 23th Nov., 2022
- π Conference: AAAI, 2023
- π§βπ¬ Authors: Runzhao Yang, Tingxiong Xiao, Yuxiao Cheng, Qianni Cao, Jinyuan Qu, Jinli Suo, Qionghai Dai.
- π PDF
- π₯οΈ Github
- π Highlight: Introduces an adaptive partitioning strategy to divide data into spectrum-concentrated blocks, a funnel-shaped INR structure for efficient data compression, and an allocation strategy for INR parameters.
-
π TINC: Tree-structured Implicit Neural Compression.
- π Publication Date: 12th Nov., 2022
- π Preprint: arXiv
- π§βπ¬ Authors: Runzhao Yang, Tingxiong Xiao, Yuxiao Cheng, Jinli Suo, Qionghai Dai.
- π PDF
- π₯οΈ Github
- π Highlight: Uses ensemble learning and a divide-and-conquer approach to compress different regions and organizes the data using a tree structure to extract shared parameters, removing redundancy and ensuring continuity.
-
π COIN++ Neural Compression Across Modalities.
- π Publication Date: 8th Dec ., 2022
- π Preprint: arXiv
- π§βπ¬ Authors: Emilien Dupont, Hrushikesh Loya, Milad Alizadeh, Adam GoliΕski, Yee Whye Teh, Arnaud Doucet.
- π PDF
- π₯οΈ Github
- π Highlight: Uses meta-learning to reduce encoding time and introduces shared structures and modulation for compression across different modalities.
-
π A Novel Implicit Neural Representation for Volume Data
- ποΈ Publication Date: 27th Feb. 2023
- π Journal: Applied Sciences
- π§βπ¬ Authors: Armin Sheibanifard, Hongchuan Yu
- π PDF
- π Highlight: Introduces a new implicit neural representation to compress high-resolution medical volume data and shows high speed and quality in compression compared to existing works.
-
π SINCO: A Novel structural regularizer for image compression using implicit neural representations.
- π Publication Date: 5th May., 2023
- π Conference: IEEE International Conference on Acoustics, Speech and Signal Processing, 2023
- π§βπ¬ Authors: Harry Gao, Weijie Gan, Zhixin Sun, Ulugbek S. Kamilov.
- π PDF
- π Highlight: Uses an MLP to compress images and a segmentation network to predict segmentation masks, along with a structural regularizer to improve Dice scores between original and compressed segmentation maps.
-
π Implicit Neural Representations for Generative Modeling of Living Cell Shapes.
- π Publication Date: 6th Oct., 2022
- π Conference: International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022
- π§βπ¬ Authors: David Wiesner, Julian Suk, Sven Dummer, David Svoboda, Jelmer M. Wolterink.
- π PDF
- π Highlight:
-
π Generative modeling of living cells with SO(3)-equivariant implicit neural representations.
- π Publication Date: 18th Apr., 2023
- π Preprint: arXiv
- π§βπ¬ Authors: David Wiesner, Julian Suk, Sven Dummer, Tereza NeΔasovΓ‘, VladimΓr Ulman, David Svoboda, Jelmer M. Wolterink.
- π PDF
- π Highlight:
