Journal Article10.48550/arXiv.2303.08061
Point Cloud Diffusion Models for Automatic Implant Generation
TL;DR: In this paper , a combination of 3D point cloud diffusion models and voxelization networks is proposed for implant generation based on a stochastic sampling process in their diffusion model, from which the physicians can choose the most suitable one.
read more
Abstract: Advances in 3D printing of biocompatible materials make patient-specific implants increasingly popular. The design of these implants is, however, still a tedious and largely manual process. Existing approaches to automate implant generation are mainly based on 3D U-Net architectures on downsampled or patch-wise data, which can result in a loss of detail or contextual information. Following the recent success of Diffusion Probabilistic Models, we propose a novel approach for implant generation based on a combination of 3D point cloud diffusion models and voxelization networks. Due to the stochastic sampling process in our diffusion model, we can propose an ensemble of different implants per defect, from which the physicians can choose the most suitable one. We evaluate our method on the SkullBreak and SkullFix datasets, generating high-quality implants and achieving competitive evaluation scores.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Fig. 1. Proposed implant generation method with shape reconstruction in point cloud space. The implant geometry I is defined as the Boolean subtraction between completed output Sc and defective input Sd in voxel space. 
Table 1. Architecture of the proposed point cloud diffusion model. The input point cloud is subsequently passed through SA1-4, FP1-4 and a MLP. Time embedding is concatenated to the point features in front of every SA & FP block. 
Fig. 3. Different implants, mean implant and variance map for a single skull defect. 
Fig. 5. Results of our method for the five defect classes of the SkullBreak dataset. 
Fig. 6. Different implants, mean implant and variance map for a single skull defect. 
Fig. 2. Conditional diffusion model for anatomy reconstruction in point cloud space. Points belonging to the defective anatomical structure c0 are shown in color and remain unchanged throughout the whole process. The forward and reverse diffusion processes therefore only affect the gray points x̃0:T belonging to the implant.
Citations
MedShapeNet - A Large-Scale Dataset of 3D Medical Shapes for Computer Vision
Jianning Li,Antonio Pepe,Christina Gsaxner,Gijs Luijten,Yuan Jin,Narmada Ambigapathy,Enrico Nasca,Naida Solak,Gianluca Melito,Afaque Rafique Memon,Xiaojun Chen,Jan Stefan Kirschke,E. D. L. Rosa,Patrich Ferndinand Christ,Hongwei Li,David G. Ellis,Michele R. Aizenberg,Sergios Gatidis,T Kuestner,Nadezhda P. Shusharina,Nicholas Heller,Vincent Andrearczyk,Adrien Depeursinge,Mathieu Hatt,Anjany Sekuboyina,Maximilian Loeffler,Hans Liebl,Reuben Dorent,Tom Vercauteren,Jonathan Shapey,Aaron Kujawa,S. Cornelissen,P. Langenhuizen,Achraf Ben-Hamadou,Ahmed Rekik,Sergi Pujades,Edmond Boyer,Federico Bolelli,Costantino Grana,Luca Lumetti,H. Salehi,Junlin Ma,Yao Zhang,Ramtin Gharleghi,Susann Beier,Eduardo A. Garza-Villarreal,Thania Balducci,Diego Angeles-Valdez,Roberto Souza,Leticia Rittner,Richard Frayne,Yuanfeng Ji,Soumick Chatterjee,A. Nuernberger,João Pedrosa,Carlos Arthur Ferreira,Guilherme Aresta,António Cunha,Aurélio Campilho,Yannick Suter,José Aznarez García,Alain Lalande,Emmanuel Audenaert,Claudia Krebs,T. V. Leeuwen,Evie Vereecke,Rainer Roehrig,F. Hoelzle,Vahid Badeli,Kathrin Krieger,Matthias Gunzer,Jianxu Chen,Amin Dada,M. Balzer,Jana Fragemann,F. Jonske,Moritz Rempe,Stanislav Malorodov,Fin Bahnsen,Constantin Seibold,A. Jaus,Ana Sofia Santos,M. Lindo,André Paulo Ferreira,V. Alves,Michael Kamp,Amr U Abourayya,Felix Nensa,Fabian Hoerst,Alexandra Brehmer,Lukas Heine,Lars Erik Podleska,Mathias Fink,J. Keyl,Konstantinos Tserpes,Moon-Sung Kim,Shireen Y. Elhabian,Hans Lamecker,Dzenan Zukic,Beatriz Paniagua,Christian Wachinger,Martin Urschler,Luc Duong,Jakob Wasserthal,Peter F. Hoyer,Oliver Basu,Thomas J.J. Maal,Max J. H. Witjes,Pingshan Luo,Bjoern H. Menze,Mauricio Reyes,Christos Davatzikos,Behrus Puladi,Jens Kleesiek,Jan Egger +114 more
TL;DR: This work presents a large collection of anatomical shapes and 3D models of surgical instrument, called MedShapeNet, created to facilitate the translation of data-driven vision algorithms to medical applications and to adapt SOTA vision algorithms from computer vision to medical problems.
16
RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model
Fengxiang Bie,Yibo Yang,Zhongzhu Zhou,Adam Ghanem,Minjia Zhang,Zhewei Yao,Xiaoxia Wu,Connor Holmes,Pareesa Ameneh Golnari,David A. Clifton,Yuxiong He,Dacheng Tao,S. Song +12 more
TL;DR: It is argued that TTI development could yield impressive productivity improvements for creation, particularly in the context of the AIGC era, and could be extended to more complex tasks such as video generation and 3D generation.
SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Images
Krithika Iyer,Jadie Adams,Shireen Elhabian +2 more
- 27 Apr 2024
TL;DR: SCorP directly predicts surface-based correspondences from unsegmented medical images, eliminating the need for optimized shape models and alleviating the linearity assumption.
AI-Enhanced Virtual Reality in Medicine: A Comprehensive Survey
Yixuan Wu,Kaiyuan Hu,Danny Z. Chen,Jian Wu +3 more
TL;DR: This is the first systematic survey of AI-powered VR systems in medical settings, laying a foundation for future research in this interdisciplinary domain and introducing a systematic taxonomy.
3
Large Intestine 3D Shape Refinement Using Point Diffusion Models for Digital Phantom Generation
Kaouther Mouheb,Mobina Ghojogh Nejad,Lavsen Dahal,Ehsan Samei,William P. Segars,Joseph Y. Lo +5 more
TL;DR: By combining geometric deep learning, denoising diffusion models, and advanced surface reconstruction techniques, the proposed method offers a promising solution for accurately modeling the large intestine's surface and can easily be extended to other anatomical structures.
References
Marching cubes: A high resolution 3D surface construction algorithm
William E. Lorensen,Harvey E. Cline +1 more
- 01 Aug 1987
TL;DR: In this paper, a divide-and-conquer approach is used to generate inter-slice connectivity, and then a case table is created to define triangle topology using linear interpolation.
•Posted Content
Denoising Diffusion Probabilistic Models
TL;DR: High quality image synthesis results are presented using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics, which naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding.
•Posted Content
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
TL;DR: A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly.
•Posted Content
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
TL;DR: This work develops an approach to systematically and slowly destroy structure in a data distribution through an iterative forward diffusion process, then learns a reverse diffusion process that restores structure in data, yielding a highly flexible and tractable generative model of the data.
•Posted Content
Denoising Diffusion Implicit Models
TL;DR: Denoising diffusion implicit models (DDIMs) are presented, a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs that can produce high quality samples faster and perform semantically meaningful image interpolation directly in the latent space.
3.8K