Building 3D In-Context Learning Universal Model in Neuroimaging

• URL: http://arxiv.org/abs/2503.02410v1
• Date: Tue, 04 Mar 2025 08:51:44 GMT
• Title: Building 3D In-Context Learning Universal Model in Neuroimaging
• Authors: Jiesi Hu, Hanyang Peng, Yanwu Yang, Xutao Guo, Yang Shang, Pengcheng Shi, Chenfei Ye, Ting Ma,
• Abstract summary: In-context learning (ICL), a type of universal model, demonstrates exceptional generalization across a wide range of tasks without retraining.<n>Existing ICL models, which take 2D images as input, struggle to fully leverage the 3D anatomical structures in neuroimages.<n>We introduce Neuroverse3D, an ICL model capable of performing multiple neuroimaging tasks in 3D.
• Score: 6.777213578517701
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In-context learning (ICL), a type of universal model, demonstrates exceptional generalization across a wide range of tasks without retraining by leveraging task-specific guidance from context, making it particularly effective for the complex demands of neuroimaging. However, existing ICL models, which take 2D images as input, struggle to fully leverage the 3D anatomical structures in neuroimages, leading to a lack of global awareness and suboptimal performance. In this regard, we introduce Neuroverse3D, an ICL model capable of performing multiple neuroimaging tasks (e.g., segmentation, denoising, inpainting) in 3D. Neuroverse3D overcomes the large memory consumption due to 3D inputs through adaptive parallel-sequential context processing and a U-shape fusion strategy, allowing it to handle an unlimited number of context images. Additionally, we propose an optimized loss to balance multi-task training and enhance the focus on anatomical structures. Our study incorporates 43,674 3D scans from 19 neuroimaging datasets and evaluates Neuroverse3D on 14 diverse tasks using held-out test sets. The results demonstrate that Neuroverse3D significantly outperforms existing ICL models and closely matches the performance of task-specific models. The code and model weights are publicly released at: https://github.com/jiesihu/Neu3D.

Related papers

• Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes [65.22070581594426]
  "Implicit-Zoo" is a large-scale dataset requiring thousands of GPU training days to facilitate research and development in this field. We showcase two immediate benefits as it enables to: (1) learn token locations for transformer models; (2) directly regress 3D cameras poses of 2D images with respect to NeRF models. This in turn leads to an improved performance in all three task of image classification, semantic segmentation, and 3D pose regression, thereby unlocking new avenues for research.
  arXiv  Detail & Related papers  (2024-06-25T10:20:44Z)
• Self-Supervised Pretext Tasks for Alzheimer's Disease Classification using 3D Convolutional Neural Networks on Large-Scale Synthetic Neuroimaging Dataset [11.173478552040441]
  Alzheimer's Disease (AD) induces both localised and widespread neural degenerative changes throughout the brain. In this work, we evaluated several unsupervised methods to train a feature extractor for downstream AD vs. CN classification.
  arXiv  Detail & Related papers  (2024-06-20T11:26:32Z)
• Brain3D: Generating 3D Objects from fMRI [76.41771117405973]
  We design a novel 3D object representation learning method, Brain3D, that takes as input the fMRI data of a subject. We show that our model captures the distinct functionalities of each region of human vision system. Preliminary evaluations indicate that Brain3D can successfully identify the disordered brain regions in simulated scenarios.
  arXiv  Detail & Related papers  (2024-05-24T06:06:11Z)
• Boosting 3D Neuron Segmentation with 2D Vision Transformer Pre-trained on Natural Images [10.790999324557179]
  We propose a novel training paradigm that leverages a 2D Vision Transformer model pre-trained on large-scale natural images. Our method builds a knowledge sharing connection between the abundant natural and the scarce neuron image domains to improve the 3D neuron segmentation ability. Evaluated on a popular benchmark, BigNeuron, our method enhances neuron segmentation performance by 8.71% over the model trained from scratch.
  arXiv  Detail & Related papers  (2024-05-04T14:57:28Z)
• MinD-3D: Reconstruct High-quality 3D objects in Human Brain [50.534007259536715]
  Recon3DMind is an innovative task aimed at reconstructing 3D visuals from Functional Magnetic Resonance Imaging (fMRI) signals. We present the fMRI-Shape dataset, which includes data from 14 participants and features 360-degree videos of 3D objects. We propose MinD-3D, a novel and effective three-stage framework specifically designed to decode the brain's 3D visual information from fMRI signals.
  arXiv  Detail & Related papers  (2023-12-12T18:21:36Z)
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm [114.47216525866435]
  We introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation. For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness.
  arXiv  Detail & Related papers  (2023-10-12T17:59:57Z)
• Deep Generative Models on 3D Representations: A Survey [81.73385191402419]
  Generative models aim to learn the distribution of observed data by generating new instances. Recently, researchers started to shift focus from 2D to 3D space. representing 3D data poses significantly greater challenges.
  arXiv  Detail & Related papers  (2022-10-27T17:59:50Z)
• Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training [45.90045513731704]
  This paper revisits an innovative yet simple fully-supervised 3D network pre-training framework. With a redesigned 3D network architecture, reformulated natural images are used to address the problem of data scarcity. Comprehensive experiments on four benchmark datasets demonstrate that the proposed pre-trained models can effectively accelerate convergence.
  arXiv  Detail & Related papers  (2022-01-05T03:11:21Z)
• CAN3D: Fast 3D Medical Image Segmentation via Compact Context Aggregation [6.188937569449575]
  We present a compact convolutional neural network with a shallow memory footprint to efficiently reduce the number of model parameters required for state-of-art performance. The proposed network can maintain data integrity by directly processing large full-size 3D input volumes with no patches required.
  arXiv  Detail & Related papers  (2021-09-12T06:27:59Z)
• Medical Transformer: Universal Brain Encoder for 3D MRI Analysis [1.6287500717172143]
  Existing 3D-based methods have transferred the pre-trained models to downstream tasks. They demand a massive amount of parameters to train the model for 3D medical imaging. We propose a novel transfer learning framework, called Medical Transformer, that effectively models 3D volumetric images in the form of a sequence of 2D image slices.
  arXiv  Detail & Related papers  (2021-04-28T08:34:21Z)
• Neural Descent for Visual 3D Human Pose and Shape [67.01050349629053]
  We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end. Central to our methodology, is a learning to learn and optimize approach, referred to as HUmanNeural Descent (HUND), which avoids both second-order differentiation.
  arXiv  Detail & Related papers  (2020-08-16T13:38:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.