The burgeoning field of brain health research increasingly leverages artificial intelligence (AI) to analyze and interpret neuroimaging data. Medical foundation models have shown promise of superior performance with better sample efficiency. This work introduces a novel approach towards creating 3-dimensional (3D) medical foundation models for multimodal neuroimage segmentation through self-supervised training. Our approach involves a novel two-stage pretraining approach using vision transformers. The first stage encodes anatomical structures in generally healthy brains from the large-scale unlabeled neuroimage dataset of multimodal brain magnetic resonance imaging (MRI) images from 41,400 participants. This stage of pertaining focuses on identifying key features such as shapes and sizes of different brain structures. The second pretraining stage identifies disease-specific attributes, such as geometric shapes of tumors and lesions and spatial placements within the brain. This dual-phase methodology significantly reduces the extensive data requirements usually necessary for AI model training in neuroimage segmentation with the flexibility to adapt to various imaging modalities. We rigorously evaluate our model, BrainSegFounder, using the Brain Tumor Segmentation (BraTS) challenge and Anatomical Tracings of Lesions After Stroke v2.0 (ATLAS v2.0) datasets. BrainSegFounder demonstrates a significant performance gain, surpassing the achievements of the previous winning solutions using fully supervised learning. Our findings underscore the impact of scaling up both the model complexity and the volume of unlabeled training data derived from generally healthy brains. Both of these factors enhance the accuracy and predictive capabilities of the model in neuroimage segmentation tasks. Our pretrained models and code are at https://github.com/lab-smile/BrainSegFounder.

中文翻译：

---

BrainSegFounder：迈向神经图像分割的 3D 基础模型


新兴的大脑健康研究领域越来越多地利用人工智能 (AI) 来分析和解释神经影像数据。医学基础模型已显示出具有卓越性能和更高样本效率的前景。这项工作介绍了一种通过自我监督训练创建用于多模态神经图像分割的 3 维 (3D) 医学基础模型的新颖方法。我们的方法涉及一种使用视觉变换器的新颖的两阶段预训练方法。第一阶段从来自 41,400 名参与者的多模态脑磁共振成像 (MRI) 图像的大规模未标记神经图像数据集中编码一般健康大脑的解剖结构。这一阶段的重点是识别关键特征，例如不同大脑结构的形状和大小。第二个预训练阶段识别疾病特定的属性，例如肿瘤和病变的几何形状以及大脑内的空间位置。这种双阶段方法显着减少了神经图像分割中人工智能模型训练通常所需的大量数据需求，并且能够灵活地适应各种成像模式。我们使用脑肿瘤分割 (BraTS) 挑战和中风后病变解剖追踪 v2.0 (ATLAS v2.0) 数据集严格评估我们的模型 BrainSegFounder。 BrainSegFounder 展示了显着的性能提升，超越了之前使用完全监督学习的获胜解决方案所取得的成就。我们的研究结果强调了扩大模型复杂性和来自一般健康大脑的未标记训练数据量的影响。 这两个因素都增强了模型在神经图像分割任务中的准确性和预测能力。我们的预训练模型和代码位于 https://github.com/lab-smile/BrainSegFounder。