Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI

• URL: http://arxiv.org/abs/2609.06807v1
• Date: Sun, 06 Sep 2026 19:56:53 GMT
• Title: Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI
• Abstract summary: Our study is based on 18 publicly available datasets containing 3D structural T1-weighted MRI scans from approximately 80,000 participants.<n>We observe that a linear model based on anatomical features matches the diagnostic performance of complex nonlinear features learned by sophisticated AI frameworks.<n>We propose a novel method to incorporate anatomical information during foundation pretraining, which outperforms existing models in biological age estimation.
• Score: 11.24842098165914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we comprehensively evaluate three popular feature-extraction paradigms in AI-based neuroimaging modeling: (1) computation of anatomical surfaces and volumes, (2) supervised learning with convolutional neural networks (CNNs), and (3) unsupervised pretraining of vision transformer (ViT) foundation models, followed by supervised finetuning. Our study is based on 18 publicly available datasets containing 3D structural T1-weighted MRI scans from approximately 80,000 participants across seven distinct clinical tasks. We observe that a linear model based on anatomical features matches the diagnostic performance of complex nonlinear features learned by sophisticated AI frameworks, including foundation models trained on thousands of scans. Conversely, CNNs and pretrained ViTs learn features that implicitly capture relevant anatomical information, bypassing the need for explicit feature extraction. Building upon these insights, we propose Anatomy Segmentation Pretraining (ASP), a novel method to incorporate anatomical information during foundation-model pretraining, which outperforms existing models in biological age estimation.

Related papers

• Health system learning achieves generalist neuroimaging models [32.579819110032766]
  We introduce NeuroVFM, a visual foundation model trained on 5.24 million clinical MRI and CT volumes.<n>NeuroVFM learns comprehensive representations of brain anatomy and pathology, achieving state-of-the-art performance across multiple clinical tasks.
  arXiv  Detail & Related papers  (2025-11-23T22:34:50Z)
• Artificial Intelligence in Breast Cancer Care: Transforming Preoperative Planning and Patient Education with 3D Reconstruction [1.5582012249641972]
  preoperative planning requires accurate algorithms for segmenting anatomical structures across diverse datasets.<n>Human-in-the-loop approach refined segmentations using U-Mamba, designed to generalize across imaging scenarios.<n>U-Mamba showed strong performance with DSC values of 0.97 for whole organs, 0.96 for fibroglandular tissue, and 0.82 for tumors on T1-weighted images.
  arXiv  Detail & Related papers  (2025-09-10T16:52:35Z)
• Abnormality-Driven Representation Learning for Radiology Imaging [0.8321462983924758]
  We introduce lesion-enhanced contrastive learning (LeCL), a novel approach to obtain visual representations driven by abnormalities in 2D axial slices across different locations of the CT scans. We evaluate our approach across three clinical tasks: tumor lesion location, lung disease detection, and patient staging, benchmarking against four state-of-the-art foundation models.
  arXiv  Detail & Related papers  (2024-11-25T13:53:26Z)
• Segment Anything for Dendrites from Electron Microscopy [36.25707481854301]
  We present DendriteSAM, a vision foundation model based on Segment Anything, for interactive and automatic segmentation of dendrites in EM images. The model is trained on high-resolution EM data from healthy hippocampus rat and is tested on diseased rat and human data.
  arXiv  Detail & Related papers  (2024-11-04T19:54:26Z)
• Deep Learning-Based Brain Image Segmentation for Automated Tumour Detection [0.0]
  The objective is to leverage state-of-the-art convolutional neural networks (CNNs) on a large dataset of brain MRI scans for segmentation. The proposed methodology applies pre-processing techniques for enhanced performance and generalizability.
  arXiv  Detail & Related papers  (2024-04-06T15:09:49Z)
• Architecture Analysis and Benchmarking of 3D U-shaped Deep Learning Models for Thoracic Anatomical Segmentation [0.8897689150430447]
  We conduct the first systematic benchmark study for variants of 3D U-shaped models. Our study examines the impact of different attention mechanisms, the number of resolution stages, and network configurations on segmentation accuracy and computational complexity.
  arXiv  Detail & Related papers  (2024-02-05T17:43:02Z)
• Interpretable 2D Vision Models for 3D Medical Images [47.75089895500738]
  This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods.
  arXiv  Detail & Related papers  (2023-07-13T08:27:09Z)
• S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences [91.48841778012782]
  We propose an unsupervised method to simultaneously learn local and global shape structures across population anatomies. Our pipeline significantly improves unsupervised correspondence estimation for SSMs compared to baseline methods. Our method is robust enough to learn from noisy neural network predictions, potentially enabling scaling SSMs to larger patient populations.
  arXiv  Detail & Related papers  (2023-04-15T09:39:52Z)
• CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection [36.08551407926805]
  We propose the CLIP-Driven Universal Model, which incorporates text embedding learned from Contrastive Language-Image Pre-training to segmentation models. The proposed model is developed from an assembly of 14 datasets, using a total of 3,410 CT scans for training and then evaluated on 6,162 external CT scans from 3 additional datasets.
  arXiv  Detail & Related papers  (2023-01-02T18:07:44Z)
• DeepAD: A Robust Deep Learning Model of Alzheimer's Disease Progression for Real-World Clinical Applications [0.9999629695552196]
  We propose a novel multi-task deep learning model to predict Alzheimer's disease progression. Our model integrates high dimensional MRI features from a 3D convolutional neural network with other data modalities.
  arXiv  Detail & Related papers  (2022-03-17T05:42:00Z)
• A multi-stage machine learning model on diagnosis of esophageal manometry [50.591267188664666]
  The framework includes deep-learning models at the swallow-level stage and feature-based machine learning models at the study-level stage. This is the first artificial-intelligence-style model to automatically predict CC diagnosis of HRM study from raw multi-swallow data.
  arXiv  Detail & Related papers  (2021-06-25T20:09:23Z)
• Deep Implicit Statistical Shape Models for 3D Medical Image Delineation [47.78425002879612]
  3D delineation of anatomical structures is a cardinal goal in medical imaging analysis. Prior to deep learning, statistical shape models that imposed anatomical constraints and produced high quality surfaces were a core technology. We present deep implicit statistical shape models (DISSMs), a new approach to delineation that marries the representation power of CNNs with the robustness of SSMs.
  arXiv  Detail & Related papers  (2021-04-07T01:15:06Z)

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.