Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks

• URL: http://arxiv.org/abs/2312.02366v4
• Date: Sat, 14 Sep 2024 03:35:04 GMT
• Title: Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks
• Abstract summary: DINOv2 is an open-source foundation model pre-trained with self-supervised learning on 142 million curated natural images. This study comprehensively evaluates the performance DINOv2 for radiology.
• Score: 5.8941124219471055
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The integration of deep learning systems into healthcare has been hindered by the resource-intensive process of data annotation and the inability of these systems to generalize to different data distributions. Foundation models, which are models pre-trained on large datasets, have emerged as a solution to reduce reliance on annotated data and enhance model generalizability and robustness. DINOv2 is an open-source foundation model pre-trained with self-supervised learning on 142 million curated natural images that exhibits promising capabilities across various vision tasks. Nevertheless, a critical question remains unanswered regarding DINOv2's adaptability to radiological imaging, and whether its features are sufficiently general to benefit radiology image analysis. Therefore, this study comprehensively evaluates the performance DINOv2 for radiology, conducting over 200 evaluations across diverse modalities (X-ray, CT, and MRI). To measure the effectiveness and generalizability of DINOv2's feature representations, we analyze the model across medical image analysis tasks including disease classification and organ segmentation on both 2D and 3D images, and under different settings like kNN, few-shot learning, linear-probing, end-to-end fine-tuning, and parameter-efficient fine-tuning. Comparative analyses with established supervised, self-supervised, and weakly-supervised models reveal DINOv2's superior performance and cross-task generalizability. The findings contribute insights to potential avenues for optimizing pre-training strategies for medical imaging and enhancing the broader understanding of DINOv2's role in bridging the gap between natural and radiological image analysis. Our code is available at https://github.com/MohammedSB/DINOv2ForRadiology

Related papers

• Entropy-Guided Self-Supervised Learning for Medical Image Classification [0.0]
  This paper introduces a synergistic deep learning framework that leverages the strengths of self-supervised learning and transfer learning for enhanced medical image classification.<n>Our approach employs two distinct ConvNeXt-Tiny models: one pre-trained on a large-scale natural image dataset (ImageNet) and another pre-trained using an entropy-guided Masked Autoencoder (MAE) on the target medical dataset.<n> Rigorous experimental validation across four diverse medical imaging datasets demonstrates the superior performance and robustness of our ensemble approach.
  arXiv  Detail & Related papers  (2026-05-21T04:01:06Z)
• Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models [56.29123284262618]
  This work proposes leveraging the universal representation capabilities of visual foundation models to estimate inherent data uncertainty.<n>We analyze the feature diversity of the model's decoded representations and quantify their singular value energy to define the semantic perception scale for each class.<n>Based on this foundation, we design two uncertainty-driven application strategies: (1) the aleatoric uncertainty-aware data filtering mechanism to eliminate potentially noisy samples and enhance model learning quality; and (2) the dynamic uncertainty-aware optimization strategy that adaptively adjusts class-specific loss weights during training based on the semantic perception scale, combined with a label denoising mechanism to improve training stability
  arXiv  Detail & Related papers  (2026-04-13T03:59:54Z)
• MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis [19.063517827476826]
  We introduce MM-DINOv2, a novel framework that adapts the pre-trained vision foundation model DINOv2 for multi-modal medical imaging.<n>Our approach incorporates multi-modal patch embeddings, enabling vision foundation models to effectively process multi-modal imaging data.<n>Our method achieves a Matthews Correlation Coefficient (MCC) of 0.6 on an external test set, surpassing state-of-the-art supervised approaches by +11.1%.
  arXiv  Detail & Related papers  (2025-09-08T12:34:15Z)
• Generalist versus Specialist Vision Foundation Models for Ocular Disease and Oculomics [10.703307148153433]
  We evaluate the adaptability of DINOv2 and DINOv3 in retinal image applications, compared to two specialist RETFound models.<n> RETFound-DINOv2 consistently outperforms these generalist foundation models in ocular-disease detection and oculomics tasks.
  arXiv  Detail & Related papers  (2025-09-03T15:48:57Z)
• Quality Assessment and Distortion-aware Saliency Prediction for AI-Generated Omnidirectional Images [70.49595920462579]
  This work studies the quality assessment and distortion-aware saliency prediction problems for AIGODIs.<n>We propose two models with shared encoders based on the BLIP-2 model to evaluate the human visual experience and predict distortion-aware saliency for AI-generated omnidirectional images.
  arXiv  Detail & Related papers  (2025-06-27T05:36:04Z)
• Comparative Evaluation of Radiomics and Deep Learning Models for Disease Detection in Chest Radiography [0.0]
  This study presents a comprehensive evaluation of radiomics-based and deep learning-based approaches for disease detection in chest radiography. It focuses on COVID-19, lung opacity, and viral pneumonia. The results aim to inform the integration of AI-driven diagnostic tools in clinical practice.
  arXiv  Detail & Related papers  (2025-04-16T16:54:37Z)
• 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)
• Assessing the Performance of the DINOv2 Self-supervised Learning Vision Transformer Model for the Segmentation of the Left Atrium from MRI Images [1.2499537119440245]
  DINOv2 is a self-supervised learning vision transformer trained on natural images for LA segmentation using MRI. We demonstrate its ability to provide accurate & consistent segmentation, achieving a mean Dice score of.871 & a Jaccard Index of.792 for end-to-end fine-tuning. These results suggest that DINOv2 effectively adapts to MRI with limited data, highlighting its potential as a competitive tool for segmentation & encouraging broader use in medical imaging.
  arXiv  Detail & Related papers  (2024-11-14T17:15:51Z)
• Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning [49.197385954021456]
  In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for visualization and subsequent analysis tasks. To reduce slice spacing, deep-learning-based super-resolution techniques are widely investigated. Most current solutions require a substantial number of paired high-resolution and low-resolution images for supervised training, which are typically unavailable in real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-10T02:20:26Z)
• Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging Classification [7.205610366609243]
  In this paper, we performed a glioma grading task using three clinical modalities of brain MRI data. We compared the performance of various pre-trained deep learning models, including those based on ImageNet and DINOv2. Our findings indicate that in our clinical dataset, DINOv2's performance was not as strong as ImageNet-based pre-trained models.
  arXiv  Detail & Related papers  (2024-02-12T11:49:08Z)
• 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)
• LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching [59.01894976615714]
  We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
  arXiv  Detail & Related papers  (2023-06-20T22:21:34Z)
• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• ROCT-Net: A new ensemble deep convolutional model with improved spatial resolution learning for detecting common diseases from retinal OCT images [0.0]
  This paper presents a new enhanced deep ensemble convolutional neural network for detecting retinal diseases from OCT images. Our model generates rich and multi-resolution features by employing the learning architectures of two robust convolutional models. Our experiments on two datasets and comparing our model with some other well-known deep convolutional neural networks have proven that our architecture can increase the classification accuracy up to 5%.
  arXiv  Detail & Related papers  (2022-03-03T17:51:01Z)
• InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images [53.4351366246531]
  We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. We analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance.
  arXiv  Detail & Related papers  (2021-12-23T15:52:37Z)
• MIMO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning [49.57261599776167]
  We propose an end-to-end robust Transformer-based solution, Mutual Integration of patient journey and Medical Ontology (MIMO) for healthcare representation learning and predictive analytics.
  arXiv  Detail & Related papers  (2021-07-20T07:04:52Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• Generalization of Deep Convolutional Neural Networks -- A Case-study on Open-source Chest Radiographs [2.934426478974089]
  One major challenge is to conceive a DCNN model with remarkable performance on both internal and external data. We demonstrate that DCNNs may not generalize to new data, but increasing the quality and heterogeneity of the training data helps to improve the generalizibility factor.
  arXiv  Detail & Related papers  (2020-07-11T14:37:28Z)

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.