Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging Classification
School of Software Engineering, Beijing University of Technology（北京工业大学软件学院）；Beijing Neurosurgical Institute（北京神经外科研究所）；Beijing Tiantan Hospital, Capital Medical University（首都医科大学附属北京天坛医院）；Sorbonne Université（索邦大学）；Institut du Cerveau – Paris Brain Institute - ICM（巴黎脑研究所（ICM））；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Inserm（法国国家健康与医学研究院）；AP-HP（巴黎公共医疗集团）；Hôpital de la Pitié-Salpêtrière（皮蒂-萨尔皮特里耶医院）
Yuning Huang, Jingchen Zou, Lanxi Meng, Xin Yue, Qing Zhao, Jianqiang Li, Changwei Song, Gabriel Jimenez, Shaowu Li, Guanghui Fu
Medical image analysis frequently encounters data scarcity challenges. Transfer learning has been effective in addressing this issue while conserving computational resources. The recent advent of foundational models like the DINOv2, which uses the vision transformer architecture, has opened new opportunities in the field and gathered significant interest. However, DINOv2's performance on clinical data still needs to be verified. 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, in a transfer learning context. Our focus was on understanding the impact of the freezing mechanism on performance. We also validated our findings on three other types of public datasets: chest radiography, fundus radiography, and dermoscopy. Our findings indicate that in our clinical dataset, DINOv2's performance was not as strong as ImageNet-based pre-trained models, whereas in public datasets, DINOv2 generally outperformed other models, especially when using the frozen mechanism. Similar performance was observed with various sizes of DINOv2 models across different tasks. In summary, DINOv2 is viable for medical image classification tasks, particularly with data resembling natural images. However, its effectiveness may vary with data that significantly differs from natural images such as MRI. In addition, employing smaller versions of the model can be adequate for medical task, offering resource-saving benefits. Our codes are available at https://github.com/GuanghuiFU/medical_DINOv2_eval.
Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心）；Peng Cheng Laboratory（鹏城实验室）；University of Chinese Academy of Sciences（中国科学院大学）；The University of Hong Kong（香港大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Linear Algebraic Approaches to Neuroimaging Data Compression: A Comparative Analysis of Matrix and Tensor Decomposition Methods for High-Dimensional Medical Images
Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images
University Hospital RWTH Aachen（亚琛工业大学附属医院）；Technische Universität Dresden（德累斯顿工业大学）；University Hospital Carl Gustav Carus Dresden（德累斯顿卡尔·古斯塔夫·卡鲁斯大学医院）；Else Kröner Fresenius Center for Digital Health（Else Kröner Fresenius 数字健康中心）；University Hospital Heidelberg（海德堡大学医院）；National Center for Tumor Diseases（国家肿瘤疾病中心）
Implicit Neural Representation in Medical Imaging: A Comparative Survey
Iran University of Science and Technology（伊朗科技大学）；South Dakota State University（南达科他州立大学）；RWTH Aachen University（亚琛工业大学）；University of Regensburg（雷根斯堡大学）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）
Enhancing Transfer Learning for Medical Image Classification with SMOTE: A Comparative Study
University of Dhaka（达卡大学）；Utah State University（犹他州立大学）；Noakhali Science and Technology University（诺阿卡利科学技术大学）；Daffodil International University（水仙花国际大学）
A comparative study of 2D image segmentation algorithms for traumatic brain lesions using CT data from the ProTECTIII multicenter clinical trial
Warren Alpert Medical School of Brown University（布朗大学沃伦·阿尔珀特医学院）；Emory University School of Medicine（埃默里大学医学院）；University of Florida School of Medicine（佛罗里达大学医学院）；Brown University（布朗大学）
Quantitative Imaging Principles Improves Medical Image Learning
University of Hawaii（夏威夷大学）；University of Hawaii Cancer Center（夏威夷大学癌症中心）；Pennington Biomedical Research Center（彭宁顿生物医学研究中心）；Louisiana State University（路易斯安那州立大学）
A Vision-language Framework for Comparative Reasoning in Radiology
University of Science and Technology of China（中国科学技术大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）；Department of Biomedical Informatics, Harvard Medical School（哈佛医学院生物医学信息学系）；Department of Radiology, Renmin Hospital of Wuhan University（武汉大学仁民医院放射科）；Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University（上海交通大学附属第六人民医院）
A knee cannot have lung disease: out-of-distribution detection with in-distribution voting using the medical example of chest X-ray classification
Munich Institute of Biomedical Engineering（慕尼黑生物医学工程研究所）；School of Computation, Information, and Technology（计算、信息与技术学院）；Technical University of Munich（慕尼黑工业大学）；Institute for History and Ethics in Medicine（医学史与医学伦理学研究所）；Munich School of Technology in Society（慕尼黑技术与社会学院）
School of Computer Science, Fudan University（复旦大学计算机科学学院）；Institute of Digestive Disease, School of Medicine, Tongji University（同济大学医学院消化病研究所）；National Engineering Center for Biochip（国家生物芯片工程研究中心）；Endoscopy Center of Zhongshan Hospital, Fudan University（复旦大学中山医院内镜中心）
Exploring the Efficacy of Partial Denoising Using Bit Plane Slicing for Enhanced Fracture Identification: A Comparative Study of Deep Learning-Based Approaches and Handcrafted Feature Extraction Techniques
