Building foundation models for MRI has emerged as a promising direction for advancing medical image analysis and improving accessibility of task specific models. Existing approaches primarily focus on effective pretraining strategies and evaluating their performance across diverse downstream tasks. While these methods show performance gains, limited attention has been given to understanding task alignment between pretraining and downstream objectives. Unlike language models, where the two stages are naturally aligned, such alignment is less evident in vision based applications. Motivated by this gap, we explore continual pretraining. Specifically, continually pretraining a pretrained ViT encoder using Low-Rank Adaptation (LoRA) on a prostate segmentation task to enhance task alignment and downstream performance. We further perform layer-wise representational analysis using Centered Kernel Alignment (CKA) to assess representational shifts and their correlation with task outcomes. Our experiments show improved performance in 3 of 6 downstream tasks and comparable results in the others. Our Feature analysis reveals that, for segmentation tasks, continually pretrained encoder features exhibit greater similarity to those of the finetuned encoder than the original pretrained encoder, correlating with observed performance gains.
Continual atlas-based segmentation of prostate MRI
Technical University of Darmstadt（达姆施塔特工业大学）；Stanford University（斯坦福大学）；University of Cologne（科隆大学）；University of Frankfurt（法兰克福大学）；University Medical Center Mainz（美因茨大学医学中心）
Ca’ Foscari University（威尼斯福斯卡里大学）；University of New South Wales（新南威尔士大学）；Computer Vision Center（计算机视觉中心）
In this paper, we investigate the continual learning of Vision Transformers (ViT) for the challenging exemplar-free scenario, with special focus on how to efficiently distill the knowledge of its crucial self-attention mechanism (SAM). Our work takes an initial step towards a surgical investigation of SAM for designing coherent continual learning methods in ViTs. We first carry out an evaluation of established continual learning regularization techniques. We then examine the effect of regularization when applied to two key enablers of SAM: (a) the contextualized embedding layers, for their abi…
AI-based Automatic Segmentation of Prostate on Multi-modality Images: A Review
Soochow University（苏州大学）；Peking University First Hospital（北京大学第一医院）；Duke Kunshan University（昆山杜克大学）；Swinburne University of Technology（斯威本科技大学）；The Hong Kong Polytechnic University（香港理工大学）；UT Southwestern Medical Center（德克萨斯大学西南医学中心）
Technical University of Darmstadt（达姆施塔特工业大学）；MedCom GmbH（MedCom股份有限公司）
Continual learning protocols are attracting increasing attention from the medical imaging community. In continual environments, datasets acquired under different conditions arrive sequentially; and each is only available for a limited period of time. Given the inherent privacy risks associated with medical data, this setup reflects the reality of deployment for deep learning diagnostic radiology systems. Many techniques exist to learn continuously for image classification, and several have been adapted to semantic segmentation. Yet most struggle to accumulate knowledge in a meaningful manner. …
Distribution-Aware Replay for Continual MRI Segmentation
Technical University of Darmstadt（达姆施塔特工业大学）；Stanford University（斯坦福大学）；The Hessian Center for Artificial Intelligence: hessian.AI（黑森人工智能中心（hessian.AI））
Hybrid Multi-Dimensional MRI Prostate Cancer Detection via Hadamard Network-Based Bias Correction and Residual Networks
Electrical and Computer Engineering Department, University of Illinois Chicago（伊利诺伊大学芝加哥分校电子与计算机工程系）；Machine and Hybrid Intelligence Lab, Northwestern University（西北大学机器与混合智能实验室）；Department of Radiology, University of Chicago（芝加哥大学放射学系）
ShanghaiTech University（上海科技大学）；University of Electronic Science and Technology of China（电子科技大学）；The University of Hong Kong（香港大学）
In clinical practice, a segmentation network is often required to continually learn on a sequential data stream from multiple sites rather than a consolidated set, due to the storage cost and privacy restriction. However, during the continual learning process, existing methods are usually restricted in either network memorizability on previous sites or generalizability on unseen sites. This paper aims to tackle the challenging problem of Synchronous Memorizability and Generalizability (SMG) and to simultaneously improve performance on both previous and unseen sites, with a novel proposed SMG-l…
Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of catastrophic forgetting, is a hard challenge. Currently, deep learning methods can attain impressive results when the data modeled does not undergo a considerable distributional shift in subsequent learning sessions, but whenever we expose such systems to this incremental setting, performance drop very quickly. Overcoming this limitation is fundamental as i…
KOAL: Knowledge-Driven Prostate Cancer Grading with Ordinal-Aware Learning
School of Computer Science, Sichuan University（四川大学计算机学院）；China Mobile (Suzhou) Software Technology Company Limited（中国移动（苏州）软件技术有限公司）；Shanghai Changhai Hospital, Naval Medical University（上海长海医院，海军医学大学）；Renji Hospital, Shanghai Jiao Tong University School of Medicine（仁济医院，上海交通大学医学院）
Interpretable Prostate Cancer Detection using a Small Cohort of MRI Images
Department of Computer Science, Boston University Metropolitan College（波士顿大学计算机科学系）；Department of Radiology, McMaster University（麦斯特大学放射科）；Department of Radiology, School of Medicine, 5th Azar Hospital, Golestan University of Medical Sciences（戈兰大学医学学院放射科，第五阿扎尔医院）；Department of Medical Imaging, Niagara Health System（尼亚加拉健康系统医学影像科）；Center of Excellence in Precision Medicine and Digital Health, Department of Physiology, Chulalongkorn University（朱拉隆梭大学精准医学与数字健康中心，生理学系）
Unlocking Compositional Generalization in Continual Few-Shot Learning
Faculty of Information Technology, University of Science, Vietnam National University（信息科技学院，科学大学，越南国家大学）；Department of Computer Science, University of Warwick（计算机科学系，沃里克大学）
Domain-incremental White Blood Cell Classification with Privacy-aware Continual Learning
University of Regensburg（雷根斯堡大学）；University Hospital RWTH Aachen（亚琛工业大学附属医院）；University Hospital Erlangen（埃尔朗根大学附属医院）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学梅维斯研究所）
Artificial Intelligence, Analytics And Informatics (AI), A*STAR（A*STAR人工智能、分析与信息学）；RMIT University（皇家墨尔本理工大学）；Institute for Infocomm Research (IR), A*STAR（A*STAR资讯通信研究院）
Deep neural networks have shown promise in several domains, and the learned data (task) specific information is implicitly stored in the network parameters. Extraction and utilization of encoded knowledge representations are vital when data is no longer available in the future, especially in a continual learning scenario. In this work, we introduce {\em flashcards}, which are visual representations that {\em capture} the encoded knowledge of a network as a recursive function of predefined random image patterns. In a continual learning scenario, flashcards help to prevent catastrophic forgettin…
Catastrophic forgetting describes the fact that machine learning models will likely forget the knowledge of previously learned tasks after the learning process of a new one. It is a vital problem in the continual learning scenario and recently has attracted tremendous concern across different communities. In this paper, we explore the catastrophic forgetting phenomena in the context of quantum machine learning. We find that, similar to those classical learning models based on neural networks, quantum learning systems likewise suffer from such forgetting problem in classification tasks emerging…
MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Samsung AI Center-Cambridge（三星AI中心-剑桥）；The Hong Kong Polytechnic University（香港理工大学）
Self-Controlled Dynamic Expansion Model for Continual Learning
Huazhong University of Science and Technology（华中科技大学）；University of Electronic Science and Technology of China（电子科技大学）；Technische Universität München（慕尼黑工业大学）
RanPAC: Random Projections and Pre-trained Models for Continual Learning
Australian Institute for Machine Learning, The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）
Gradient Projection For Continual Parameter-Efficient Tuning
School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；School of Information Science and Technology, Xiamen University（厦门大学信息科学与技术学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院 Gallagher 学院）；School of Software, Beihang University（北航软件学院）；Meituan（美团）
Zhejiang University（浙江大学）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Continual learning is a longstanding research topic due to its crucial role in tackling continually arriving tasks. Up to now, the study of continual learning in computer vision is mainly restricted to convolutional neural networks (CNNs). However, recently there is a tendency that the newly emerging vision transformers (ViTs) are gradually dominating the field of computer vision, which leaves CNN-based continual learning lagging behind as they can suffer from severe performance degradation if straightforwardly applied to ViTs. In this paper, we study ViT-backed continual learning to strive fo…
AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting
The University of Melbourne（墨尔本大学）；Fortemedia Singapore（Fortemedia新加坡）；Nanyang Technological University（南洋理工大学）；South China University of Technology（华南理工大学）
Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning
Department of Intelligent Systems and Robotics, University of West Florida（智能系统与机器人系，西佛罗里达大学）；Florida Institute For Human and Machine Cognition (IHMC)（佛罗里达人类与机器认知研究所）；Center for Cybersecurity, University of West Florida（网络安全中心，西佛罗里达大学）
