Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusion
Dept. of Math and Computer Science, University of Catania（数学与计算机科学系，卡塔尼亚大学）；Centre for Medical Image Computing, University College London（医学影像计算中心，伦敦大学学院）；MIFT Department, University of Messina（MIFT系，梅斯ina大学）
Lemuel Puglisi, Daniel C. Alexander, Daniele Ravì
备注：
arXiv admin note: text overlap with arXiv:2405.03328
提出 BrLP 时空模型，通过在小型潜在空间运行、整合受试者元数据与疾病动力学先验，并引入 LAS 算法，实现了 3D 脑部 MRI 个体化疾病进展的高精度预测。
摘要：
纵向磁共振成像（MRI）数据集的日益普及促进了人工智能（AI）驱动的疾病进展建模，使得为个体患者预测未来医学扫描成为可能。然而，尽管 AI 取得了重大进展，当前方法仍面临挑战，包括实现患者特异性个体化、确保时空一致性、有效利用纵向数据以及管理 3D 扫描的大量内存需求。为了应对这些挑战，我们提出了 Brain Latent Progression（BrLP），这是一种新颖的时空模型，旨在预测 3D 脑部 MRI 中的个体层面疾病进展。BrLP 的关键贡献有四方面：（i）它在小型潜在空间中运行，缓解了高维成像数据带来的计算挑战；（ii）它显式整合受试者元数据以增强预测的个体化；（iii）它通过辅助模型纳入疾病动力学的先验知识，促进纵向数据的整合；（iv）它引入了 Latent Average Stabilization（LAS）算法，该算法（a）在推理时强制预测进展中的时空一致性，并且（b）允许我们得出全局和体素层面预测的不确定性度量。我们在来自 2,805 名受试者的 11,730 张 T1 加权（T1w）脑部 MRI 上训练和评估 BrLP，并在包含来自 962 名受试者的 2,257 张 MRI 的外部测试集上验证其泛化能力。我们的实验将 BrLP 生成的 MRI 扫描与真实随访 MRI 进行比较，证明了与现有方法相比具有最先进的准确性。代码公开于：https://github.com/LemuelPuglisi/BrLP。
英文摘要：
The growing availability of longitudinal Magnetic Resonance Imaging (MRI) datasets has facilitated Artificial Intelligence (AI)-driven modeling of disease progression, making it possible to predict future medical scans for individual patients. However, despite significant advancements in AI, current methods continue to face challenges including achieving patient-specific individualization, ensuring spatiotemporal consistency, efficiently utilizing longitudinal data, and managing the substantial memory demands of 3D scans. To address these challenges, we propose Brain Latent Progression (BrLP), a novel spatiotemporal model designed to predict individual-level disease progression in 3D brain MRIs. The key contributions in BrLP are fourfold: (i) it operates in a small latent space, mitigating the computational challenges posed by high-dimensional imaging data; (ii) it explicitly integrates subject metadata to enhance the individualization of predictions; (iii) it incorporates prior knowledge of disease dynamics through an auxiliary model, facilitating the integration of longitudinal data; and (iv) it introduces the Latent Average Stabilization (LAS) algorithm, which (a) enforces spatiotemporal consistency in the predicted progression at inference time and (b) allows us to derive a measure of the uncertainty for the prediction at the global and voxel level. We train and evaluate BrLP on 11,730 T1-weighted (T1w) brain MRIs from 2,805 subjects and validate its generalizability on an external test set comprising 2,257 MRIs from 962 subjects. Our experiments compare BrLP-generated MRI scans with real follow-up MRIs, demonstrating state-of-the-art accuracy compared to existing methods. The code is publicly available at: https://github.com/LemuelPuglisi/BrLP.
Stanford University（斯坦福大学）；Stanford School of Medicine（斯坦福医学院）；University of California San Diego（加州大学圣地亚哥分校）；SRI International（斯坦福国际研究院）
Many neurological diseases are characterized by gradual deterioration of brain structure and function. Large longitudinal MRI datasets have revealed such deterioration, in part, by applying machine and deep learning to predict diagnosis. A popular approach is to apply Convolutional Neural Networks (CNN) to extract informative features from each visit of the longitudinal MRI and then use those features to classify each visit via Recurrent Neural Networks (RNNs). Such modeling neglects the progressive nature of the disease, which may result in clinically implausible classifications across visits…
GLOMIA-Pro: A Generalizable Longitudinal Medical Image Analysis Framework for Disease Progression Prediction
School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）；Department of Thoracic Surgery, Sun Yat-sen University Cancer Center（中山大学肿瘤医院胸外科部门）；Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University（中山大学第五附属医院放射科部门）；Beijing Duanliu Medical Technology Co., Ltd.（北京杜流医疗科技有限公司）
Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge
Dept. of Math and Computer Science, University of Catania, Italy（数学与计算机科学系，卡塔尼亚大学，意大利）；Centre for Medical Image Computing, University College London, UK（医学影像计算中心，伦敦大学学院，英国）；School of Physics, Engineering and CS, University of Hertfordshire, UK（物理、工程与计算机科学学院，赫特福德大学，英国）
Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation
School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院）；Xi’an Key Laboratory of Big Data and Intelligent Vision（西安大数据与智能视觉重点实验室）；Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University（教育部协同智能系统重点实验室）；Warren Alpert Medical School, Brown University（布朗大学沃伦·阿尔佩特医学学院）
University of Iceland（冰岛大学）；Landspitali - University Hospital（兰斯皮塔利大学医院）；The Icelandic Heart Association（冰岛心脏协会）；The Johns Hopkins University（约翰斯·霍普金斯大学）
Lesions that appear hyperintense in both Fluid Attenuated Inversion Recovery (FLAIR) and T2-weighted magnetic resonance images (MRIs) of the human brain are common in the brains of the elderly population and may be caused by ischemia or demyelination. Lesions are biomarkers for various neurodegenerative diseases, making accurate quantification of them important for both disease diagnosis and progression. Automatic lesion detection using supervised learning requires manually annotated images, which can often be impractical to acquire. Unsupervised lesion detection, on the other hand, does not r…
University College London（伦敦大学学院）；Inria（法国国家信息与自动化研究所）；Université Côte d'Azur（蔚蓝海岸大学）
Here we present DIVE: Data-driven Inference of Vertexwise Evolution. DIVE is an image-based disease progression model with single-vertex resolution, designed to reconstruct long-term patterns of brain pathology from short-term longitudinal data sets. DIVE clusters vertex-wise biomarker measurements on the cortical surface that have similar temporal dynamics across a patient population, and concurrently estimates an average trajectory of vertex measurements in each cluster. DIVE uniquely outputs a parcellation of the cortex into areas with common progression patterns, leading to a new signature…
Télécom SudParis, Institut Polytechnique de Paris（巴黎电信 SudParis，巴黎综合理工学院）；University College London（伦敦大学学院）；Digital Technologies and Artificial Intelligence Development Research Institute (AIRI)（数字技术与人工智能发展研究院（AIRI））
Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases. Analyzing this data via machine learning generally requires a large number of ground-truth labels, which are often missing or expensive to obtain. Reducing the need for labels, we propose a self-supervised strategy for representation learning named Longitudinal Neighborhood Embedding (LNE). Motivated by concepts in contrastive learning, LNE explicitly models the similarity between trajectory vectors across different subjects. We do so by building a gra…
Cell motion and appearance have a strong correlation with cell cycle and disease progression. Many contemporary efforts in machine learning utilize spatio-temporal models to predict a cell's physical state and, consequently, the advancement of disease. Alternatively, generative models learn the underlying distribution of the data, creating holistic representations that can be used in learning. In this work, we propose an aggregate model that combine Generative Adversarial Networks (GANs) and Autoregressive (AR) models to predict cell motion and appearance in human neutrophils imaged by differe…
Hosei University（法政大学）；Johns Hopkins University School of Medicine（约翰斯·霍普金斯大学医学院）
To build a robust and practical content-based image retrieval (CBIR) system that is applicable to a clinical brain MRI database, we propose a new framework -- Disease-oriented image embedding with pseudo-scanner standardization (DI-PSS) -- that consists of two core techniques, data harmonization and a dimension reduction algorithm. Our DI-PSS uses skull stripping and CycleGAN-based image transformations that map to a standard brain followed by transformation into a brain image taken with a given reference scanner. Then, our 3D convolutioinal autoencoders (3D-CAE) with deep metric learning acqu…
Mechanistic Learning with Guided Diffusion Models to Predict Spatio-Temporal Brain Tumor Growth
ETH Zurich, 8092 Zurich, Switzerland - SIB Swiss Institue of Bioinformatics, 1015 Lausanne, Switzerland Department of Radiation Oncology, Inselspital, Bern University Hospital；University of Bern, Switzerland Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Medical Center, Washington, DC 20010, United States University of California San Francisco, San Francisco, CA 94143, United States University Children's Hospital Zurich, 8008 Zurich, Switzerland
4DLoG: Generative Modeling of Neurodegenerative Brain Anatomy with 4D Longitudinal Diffusion Model
Department of Electrical and Computer Engineering（电气与计算机工程系）；Department of Radiology（放射学系）；Department of Electrical and Computer Engineering, Department of Computer Science（电气与计算机工程系、计算机科学系）
Synthesizing Individualized Aging Brains in Health and Disease with Generative Models and Parallel Transport
Division of Biomedical Imaging, KTH Royal Institute of Technology, Stockholm, Sweden（生物医学成像系，皇家理工学院，斯德哥尔摩，瑞典）；Division of Clinical Geriatrics, Center for Alzheimer Research, Karolinska Institute, Stockholm, Sweden（临床老年医学系，阿尔茨海默病研究中心，卡罗林斯卡研究所，斯德哥尔摩，瑞典）；Division of Gene Technology, KTH Royal Institute of Technology, Stockholm, Sweden（基因技术系，皇家理工学院，斯德哥尔摩，瑞典）；Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, MA, USA（计算机科学与人工智能实验室，麻省理工学院，马萨诸塞州，美国）；MedTechLabs, BioClinicum, Karolinska University Hospital, Solna, Sweden（MedTechLabs，BioClinicum，卡罗林斯卡大学医院，索纳，瑞典）
