Nature Biomedical Engineering最新文献_第2页

A three-dimensional multi-modal foundation model for optical coherence tomography. 光学相干层析成像三维多模态基础模型。

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-24 DOI: 10.1038/s41551-026-01662-2

Zixuan Liu,Hanwen Xu,Addie Woicik,Linda G Shapiro,Marian Blazes,Yue Wu,Verena Steffen,Catherine A Cukras,Cecilia S Lee,Miao Zhang,Aaron Y Lee,Sheng Wang

{"title":"A three-dimensional multi-modal foundation model for optical coherence tomography.","authors":"Zixuan Liu,Hanwen Xu,Addie Woicik,Linda G Shapiro,Marian Blazes,Yue Wu,Verena Steffen,Catherine A Cukras,Cecilia S Lee,Miao Zhang,Aaron Y Lee,Sheng Wang","doi":"10.1038/s41551-026-01662-2","DOIUrl":"https://doi.org/10.1038/s41551-026-01662-2","url":null,"abstract":"Vision loss caused by retinal diseases remains a leading global cause of disability. Optical coherence tomography (OCT) is an imaging technique that is used for diagnosing retinal diseases. Computational models can use OCT images for various diagnostic and prognostic tasks, but most existing approaches fail to fully leverage the rich three-dimensional (3D) structure of OCT data and lack the capability to integrate other retinal imaging modalities into the analysis. Here, to address these limitations, we present OCTCube-M, a 3D OCT-based multi-modal framework designed for the integrated analysis of 3D OCT and 2D en face (EF) images. OCTCube-M exploits COEP, an effective multi-modal contrastive learning method, to integrate OCT with other retinal imaging modalities, such as fundus autofluorescence imaging and infrared retinal imaging (IR). Using the OCTCube-M framework, we developed three models: OCTCube (uni-modal), OCTCube-IR (bi-modal) and OCTCube-EF (tri-modal). OCTCube, a 3D foundation model pre-trained on 26,605 3D OCT volumes comprising 1.62 million 2D OCT slices, achieved state-of-the-art performance in predicting 8 retinal diseases while demonstrating robust generalizability across cohorts, devices and modalities. OCTCube-IR extends OCTCube by incorporating 26,685 pairs of OCT and IR images, enabling accurate cross-modality retrieval and joint analysis of these two modalities. OCTCube-EF, trained on over 4 million 2D OCT slices and 400 thousand EF retinal images, excels in predicting the growth rate of geographic atrophy across datasets collected from 6 multi-centre clinical trials across 23 countries. Collectively, OCTCube-M is a 3D multi-modal foundation model framework for integrating OCT and other retinal imaging modalities. It demonstrated substantial advancements in cross-site, cross-device, cross-modality and systemic disease prediction, while offering substantial utility in geographic atrophy clinical trials.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"4 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147738955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards a general-purpose foundation model for functional MRI analysis 迈向功能性MRI分析的通用基础模型

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-23 DOI: 10.1038/s41551-026-01666-y

Cheng Wang, Yu Jiang, Zhihao Peng, Chenxin Li, Chang-bae Bang, Lin Zhao, Wanyi Fu, Jinglei Lv, Jorge Sepulcre, Carl Yang, Lifang He, Tianming Liu, Xue-Jun Kong, Quanzheng Li, Daniel S. Barron, Anqi Qiu, Randy Hirschtick, Byung-Hoon Kim, Hongbin Han, Xiang Li, Yixuan Yuan

{"title":"Towards a general-purpose foundation model for functional MRI analysis","authors":"Cheng Wang, Yu Jiang, Zhihao Peng, Chenxin Li, Chang-bae Bang, Lin Zhao, Wanyi Fu, Jinglei Lv, Jorge Sepulcre, Carl Yang, Lifang He, Tianming Liu, Xue-Jun Kong, Quanzheng Li, Daniel S. Barron, Anqi Qiu, Randy Hirschtick, Byung-Hoon Kim, Hongbin Han, Xiang Li, Yixuan Yuan","doi":"10.1038/s41551-026-01666-y","DOIUrl":"https://doi.org/10.1038/s41551-026-01666-y","url":null,"abstract":"Functional magnetic resonance imaging (fMRI) is crucial for studying brain function and diagnosing neurological disorders. However, existing analysis methods suffer from reproducibility and transferability challenges due to complex preprocessing pipelines and task-specific model designs. Here we introduce the Neuroimaging Foundation Model with Spatial–Temporal Optimized and Representation Modelling (NeuroSTORM), which learns generalizable representations directly from four-dimensional fMRI volumes and enables efficient transfer to diverse downstream applications. Specifically, NeuroSTORM is pretrained on 28.65 million fMRI frames from over 50,000 participants, spanning multiple centres and ages 5–100. It combines an efficient spatiotemporal modelling design and lightweight task adaptation to enable scalable pretraining and fast transfer to downstream applications. We show that NeuroSTORM consistently outperforms existing methods across five downstream tasks, including demographic prediction, phenotype prediction, disease diagnosis, re-identification and state classification. On two multihospital clinical cohorts with 17 diagnoses, NeuroSTORM achieves the best diagnosis performance while remaining predictive of psychological and cognitive phenotypes. These results suggest that NeuroSTORM could become a standardized foundation model for reproducible and transferable fMRI analysis.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"145 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2026-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147734057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pre-intervention with intravenous immunoglobulin reverses the immunogenic clearance of PEGylated nanomedicines 静脉注射免疫球蛋白干预可以逆转聚乙二醇化纳米药物的免疫原性清除

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-23 DOI: 10.1038/s41551-026-01661-3

Keren Lai, Peiyi He, Yuejian He, Mingheng Xu, Xiaoxi Zhao, Xinyue Wang, Guifeng Miao, Yanqiu Feng, Xiaorui Wang

{"title":"Pre-intervention with intravenous immunoglobulin reverses the immunogenic clearance of PEGylated nanomedicines","authors":"Keren Lai, Peiyi He, Yuejian He, Mingheng Xu, Xiaoxi Zhao, Xinyue Wang, Guifeng Miao, Yanqiu Feng, Xiaorui Wang","doi":"10.1038/s41551-026-01661-3","DOIUrl":"https://doi.org/10.1038/s41551-026-01661-3","url":null,"abstract":"Nanomedicines are susceptible to immunogenic clearance before reaching their disease targets, thereby limiting their pharmacodynamic efficacy. To overcome this challenge, PEGylation has been developed and widely used. However, in therapies that necessitate multiple repeated administrations, the immunogenicity of PEGylated nanoparticles often becomes non-negligible, resulting in an accelerated blood clearance (ABC) effect and declining therapeutic efficacy. Here we propose a simple and clinically applicable strategy of pre-intervention with FDA-approved intravenous immunoglobulin (IVIG) before injection of nanoparticles. Pretreatment with IVIG was found to regulate the organism’s immunologic macroenvironment and transiently block the mononuclear phagocyte system, thereby circumventing the anti-PEG antibody-mediated clearance of nanomedicines. The universal applicability of the IVIG pretreatment strategy is demonstrated by its consistent reversal of the ABC effect across five structurally diverse nanomaterials, with sizes of 10–120 nm. IVIG significantly enhances therapeutic efficiency in breast tumours, particularly in large tumours (~350 mm3), with up to a 3.9-fold improvement. Overall, pre-intervention with IVIG opens a new paradigm for addressing the immunogenic clearance issue and enhancing the performance of nanomedicines.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"33 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2026-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147734056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Engineering astrocytes as programmable amyloid-clearing cells 工程星形胶质细胞作为可编程的淀粉样蛋白清除细胞

IF 26.8 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-22 DOI: 10.1038/s41551-026-01678-8

Xinyu Zhou

引用次数: 0

3D foundation model for generalizable disease detection in head computed tomography 头部计算机断层扫描可推广疾病检测的三维基础模型

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-22 DOI: 10.1038/s41551-026-01668-w

Weicheng Zhu, Haoxu Huang, Huanze Tang, Rushabh Musthyala, Boyang Yu, Long Chen, Emilio Vega, Thomas O’Donnell, Reya Hayek, Lindsey Kuohn, Seena Dehkharghani, Jennifer A. Frontera, Arjun V. Masurkar, Kara Melmed, Narges Razavian

{"title":"3D foundation model for generalizable disease detection in head computed tomography","authors":"Weicheng Zhu, Haoxu Huang, Huanze Tang, Rushabh Musthyala, Boyang Yu, Long Chen, Emilio Vega, Thomas O’Donnell, Reya Hayek, Lindsey Kuohn, Seena Dehkharghani, Jennifer A. Frontera, Arjun V. Masurkar, Kara Melmed, Narges Razavian","doi":"10.1038/s41551-026-01668-w","DOIUrl":"https://doi.org/10.1038/s41551-026-01668-w","url":null,"abstract":"Head computed tomography (CT) imaging is a widely used imaging modality with multitudes of medical indications, particularly in assessing pathology of the brain, skull and cerebrovascular system. It is commonly used as the first-line imaging in neurologic emergencies given its rapidity of image acquisition, safety, cost and ubiquity. Deep learning models may facilitate detection of a wide range of diseases. However, the scarcity of high-quality labels and annotations, particularly among less common conditions, substantially hinders the development of powerful models. To address this challenge, we introduce FM-HCT, a Foundation Model for Head CT for generalizable disease detection, trained using self-supervised learning. Our approach pretrains a deep learning model on a large, diverse dataset of 361,663 non-contrast 3D head CT scans without the need for manual annotations, enabling the model to learn robust, generalizable features. Our results demonstrate that the self-supervised foundation model substantially improves performance on downstream diagnostic tasks compared to models trained from scratch and previous 3D CT foundation models trained on scarce annotated datasets.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"18 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147734058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Where engineering and immunotherapy meet 工程学和免疫疗法在哪里相遇

IF 26.8 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-22 DOI: 10.1038/s41551-026-01679-7

引用次数: 0

Gut microorganisms turn low-protein diet into fat browning 肠道微生物将低蛋白饮食转化为脂肪褐化

IF 26.8 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-22 DOI: 10.1038/s41551-026-01674-y

Alessandra Griffo

引用次数: 0

Theoretical quantitative model and clinical outcome predictions of conductive cardiac patches for electrophysiological treatments. 导电心脏贴片电生理治疗的理论定量模型及临床结果预测。

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-21 DOI: 10.1038/s41551-026-01659-x

Yuchen Miao,Zhenyin Fu,Juhong Zhang,Yuhang Tao,Kai Pang,Chengjun Wang,Qianqian Jiang,Liyin Shen,Tian Xia,Peixuan Lu,Zhen Xu,Ling Xia,Lijian Zuo,Ruiqing Dong,Yumeng Liu,Zefeng Wang,Nan Zhang,Jizhou Song,Changyou Gao,Ruhong Jiang,Dongdong Deng,Yang Zhu

{"title":"Theoretical quantitative model and clinical outcome predictions of conductive cardiac patches for electrophysiological treatments.","authors":"Yuchen Miao,Zhenyin Fu,Juhong Zhang,Yuhang Tao,Kai Pang,Chengjun Wang,Qianqian Jiang,Liyin Shen,Tian Xia,Peixuan Lu,Zhen Xu,Ling Xia,Lijian Zuo,Ruiqing Dong,Yumeng Liu,Zefeng Wang,Nan Zhang,Jizhou Song,Changyou Gao,Ruhong Jiang,Dongdong Deng,Yang Zhu","doi":"10.1038/s41551-026-01659-x","DOIUrl":"https://doi.org/10.1038/s41551-026-01659-x","url":null,"abstract":"Myocardial infarction (MI) impairs cardiac electrical signal transmission, which could be partially remedied by implantable electroactive biomaterials. Here we characterize electroactive cardiac patches (eCarPs) with conductivities spanning five orders of magnitude both in vitro and in rat models. In contrast to common belief, we reveal that highly conductive eCarPs are more effective in lowering the risk of post-MI arrhythmia and preserving cardiac function with respect to eCarPs with conductivity similar to normal myocardium. We show that highly conductive eCarPs restore electrical signal conduction velocity across infarcted myocardium to healthy levels, while less conductive eCarPs fail to do this. We quantitatively demonstrate that three-dimensional cardiac simulation based on the monodomain model accurately replicates the effect of high-conductivity patches in eliminating conduction blocks in porcine myocardium and the locations of reentrant circuits in patients with MI. Our results suggest that eCarP conductivity higher than healthy human myocardium is preferred for lowering the risk of arrhythmia in patients by reducing the number of reentrants and stabilizing the reentrant routes.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"29 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147731379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Living depots for breast cancer control and reconstruction. 乳腺癌控制和重建的生活仓库。

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-17 DOI: 10.1038/s41551-026-01657-z

Cristina C Barrias

引用次数: 0

Three-dimensional quantitative tissue clearing reveals differences in osteovascular niche of aged and young human mesenchymal stromal cells. 三维定量组织清除揭示了老年人和年轻人间充质间质细胞骨血管生态位的差异。

IF 28.1 1区医学

Nature Biomedical Engineering Pub Date : 2026-04-17 DOI: 10.1038/s41551-026-01645-3

Nelson Tsz Long Chu,Ostap Dregval,Yu-Wei Chang,Emil Kriukov,Xin Tian,Xin Liu,Dana Trompet,Misty Shuo Zhang,Lei Li,Zhong Li,Emiliano Gomez Ruiz,Joana B Pereira,Mats Brittberg,Björn Barenius,Lars Sävendahl,Ralf H Adams,Inger Gjertsson,Claes Ohlsson,Giovanni Volpe,Andrei S Chagin

{"title":"Three-dimensional quantitative tissue clearing reveals differences in osteovascular niche of aged and young human mesenchymal stromal cells.","authors":"Nelson Tsz Long Chu,Ostap Dregval,Yu-Wei Chang,Emil Kriukov,Xin Tian,Xin Liu,Dana Trompet,Misty Shuo Zhang,Lei Li,Zhong Li,Emiliano Gomez Ruiz,Joana B Pereira,Mats Brittberg,Björn Barenius,Lars Sävendahl,Ralf H Adams,Inger Gjertsson,Claes Ohlsson,Giovanni Volpe,Andrei S Chagin","doi":"10.1038/s41551-026-01645-3","DOIUrl":"https://doi.org/10.1038/s41551-026-01645-3","url":null,"abstract":"Human bone marrow mesenchymal stromal/stem cells (BM-MSCs) are widely used in clinical trials and tissue engineering, yet their native microenvironment remains poorly understood. Here we introduce a tissue-clearing protocol, DeepBone, for human bones and integrate it with simultaneous mRNA and protein detection. Using this protocol, we spatially map BM-MSCs relative to key bone microenvironment components, including human blood capillaries, adipocytes, sinusoids and bony trabeculae. Quantitative analysis reveals that the native microenvironment of human BM-MSCs in young bone is enriched in vasculature, sinusoids, bone matrix and adipocytes. In contrast, in aged bone, BM-MSCs show no preferential association with bone or adipocytes. Proliferative BM-MSCs are predominantly found along blood vessels. Moreover, we identify a specialized microenvironment for BM-MSCs in young bone, characterized by sinusoids coiled around trabeculae and enriched by R-type vessels. These findings provide insights into the native niches of BM-MSCs, offering a foundation for the development of tissue engineering strategies that mimic their physiological context.","PeriodicalId":19063,"journal":{"name":"Nature Biomedical Engineering","volume":"42 1","pages":""},"PeriodicalIF":28.1,"publicationDate":"2026-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147702130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0