Visual Computer最新文献

英文中文

Transformer-based arterial spin labeling perfusion MRI denoising. 基于变压器的动脉自旋标记灌注MRI去噪。

IF 2.9 3区计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Visual Computer

Pub Date : 2025-07-03 DOI: 10.1007/s00371-025-04061-x

Muhammad Nadeem Cheema, Lei Zhang, Anam Nazir, Yiran Li, John A Detre, Ze Wang

Arterial Spin Labeling (ASL) perfusion MRI is the only non-invasive technique for quantifying regional cerebral blood flow (CBF) visualization, which is an important physiological variable. ASL MRI has a relatively low signal-to-noise-ratio (SNR), making it challenging to achieve high quality CBF images using limited data. Promising ASL CBF denoising results have been shown in recent convolutional neural network (CNN)-based methods. A common problem of these methods is the loss of output image texture and image intensity variabilities. To address this problem, we proposed a Hybrid U-Net and Swin Transformer (HUST) ASL CBF denoising method. Transformers explicitly encode spatial positions of input data and can learn features with long-range dependency. These features can substantially mitigate the image blurring issue and preserve individual data variability. We used the U-Net as the network backbone due to its demonstrated capability for capturing local and global features and replaced the original CNNs layers with transformers. Swin Transformer was used to reduce the number of parameters required by a regular transformer for image denoising. Reduction in parameters is achieved by hierarchical structure along with shifting window-based attention mechanism. The proposed method is trained and tested with 2D and 3D ASL CBF images, HUST substantially improved CBF image visualization and preserved image textures. The 2D data were acquired from 277 normal healthy subjects aged 23 to 47, 110 males, and 167 females were included. The 3D data (110 subjects) were pooled from a local database and were acquired using our background suppressed 3D stack of spirals fast spin echo pseudo-continuous ASL sequence ^27-30. HUST makes it possible to substantially reduce the data acquisition time without compromising CBF quantification quality. HUST outperforms three state-of-the-art for both 2D and 3D ASL perfusion MRI data, achieving higher mean PSNR (45.15 for 3D, 33.67 for 2D) and SSIM (0.99 for 3D, 0.96 for 2D), indicating superior image quality and closer resemblance to the reference image.

动脉自旋标记（ASL）灌注MRI是唯一一种量化区域脑血流量（CBF）可视化的无创技术，是一个重要的生理变量。ASL MRI具有相对较低的信噪比（SNR），这使得使用有限的数据获得高质量的CBF图像具有挑战性。近年来基于卷积神经网络（CNN）的方法已显示出良好的ASL脑电信号去噪效果。这些方法的一个共同问题是输出图像纹理和图像强度可变性的损失。为了解决这个问题，我们提出了一种混合U-Net和Swin变压器（HUST） ASL CBF去噪方法。变压器显式地编码输入数据的空间位置，并且可以学习具有远程依赖关系的特征。这些特征可以大大减轻图像模糊问题，并保持个人数据的可变性。我们使用U-Net作为网络骨干，因为它具有捕获本地和全局特征的能力，并用变压器取代了原来的cnn层。采用Swin变压器来减少常规变压器在图像去噪时所需的参数数量。通过分层结构和基于移动窗口的注意机制实现参数约简。通过对二维和三维ASL CBF图像的训练和测试，HUST大大提高了CBF图像的可视化效果，并保留了图像纹理。二维数据来自277名23 ~ 47岁的正常健康受试者，其中男性110人，女性167人。三维数据（110名受试者）来自本地数据库，使用我们的背景抑制螺旋快速自旋回波伪连续ASL序列27-30获得。HUST可以在不影响CBF量化质量的情况下大幅减少数据采集时间。HUST在2D和3D ASL灌注MRI数据方面都优于三种最先进的技术，实现了更高的平均PSNR （3D为45.15,2D为33.67）和SSIM (3D为0.99,2D为0.96)，表明了更高的图像质量和更接近参考图像。

{"title":"Transformer-based arterial spin labeling perfusion MRI denoising.","authors":"Muhammad Nadeem Cheema, Lei Zhang, Anam Nazir, Yiran Li, John A Detre, Ze Wang","doi":"10.1007/s00371-025-04061-x","DOIUrl":"https://doi.org/10.1007/s00371-025-04061-x","url":null,"abstract":"Arterial Spin Labeling (ASL) perfusion MRI is the only non-invasive technique for quantifying regional cerebral blood flow (CBF) visualization, which is an important physiological variable. ASL MRI has a relatively low signal-to-noise-ratio (SNR), making it challenging to achieve high quality CBF images using limited data. Promising ASL CBF denoising results have been shown in recent convolutional neural network (CNN)-based methods. A common problem of these methods is the loss of output image texture and image intensity variabilities. To address this problem, we proposed a Hybrid U-Net and Swin Transformer (HUST) ASL CBF denoising method. Transformers explicitly encode spatial positions of input data and can learn features with long-range dependency. These features can substantially mitigate the image blurring issue and preserve individual data variability. We used the U-Net as the network backbone due to its demonstrated capability for capturing local and global features and replaced the original CNNs layers with transformers. Swin Transformer was used to reduce the number of parameters required by a regular transformer for image denoising. Reduction in parameters is achieved by hierarchical structure along with shifting window-based attention mechanism. The proposed method is trained and tested with 2D and 3D ASL CBF images, HUST substantially improved CBF image visualization and preserved image textures. The 2D data were acquired from 277 normal healthy subjects aged 23 to 47, 110 males, and 167 females were included. The 3D data (110 subjects) were pooled from a local database and were acquired using our background suppressed 3D stack of spirals fast spin echo pseudo-continuous ASL sequence 27-30. HUST makes it possible to substantially reduce the data acquisition time without compromising CBF quantification quality. HUST outperforms three state-of-the-art for both 2D and 3D ASL perfusion MRI data, achieving higher mean PSNR (45.15 for 3D, 33.67 for 2D) and SSIM (0.99 for 3D, 0.96 for 2D), indicating superior image quality and closer resemblance to the reference image.","PeriodicalId":49376,"journal":{"name":"Visual Computer","volume":" ","pages":""},"PeriodicalIF":2.9,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12366763/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human Plasma Proteomic Profile of Clonal Hematopoiesis. 克隆性造血的人体血浆蛋白质组概况

IF 2.9 3区计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Visual Computer

Pub Date : 2024-10-31 DOI: 10.1101/2023.07.25.550557

Zhi Yu, Amélie Vromman, Ngoc Quynh H Nguyen, Art Schuermans, Thiago Rentz, Shamsudheen K Vellarikkal, Md Mesbah Uddin, Abhishek Niroula, Gabriel Griffin, Michael C Honigberg, Amy E Lin, Christopher J Gibson, Daniel H Katz, Usman Tahir, Shi Fang, Sara Haidermota, Shriienidhie Ganesh, Tajmara Antoine, Joshua Weinstock, Thomas R Austin, Vasan S Ramachandran, Gina M Peloso, Whitney Hornsby, Peter Ganz, JoAnn E Manson, Bernhard Haring, Charles L Kooperberg, Alexander P Reiner, Joshua C Bis, Bruce M Psaty, Yuan-I Min, Adolfo Correa, Leslie A Lange, Wendy S Post, Jerome I Rotter, Stephen S Rich, James G Wilson, Benjamin L Ebert, Bing Yu, Christie M Ballantyne, Josef Coresh, Vijay G Sankaran, Alexander G Bick, Siddhartha Jaiswal, Robert E Gerszten, Peter Libby, Rajat M Gupta, Pradeep Natarajan

Plasma proteomic profiles associated with subclinical somatic mutations in blood cells may offer novel insights into downstream clinical consequences. Here, we explore such patterns in clonal hematopoiesis of indeterminate potential (CHIP), which is linked to several cancer and non-cancer outcomes, including coronary artery disease (CAD). Among 61,833 ancestrally diverse participants (3,881 with CHIP) from NHLBI TOPMed and UK Biobank with blood-based DNA sequencing and proteomic measurements (1,148 proteins by SomaScan in TOPMed and 2,917 proteins by Olink in UK Biobank), we identified 32 and 345 unique proteins from TOPMed and UK Biobank, respectively, associated with the most prevalent driver genes (DNMT3A, TET2, and ASXL1). These associations showed substantial heterogeneity by driver genes, sex, and race, and were enriched for immune response and inflammation pathways. Mendelian randomization in humans, coupled with ELISA in hematopoietic Tet2-/- vs wild-type mice validation, disentangled causal proteomic perturbations from TET2 CHIP. Lastly, we identified plasma proteins shared between CHIP and CAD.

与血细胞亚临床体细胞突变相关的血浆蛋白质组图谱可为下游临床后果提供新的见解。在这里，我们探讨了具有不确定潜能的克隆性造血（CHIP）中的这种模式，CHIP 与包括冠状动脉疾病（CAD）在内的多种癌症和非癌症结果有关。在来自 NHLBI TOPMed 和英国生物库的 61,833 名祖先不同的参与者（3,881 人患有 CHIP）中，我们通过基于血液的 DNA 测序和蛋白质组测量（TOPMed 的 SomaScan 检测 1,148 个蛋白质，英国生物库的 Olink 检测 2,917 个蛋白质），分别从 TOPMed 和英国生物库中鉴定出 32 个和 345 个独特的蛋白质，这些蛋白质与最普遍的驱动基因（DNMT3A、TET2 和 ASXL1）相关。这些关联因驱动基因、性别和种族的不同而表现出很大的异质性，并且富集于免疫反应和炎症通路。人类的孟德尔随机化以及造血 Tet2 -/- 与野生型小鼠的 ELISA 验证，将因果蛋白质组扰动与 TET2 CHIP 区分开来。最后，我们确定了 CHIP 和 CAD 之间共有的血浆蛋白。

{"title":"Human Plasma Proteomic Profile of Clonal Hematopoiesis.","authors":"Zhi Yu, Amélie Vromman, Ngoc Quynh H Nguyen, Art Schuermans, Thiago Rentz, Shamsudheen K Vellarikkal, Md Mesbah Uddin, Abhishek Niroula, Gabriel Griffin, Michael C Honigberg, Amy E Lin, Christopher J Gibson, Daniel H Katz, Usman Tahir, Shi Fang, Sara Haidermota, Shriienidhie Ganesh, Tajmara Antoine, Joshua Weinstock, Thomas R Austin, Vasan S Ramachandran, Gina M Peloso, Whitney Hornsby, Peter Ganz, JoAnn E Manson, Bernhard Haring, Charles L Kooperberg, Alexander P Reiner, Joshua C Bis, Bruce M Psaty, Yuan-I Min, Adolfo Correa, Leslie A Lange, Wendy S Post, Jerome I Rotter, Stephen S Rich, James G Wilson, Benjamin L Ebert, Bing Yu, Christie M Ballantyne, Josef Coresh, Vijay G Sankaran, Alexander G Bick, Siddhartha Jaiswal, Robert E Gerszten, Peter Libby, Rajat M Gupta, Pradeep Natarajan","doi":"10.1101/2023.07.25.550557","DOIUrl":"10.1101/2023.07.25.550557","url":null,"abstract":"Plasma proteomic profiles associated with subclinical somatic mutations in blood cells may offer novel insights into downstream clinical consequences. Here, we explore such patterns in clonal hematopoiesis of indeterminate potential (CHIP), which is linked to several cancer and non-cancer outcomes, including coronary artery disease (CAD). Among 61,833 ancestrally diverse participants (3,881 with CHIP) from NHLBI TOPMed and UK Biobank with blood-based DNA sequencing and proteomic measurements (1,148 proteins by SomaScan in TOPMed and 2,917 proteins by Olink in UK Biobank), we identified 32 and 345 unique proteins from TOPMed and UK Biobank, respectively, associated with the most prevalent driver genes (DNMT3A, TET2, and ASXL1). These associations showed substantial heterogeneity by driver genes, sex, and race, and were enriched for immune response and inflammation pathways. Mendelian randomization in humans, coupled with ELISA in hematopoietic Tet2-/- vs wild-type mice validation, disentangled causal proteomic perturbations from TET2 CHIP. Lastly, we identified plasma proteins shared between CHIP and CAD.","PeriodicalId":49376,"journal":{"name":"Visual Computer","volume":"31 1","pages":""},"PeriodicalIF":2.9,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11565774/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73564233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robotic Low Anterior Resection After Transanal Minimally Invasive Surgery and Chemoradiation Therapy for T1N1a Rectal Cancer. 经肛门微创手术和化疗治疗 T1N1a 直肠癌后的机器人低位前切除术

IF 3.9 3区计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Visual Computer

Pub Date : 2024-01-01 Epub Date: 2023-08-30 DOI: 10.1097/DCR.0000000000002923

Ryan A Schmelter, Marc A Gorvet, Zachary Grossmann, Clinton Crowder, Shankar R Raman