Pub Date : 2024-09-10DOI: 10.1109/tmi.2024.3457228
Yirui Zhang, Yanni Zou, Peter X. Liu
{"title":"Point Cloud Registration in Laparoscopic Liver Surgery Using Keypoint Correspondence Registration Network","authors":"Yirui Zhang, Yanni Zou, Peter X. Liu","doi":"10.1109/tmi.2024.3457228","DOIUrl":"https://doi.org/10.1109/tmi.2024.3457228","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"103 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142166141","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}
Pub Date : 2024-09-09DOI: 10.1109/tmi.2024.3456676
Alexis Leconte, Jonathan Porée, Brice Rauby, Alice Wu, Nin Ghigo, Paul Xing, Stephen LEE, Chloé Bourquin, Gerardo Ramos-Palacios, Abbas F. Sadikot, Jean Provost
{"title":"A Tracking prior to Localization workflow for Ultrasound Localization Microscopy","authors":"Alexis Leconte, Jonathan Porée, Brice Rauby, Alice Wu, Nin Ghigo, Paul Xing, Stephen LEE, Chloé Bourquin, Gerardo Ramos-Palacios, Abbas F. Sadikot, Jean Provost","doi":"10.1109/tmi.2024.3456676","DOIUrl":"https://doi.org/10.1109/tmi.2024.3456676","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"104 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142160541","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}
Pub Date : 2024-09-09DOI: 10.1109/tmi.2024.3456595
Yilin Luo, Hsuan-Kai Huang, Karteekeya Sastry, Peng Hu, Xin Tong, Joseph Kuo, Yousuf Aborahama, Shuai Na, Umberto Villa, Mark A. Anastasio, Lihong V. Wang
{"title":"Full-wave Image Reconstruction in Transcranial Photoacoustic Computed Tomography using a Finite Element Method","authors":"Yilin Luo, Hsuan-Kai Huang, Karteekeya Sastry, Peng Hu, Xin Tong, Joseph Kuo, Yousuf Aborahama, Shuai Na, Umberto Villa, Mark A. Anastasio, Lihong V. Wang","doi":"10.1109/tmi.2024.3456595","DOIUrl":"https://doi.org/10.1109/tmi.2024.3456595","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"22 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142160540","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}
Pub Date : 2024-06-27DOI: 10.1109/tmi.2024.3419809
Wenting Chen, Jie Liu, Tommy W.S. Chow, Yixuan Yuan
{"title":"STAR-RL: Spatial-temporal Hierarchical Reinforcement Learning for Interpretable Pathology Image Super-Resolution","authors":"Wenting Chen, Jie Liu, Tommy W.S. Chow, Yixuan Yuan","doi":"10.1109/tmi.2024.3419809","DOIUrl":"https://doi.org/10.1109/tmi.2024.3419809","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"47 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141462332","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}
Pub Date : 2024-06-27DOI: 10.1109/tmi.2024.3419780
Chengkang Shen, Hao Zhu, You Zhou, Yu Liu, Si Yi, Lili Dong, Weipeng Zhao, David J. Brady, Xun Cao, Zhan Ma, Yi Lin
{"title":"Continuous 3D Myocardial Motion Tracking via Echocardiography","authors":"Chengkang Shen, Hao Zhu, You Zhou, Yu Liu, Si Yi, Lili Dong, Weipeng Zhao, David J. Brady, Xun Cao, Zhan Ma, Yi Lin","doi":"10.1109/tmi.2024.3419780","DOIUrl":"https://doi.org/10.1109/tmi.2024.3419780","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"30 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141462351","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}
Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5× and 6× accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.
并行成像是加速磁共振成像(MRI)数据采集的常用技术。从数学上讲,并行磁共振成像重建可表述为一个将稀疏采样的 k 空间测量值与所需磁共振成像图像相关联的逆问题。尽管许多现有的重建算法都取得了成功,但要从高度缩小的 k 空间测量数据中可靠地重建出高质量的图像,仍然是一项挑战。最近,隐式神经表征作为一种强大的范例出现了,它能利用部分获取数据的内部信息和物理特性生成所需的对象。在这项研究中,我们引入了 IMJENSE,这是一种基于特定扫描的隐式神经表征方法,用于改进并行 MRI 重建。具体来说,基础 MRI 图像和线圈灵敏度被建模为空间坐标的连续函数,分别由神经网络和多项式参数化。神经网络中的权重和多项式中的系数同时直接从稀疏获取的 k 空间测量数据中学习,而不需要完全采样的地面实况数据进行训练。得益于强大的连续表示法以及对磁共振成像和线圈灵敏度的联合估计,IMJENSE 优于传统的图像或 k 空间域重建算法。在校准数据极其有限的情况下,IMJENSE 比无监督校准和基于校准的深度学习方法更加稳定。结果表明,在二维笛卡尔采集中,IMJENSE 仅用 4 或 8 条校准线就能稳健地重建以 5 倍和 6 倍加速度采集的图像,这相当于 22.0% 和 19.5% 的欠采样率。高质量的结果和扫描特异性使所提出的方法有望进一步加速并行磁共振成像的数据采集。
{"title":"IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI","authors":"Rui-jun Feng, Qing Wu, Jie Feng, Huajun She, Chunlei Liu, Yuyao Zhang, Hongjiang Wei","doi":"10.48550/arXiv.2311.12892","DOIUrl":"https://doi.org/10.48550/arXiv.2311.12892","url":null,"abstract":"Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5× and 6× accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"202 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139254245","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}
To understand the biological characteristics of neurological disorders with functional connectivity (FC), recent studies have widely utilized deep learning-based models to identify the disease and conducted post-hoc analyses via explainable models to discover disease-related biomarkers. Most existing frameworks consist of three stages, namely, feature selection, feature extraction for classification, and analysis, where each stage is implemented separately. However, if the results at each stage lack reliability, it can cause misdiagnosis and incorrect analysis in afterward stages. In this study, we propose a novel unified framework that systemically integrates diagnoses (i.e., feature selection and feature extraction) and explanations. Notably, we devised an adaptive attention network as a feature selection approach to identify individual-specific disease-related connections. We also propose a functional network relational encoder that summarizes the global topological properties of FC by learning the inter-network relations without pre-defined edges between functional networks. Last but not least, our framework provides a novel explanatory power for neuroscientific interpretation, also termed counter-condition analysis. We simulated the FC that reverses the diagnostic information (i.e., counter-condition FC): converting a normal brain to be abnormal and vice versa. We validated the effectiveness of our framework by using two large resting-state functional magnetic resonance imaging (fMRI) datasets, Autism Brain Imaging Data Exchange (ABIDE) and REST-meta-MDD, and demonstrated that our framework outperforms other competing methods for disease identification. Furthermore, we analyzed the disease-related neurological patterns based on counter-condition analysis.
{"title":"A Learnable Counter-condition Analysis Framework for Functional Connectivity-based Neurological Disorder Diagnosis","authors":"Eunsong Kang, Da-Woon Heo, Jiwon Lee, Heung-Il Suk","doi":"10.48550/arXiv.2310.03964","DOIUrl":"https://doi.org/10.48550/arXiv.2310.03964","url":null,"abstract":"To understand the biological characteristics of neurological disorders with functional connectivity (FC), recent studies have widely utilized deep learning-based models to identify the disease and conducted post-hoc analyses via explainable models to discover disease-related biomarkers. Most existing frameworks consist of three stages, namely, feature selection, feature extraction for classification, and analysis, where each stage is implemented separately. However, if the results at each stage lack reliability, it can cause misdiagnosis and incorrect analysis in afterward stages. In this study, we propose a novel unified framework that systemically integrates diagnoses (i.e., feature selection and feature extraction) and explanations. Notably, we devised an adaptive attention network as a feature selection approach to identify individual-specific disease-related connections. We also propose a functional network relational encoder that summarizes the global topological properties of FC by learning the inter-network relations without pre-defined edges between functional networks. Last but not least, our framework provides a novel explanatory power for neuroscientific interpretation, also termed counter-condition analysis. We simulated the FC that reverses the diagnostic information (i.e., counter-condition FC): converting a normal brain to be abnormal and vice versa. We validated the effectiveness of our framework by using two large resting-state functional magnetic resonance imaging (fMRI) datasets, Autism Brain Imaging Data Exchange (ABIDE) and REST-meta-MDD, and demonstrated that our framework outperforms other competing methods for disease identification. Furthermore, we analyzed the disease-related neurological patterns based on counter-condition analysis.","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"8 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139322196","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}