High Intensity Focused Ultrasound (HIFU) can be used to achieve a local temperature increase deep inside the human body in a non-invasive way. MRI guidance of the procedure allows in situ target definition. In addition, MRI can be used to provide continuous temperature mapping during HIFU for spatial and temporal control of the heating procedure and prediction of the final lesion based on the received thermal dose. Temperature mapping of mobile organs as kidney and liver is challenging, as well as real-time processing methods for feedback control of the HIFU procedure. In this paper, recent technological advances are reviewed in MR temperature mapping of these organs, in motion compensation of the HIFU beam, in intercostal HIFU sonication, and in volumetric ablation and feedback control strategies. Recent pre-clinical studies have demonstrated the feasibility of each of these novel methods. The perspectives to translate those advances into the clinic are addressed. It can be concluded that MR guided HIFU for ablation in liver and kidney appears feasible but requires further work on integration of technologically advanced methods.
University of Pennsylvania（宾夕法尼亚大学）；Yantai University（烟台大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；The Children's Hospital of Philadelphia（费城儿童医院）
Classification of ultrasound (US) kidney images for diagnosis of congenital abnormalities of the kidney and urinary tract (CAKUT) in children is a challenging task. It is desirable to improve existing pattern classification models that are built upon conventional image features. In this study, we propose a transfer learning-based method to extract imaging features from US kidney images in order to improve the CAKUT diagnosis in children. Particularly, a pre-trained deep learning model (imagenet-caffe-alex) is adopted for transfer learning-based feature extraction from 3-channel feature maps co…
James Cook University（詹姆斯·库克大学）；Mahidol University（玛希隆大学）；University of Bremen（不来梅大学）
Automatic segmentation of hepatic lesions in computed tomography (CT) images is a challenging task to perform due to heterogeneous, diffusive shape of tumors and complex background. To address the problem more and more researchers rely on assistance of deep convolutional neural networks (CNN) with 2D or 3D type architecture that have proven to be effective in a wide range of computer vision tasks, including medical image processing. In this technical report, we carry out research focused on more careful approach to the process of learning rather than on complex architecture of the CNN. We have…
PAII Inc.（PAII 公司）；Chang Gung Memorial Hospital, Linkou Medical Center（长庚纪念医院林口医学中心）；Institute of Molecular and Genomic Medicine, National Health Research Institutes（国家卫生研究院分子与基因组医学研究所）；Ping An Insurance Group（平安保险集团）
Background & Aims: Hepatic steatosis is a major cause of chronic liver disease. 2D ultrasound is the most widely used non-invasive tool for screening and monitoring, but associated diagnoses are highly subjective. We developed a scalable deep learning (DL) algorithm for quantitative scoring of liver steatosis from 2D ultrasound images. Approach & Results: Using retrospectively collected multi-view ultrasound data from 3,310 patients, 19,513 studies, and 228,075 images, we trained a DL algorithm to diagnose steatosis stages (healthy, mild, moderate, or severe) from ultrasound diagnoses. Perform…
Middlesex University（密德萨斯大学）；UCL Institute of Child Health（伦敦大学学院儿童健康研究所）；University of Surrey（萨里大学）
Delineation of the kidney region in dynamic contrast-enhanced magnetic resonance Imaging (DCE-MRI) is required during post-acquisition analysis in order to quantify various aspects of renal function, such as filtration and perfusion or blood flow. However, this can be obfuscated by the Partial Volume Effect (PVE), caused due to the mixing of any single voxel with two or more signal intensities from adjacent regions such as liver region and other tissues. To avoid this problem, firstly, a kidney region of interest (ROI) needs to be defined for the analysis. A clinician may choose to select a re…
Emory University（埃默里大学）；University of Chicago（芝加哥大学）；Georgia Institute of Technology（佐治亚理工学院）；Emory University School of Medicine（埃默里大学医学院）
This study proposed a deep learning-based tracking method for ultrasound (US) image-guided radiation therapy. The proposed cascade deep learning model is composed of an attention network, a mask region-based convolutional neural network (mask R-CNN), and a long short-term memory (LSTM) network. The attention network learns a mapping from a US image to a suspected area of landmark motion in order to reduce the search region. The mask R-CNN then produces multiple region-of-interest (ROI) proposals in the reduced region and identifies the proposed landmark via three network heads: bounding box re…
AI generated annotations for Breast, Brain, Liver, Lungs and Prostate cancer collections in National Cancer Institute Imaging Data Commons
BAMF Health（BAMF健康公司）；National Institute of Health（美国国立卫生研究院）；Frederick National Laboratory for Cancer Research（弗雷德里克国家癌症研究实验室）；Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）
Kidney cancer is a severe disease which can be treated non-invasively using high-intensity focused ultrasound (HIFU) therapy. However, tissue in front of the transducer and the deep location of kidney can cause significant losses to the efficiency of the treatment. The effect of attenuation, refraction and reflection due to different tissue types on HIFU therapy of the kidney was studied using a nonlinear ultrasound simulation model. The geometry of the tissue was derived from a computed tomography (CT) dataset of a patient which had been segmented for water, bone, soft tissue, fat and kidney.…
The quantification of liver fat as a diagnostic assessment of steatosis remains an important priority for noninvasive imaging systems. We derive a framework in which the unknown fat volume percentage can be estimated from a pair of ultrasound measurements. The precise estimation of ultrasound speed of sound and attenuation within the liver are shown to be sufficient for estimating fat volume assuming a classical model of the properties of a composite elastic material. In this model, steatosis is represented as a random dispersion of spherical fat vacuoles with acoustic properties similar to th…
Objective: High-intensity focused ultrasound (HIFU) therapy can be used for non-invasive treatment of kidney (renal) cancer, but the clinical outcomes have been variable. In this study, the efficacy of renal HIFU therapy was studied using nonlinear acoustic and thermal simulations in three patients. Methods: The acoustic simulations were conducted with and without refraction in order to investigate its effect on the shape, size and pressure distribution at the focus. The values for the attenuation, sound speed, perfusion and thermal conductivity of the kidney were varied over the reported rang…
Institute of Fundamental Technological Research, Polish Academy of Sciences（波兰科学院基础技术研究所）；Medical University of Warsaw（华沙医科大学）
Convolutional neural networks (CNNs) have achieved remarkable success in medical image analysis tasks. In ultrasound (US) imaging, CNNs have been applied to object classification, image reconstruction and tissue characterization. However, CNNs can be vulnerable to adversarial attacks, even small perturbations applied to input data may significantly affect model performance and result in wrong output. In this work, we devise a novel adversarial attack, specific to ultrasound (US) imaging. US images are reconstructed based on radio-frequency signals. Since the appearance of US images depends on …
This paper presents a method to register a pre-operative Computed-Tomography (CT) volume to a sparse set of intra-operative Ultra-Sound (US) slices. In the context of percutaneous renal puncture, the aim is to transfer planning information to an intra-operative coordinate system. The spatial position of the US slices is measured by optically localizing a calibrated probe. Assuming the reproducibility of kidney motion during breathing, and no deformation of the organ, the method consists in optimizing a rigid 6 Degree Of Freedom (DOF) transform by evaluating at each step the similarity between …
Robust High-Resolution Multi-Organ Diffusion MRI Using Synthetic-Data-Tuned Prompt Learning
Xiamen University（厦门大学）；Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University（厦门大学萨本栋微纳米科学技术研究院）；The Second Hospital of Shandong University（山东大学第二医院）；Zhongshan Hospital, Fudan University (Xiamen Branch)（复旦大学附属中山医院厦门医院）；Neusoft Medical Systems（东软医疗系统股份有限公司）；United Imaging Healthcare（上海联影医疗科技股份有限公司）；Lishui Central Hospital（丽水市中心医院）；Xiang'an Hospital of Xiamen University, School of Medicine, Xiamen University（厦门大学附属翔安医院）；Zhongshan Hospital Affiliated to Xiamen University（厦门大学附属中山医院）；Xianning Central Hospital, The First Affiliated Hospital of Hubei University of Science and Technology（湖北科技学院附属第一医院（咸宁市中心医院））；th Hospital of PLA Joint Logistic Support Force, Dongfang Hospital of Xiamen University, School of Medicine, Xiamen University（厦门大学附属东方医院（解放军联勤保障部队第九〇〇医院））；The First Affiliated Hospital of the Medical College of Shantou University（汕头大学医学院第一附属医院）；The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University（厦门大学附属第一医院）；Xiamen University of Technology（厦门理工学院）
This paper presents a method to register a preoperative CT volume to a sparse set of intraoperative US slices. In the context of percutaneous renal puncture, the aim is to transfer a planning information to an intraoperative coordinate system. The spatial position of the US slices is measured by localizing a calibrated probe. Our method consists in optimizing a rigid 6 degree of freedom (DOF) transform by evaluating at each step the similarity between the set of US images and the CT volume. The images have been preprocessed in order to increase the relationship between CT and US pixels. Correl…
Purpose: As a typical chronic kidney disease (CKD), hypertensive nephrosclerosis (HN) is a common syndrome of hypertension, characterized by chronic kidney microvascular damage. Early diagnosis of microvascular damage using conventional ultrasound imaging encounters challenges in sensitivity and specificity owing to the inherent diffraction limit. Ultrasound localization microscopy (ULM) has been developed to obtain microvasculature and microvascular hemodynamics within the kidney, and would be a promising tool for early diagnosis of CKD. Methods: In this study, the advantage of ULM over conve…
Shadow Reduction in Ultrasound Imaging Using Differentiable Simulation and Radiance Field Decomposition
University of Oxford（牛津大学）；University of Amsterdam（阿姆斯特丹大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大-埃尔朗根-纽伦堡大学）；Imperial College London（伦敦帝国理工学院）；University of Copenhagen（哥本哈根大学）
The hearts, kidneys, livers, spleens and brains of ${}^57$Fe enriched wild-type and heterozygous $β$-thalassaemic mice at 1, 3, 6 and 9 months of age were studied by means of Mössbauer Spectroscopy at 80K. Ferritin-like iron depositions in the heart and the brain of the thalassaemic mice were found to be slightly increased while significant amounts of Ferritin-like iron were found in the kidneys, liver and spleen. The ferritin-like iron doublet, found in the organs, could be further separated into two sub-doublets representing the inner and surface structures of ferritin mineral core. Surface …
Accurate automatic organ segmentation is an important yet challenging problem for medical image analysis. The pancreas is an abdominal organ with very high anatomical variability. This inhibits traditional segmentation methods from achieving high accuracies, especially compared to other organs such as the liver, heart or kidneys. In this paper, we present a holistic learning approach that integrates semantic mid-level cues of deeply-learned organ interior and boundary maps via robust spatial aggregation using random forest. Our method generates boundary preserving pixel-wise class labels for p…
Duke University School of Medicine（杜克大学医学院）；Duke University（杜克大学）；University of Arizona（亚利桑那大学）
Purpose: To design multi-disease classifiers for body CT scans for three different organ systems using automatically extracted labels from radiology text reports.Materials & Methods: This retrospective study included a total of 12,092 patients (mean age 57 +- 18; 6,172 women) for model development and testing (from 2012-2017). Rule-based algorithms were used to extract 19,225 disease labels from 13,667 body CT scans from 12,092 patients. Using a three-dimensional DenseVNet, three organ systems were segmented: lungs and pleura; liver and gallbladder; and kidneys and ureters. For each organ, a t…
MRI-guided High Intensity Focused Ultrasound (MRI-HIFU) is a promising method for the non-invasive ablation of pathological tissue in many organs, including mobile organs such as liver and kidney. The possibility to locally deposit thermal energy in a non-invasive way opens a path towards new therapeutic strategies with improved reliability and reduced associated trauma, leading to improved efficacy, reduced hospitalization and costs. Liver and kidney tumors represent a major health problem because not all patients are suitable for curative treatment with surgery. Currently, radio-frequency is…
Graduate School of Informatics, Kyoto University（京都大学信息学研究科）；Graduate School of Medicine, Kyoto University（京都大学医学研究科）
Organ shape reconstruction based on a single-projection image during treatment has wide clinical scope, e.g., in image-guided radiotherapy and surgical guidance. We propose an image-to-graph convolutional network that achieves deformable registration of a 3D organ mesh for a single-viewpoint 2D projection image. This framework enables simultaneous training of two types of transformation: from the 2D projection image to a displacement map, and from the sampled per-vertex feature to a 3D displacement that satisfies the geometrical constraint of the mesh structure. Assuming application to radiati…
Computed ultrasound tomography in echo mode (CUTE) is a new ultrasound (US)-based medical imaging modality with promise for diagnosing various types of disease based on the tissue's speed of sound (SoS). It is developed for conventional pulse-echo US using handheld probes and can thus be implemented in state-of-the-art medical US systems. One promising application is the quantification of the liver fat fraction in fatty liver disease. So far, CUTE was demonstrated using linear array probes where the imaging depth is comparable to the aperture size. For liver imaging, however, convex probes are…
The influences of blood vessels and focused location on temperature distribution during high-intensity focused ultrasound (HIFU) ablation of liver tumors is studied. A three-dimensional acoustics-thermal-fluid coupling model is employed to compute the temperature field in the hepatic cancerous region. The model is based on the linear Westervelt and bioheat equations as well as the nonlinear Navier-Stokes equations for the liver parenchyma and blood vessels. The effect of acoustic streaming is also taken into account in the present HIFU simulation study. Different blood vessel diameters and foc…
Model-based treatment planning and exposimetry for high-intensity focused ultrasound (HIFU) requires the numerical simulation of nonlinear ultrasound propagation through heterogeneous and absorbing media. This is a computationally demanding problem due to the large distances travelled by the ultrasound waves relative to the wavelength of the highest frequency harmonic. Here, the k-space pseudospectral method is used to solve a set of coupled partial differential equations equivalent to a generalised Westervelt equation. The model is implemented in C++ and parallelised using the message passing…
In high intensity focused ultrasound (HIFU) systems using non-ionizing methods in cancer treatment, if the device is applied to the body externally, the HIFU beam can damage nearby healthy tissues and burn skin due to lack of knowledge about the viscoelastic properties of patient tissue and failure to consider the physical properties of tissue in treatment planning. Addressing this problem by using various methods, such as MRI or ultrasound, elastography can effectively measure visco-elastic properties of tissue and fits within the pattern of stimulation and total treatment planning. In this p…
Over the past few decades, researchers have developed several approaches such as the Reference Phantom Method (RPM) to estimate ultrasound attenuation coefficient (AC) and backscatter coefficient (BSC). AC and BSC can help to discriminate pathology from normal tissue during in-vivo imaging. In this paper, we propose a new RPM model to simultaneously compute AC and BSC for harmonic imaging and a normalized score that combines the two parameters as a measure of disease progression. The model utilizes the spectral difference between two regions of interest, the first, a proximal, close to the pro…
Non-invasive detection of microvascular alterations in deep tissues in vivo provides critical information for clinical diagnosis and evaluation of a broad-spectrum of pathologies. Recently, the emergence of super-resolution ultrasound localization microscopy (ULM) offers new possibilities for clinical imaging of microvasculature at capillary level. Currently, the clinical utility of ULM on clinical ultrasound scanners is hindered by the technical limitations, such as long data acquisition time, and compromised tracking performance associated with low imaging frame-rate. Here we present an in-h…
Ultrasound super-localization microscopy techniques presented in the last few years enable non-invasive imaging of vascular structures at the capillary level by tracking the flow of ultrasound contrast agents (gas microbubbles). However, these techniques are currently limited by low temporal resolution and long acquisition times. Super-resolution optical fluctuation imaging (SOFI) is a fluorescence microscopy technique enabling sub-diffraction limit imaging with high temporal resolution by calculating high order statistics of the fluctuating optical signal. The aim of this work is to achieve f…
High-intensity focused ultrasound (HIFU) is a promising treatment modality for the non-invasive ablation of pathogenic tissue in many organs. Optimal treatment planning strategies based on high-performance computing methods are expected to form a vital component of a successful clinical outcome in which healthy tissue is preserved and accurate focusing achieved. The practical application of the algorithms informing these strategies depends on the ability to produce fast and accurate full-wave patient-specific simulations, with minimal computational overheads. For realistic clinical scenarios, …
Non-invasive therapeutic ultrasound methods, such as high-intensity focused ultrasound (HIFU), have limited access to tissue targets shadowed by bones or presence of gas. This study demonstrates that an ultrasonically actuated medical needle can be used to translate nanoparticles and fluids under the action of nonlinear phenomena, potentially overcoming some limitations of HIFU. A simulation study was first conducted to study the delivery of a tracer with an ultrasonically actuated needle (33 kHz) inside a porous medium acting as a model for soft tissue. The model was then validated experiment…
