Medical ultrasound is widely used technique for diagnosing internal organs. As common artifacts, shadows often appear in ultrasound images. Detecting such shadows is curious because they prevent accurate diagnosis. In this paper, we propose a novel shadow detection method based on auto-encoding structure. It once separates an input image into a shadow image and a content image using two decoders and combines them to reconstruct the input. To lead the network into separating the input, we inject synthetic shadows into the input and make the network to predict them as the shadow image. Since we know the rough shape of shadows as basic domain knowledge, we can generate plausible shadows. These processes are achieved by using only unlabeled data. Experiments on ultrasound images for fetal heart diagnosis shows the effectiveness of the method.
Ultrasound imaging has been improving, but continues to suffer from inherent artifacts that are challenging to model, such as attenuation, shadowing, diffraction, speckle, etc. These artifacts can potentially confuse image analysis algorithms unless an attempt is made to assess the certainty of individual pixel values. Our novel confidence algorithms analyze pixel values using a directed acyclic graph based on acoustic physical properties of ultrasound imaging. We demonstrate unique capabilities of our approach and compare it against previous confidence-measurement algorithms for shadow-detect…
Queen’s University（女王大学）；University of British Columbia（不列颠哥伦比亚大学）；Exact Imaging（Exact Imaging公司）
Deep learning-based analysis of high-frequency, high-resolution micro-ultrasound data shows great promise for prostate cancer detection. Previous approaches to analysis of ultrasound data largely follow a supervised learning paradigm. Ground truth labels for ultrasound images used for training deep networks often include coarse annotations generated from the histopathological analysis of tissue samples obtained via biopsy. This creates inherent limitations on the availability and quality of labeled data, posing major challenges to the success of supervised learning methods. On the other hand, …
Detection of relative changes in circulating blood volume is important to guide resuscitation and manage variety of medical conditions including sepsis, trauma, dialysis and congestive heart failure. Recent studies have shown that estimates of circulating blood volume can be obtained from ultrasound imagery of the of the internal jugular vein (IJV). However, segmentation and tracking of the IJV is significantly influenced by speckle noise and shadowing which introduce uncertainty in the boundaries of the vessel. In this paper, we investigate the use of optical flow algorithms for segmentation …
Convolutional Neural Networks (CNN) have been found to have great potential in optical flow problems thanks to an abundance of data available for training a deep network. The displacement estimation step in UltraSound Elastography (USE) can be viewed as an optical flow problem. Despite the high performance of CNNs in optical flow, they have been rarely used for USE due to unique challenges that both input and output of USE networks impose. Ultrasound data has much higher high-frequency content compared to natural images. The outputs are also drastically different, where displacement values in …
ShanghaiTech University（上海科技大学）；Shanghai Advanced Research Institute, Chinese Academy of Sciences（中国科学院上海高等研究院）；University of Chinese Academy of Sciences（中国科学院大学）；The Chinese University of Hong Kong（香港中文大学）
Three-dimensional (3D) ultrasound imaging technique has been applied for scoliosis assessment, but current assessment method only uses coronal projection image and cannot illustrate the 3D deformity and vertebra rotation. The vertebra detection is essential to reveal 3D spine information, but the detection task is challenging due to complex data and limited annotations. We propose VertMatch, a two-step framework to detect vertebral structures in 3D ultrasound volume by utilizing unlabeled data in semi-supervised manner. The first step is to detect the possible positions of structures on transv…
Volume visualization is a method that displays three-dimensional (3D) data in two-dimensional (2D) space. Using 3D datasets instead of 2D traditional images improves the visualization of anatomical structures, and volume visualization helps radiologists and surgeons to review large datasets comprehensively so that diagnosis and treatment can be enhanced. In liver surgery, blood vessel detection is important. Liver vessels have various shapes and due to the presence of noise in the ultrasound images, they can be confused with noise. Suboptimal images can sometimes lead to surgical errors where …
Identifying visible tissue in intraoperative ultrasound: a method and application
The Hamlyn Centre（哈姆林中心）；Imperial College London（帝国理工学院伦敦分校）；Department Of Imaging（成像部）；Charing Cross Hospital（查林十字医院）；School Of Computation, Information and Technology（计算、信息与技术学校）；Technical University of Munich（慕尼黑技术大学）；Department Of Neurosurgery（神经外科部）
Johns Hopkins University（约翰斯·霍普金斯大学）；University of British Columbia（不列颠哥伦比亚大学）
Segmenting both bone surface and the corresponding acoustic shadow are fundamental tasks in ultrasound (US) guided orthopedic procedures. However, these tasks are challenging due to minimal and blurred bone surface response in US images, cross-machine discrepancy, imaging artifacts, and low signal-to-noise ratio. Notably, bone shadows are caused by a significant acoustic impedance mismatch between the soft tissue and bone surfaces. To leverage this mutual information between these highly related tasks, we propose a single end-to-end network with a shared transformer-based encoder and task inde…
Ultrasound simulation based on ray tracing enables the synthesis of highly realistic images. It can provide an interactive environment for training sonographers as an educational tool. However, due to high computational demand, there is a trade-off between image quality and interactivity, potentially leading to sub-optimal results at interactive rates. In this work we introduce a deep learning approach based on adversarial training that mitigates this trade-off by improving the quality of simulated images with constant computation time. An image-to-image translation framework is utilized to tr…
Xiamen University（厦门大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究院）；The Hong Kong Polytechnic University（香港理工大学）
Breast lesion detection in ultrasound is critical for breast cancer diagnosis. Existing methods mainly rely on individual 2D ultrasound images or combine unlabeled video and labeled 2D images to train models for breast lesion detection. In this paper, we first collect and annotate an ultrasound video dataset (188 videos) for breast lesion detection. Moreover, we propose a clip-level and video-level feature aggregated network (CVA-Net) for addressing breast lesion detection in ultrasound videos by aggregating video-level lesion classification features and clip-level temporal features. The clip-…
Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation
Research Ireland Centre for Research Training in Machine Learning（爱尔兰研究机器学习研究中心）；School of Medicine, University College Dublin（都柏林大学医学院）；School of Computer Science, University College Dublin（都柏林大学计算机科学学院）；School of Computer Science and Digital Technologies, Aston University（阿斯顿大学计算机科学与数字技术学院）
The University of Tokyo（东京大学）；Southeast University（东南大学）
Speech production is a dynamic procedure, which involved multi human organs including the tongue, jaw and lips. Modeling the dynamics of the vocal tract deformation is a fundamental problem to understand the speech, which is the most common way for human daily communication. Researchers employ several sensory streams to describe the process simultaneously, which are incontrovertibly statistically related to other streams. In this paper, we address the following question: given an observable image sequences of lips, can we picture the corresponding tongue motion. We formulated this problem as t…
University of Oxford（牛津大学）；Tel-Aviv University（特拉维夫大学）
Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations that are inconsistent in appearance and semantics. In this paper, we propose to improve visual representations of medical images via anatomy-aware contrastive learning (AWCL), which incorporates anatomy information to augment the positive/negative pa…
Stanford University（斯坦福大学）；University College London（伦敦大学学院）；University of California Los Angeles（加利福尼亚大学洛杉矶分校）
Prostate biopsy and image-guided treatment procedures are often performed under the guidance of ultrasound fused with magnetic resonance images (MRI). Accurate image fusion relies on accurate segmentation of the prostate on ultrasound images. Yet, the reduced signal-to-noise ratio and artifacts (e.g., speckle and shadowing) in ultrasound images limit the performance of automated prostate segmentation techniques and generalizing these methods to new image domains is inherently difficult. In this study, we address these challenges by introducing a novel 2.5D deep neural network for prostate segm…
Institute of Fundamental Technological Research, Polish Academy of Sciences（波兰科学院基础技术研究所）
Standard classification methods based on handcrafted morphological and texture features have achieved good performance in breast mass differentiation in ultrasound (US). In comparison to deep neural networks, commonly perceived as "black-box" models, classical techniques are based on features that have well-understood medical and physical interpretation. However, classifiers based on morphological features commonly underperform in the presence of the shadowing artifact and ill-defined mass borders, while texture based classifiers may fail when the US image is too noisy. Therefore, in practice …
Striving for Simplicity: Simple Yet Effective Prior-Aware Pseudo-Labeling for Semi-Supervised Ultrasound Image Segmentation
Wuhan University of Technology（武汉理工大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；MedAI Technology (Wuxi) Co. Ltd.（MedAI科技（无锡）有限公司）；Technical University of Munich（慕尼黑工业大学）
University College London（伦敦大学学院）；Frimley Health NHS Foundation Trust（弗林姆利健康国民医疗服务基金会信托）；Royal Berkshire NHS Foundation Trust（皇家伯克郡国民医疗服务基金会信托）；Hospital de La Santa Creu I Sant Pau（圣克鲁和圣保罗医院）；West Suffolk NHS Foundation Trust（西萨福克国民医疗服务基金会信托）；Cambridge University Hospital（剑桥大学医院）；University of Cambridge（剑桥大学）；Great Ormond Street Children's Hospital NHS Foundation Trust（大奥蒙德街儿童医院国民医疗服务基金会信托）；Institute of Child Health, University College London（伦敦大学学院儿童健康研究所）；UCL Queen Square Institute of Neurology（伦敦大学学院皇后广场神经病学研究所）；University of Pavia（帕维亚大学）
Lung ultrasound imaging has been shown effective in detecting typical patterns for interstitial pneumonia, as a point-of-care tool for both patients with COVID-19 and other community-acquired pneumonia (CAP). In this work, we focus on the hyperechoic B-line segmentation task. Using deep neural networks, we automatically outline the regions that are indicative of pathology-sensitive artifacts and their associated sonographic patterns. With a real-world data-scarce scenario, we investigate approaches to utilize both COVID-19 and CAP lung ultrasound data to train the networks; comparing fine-tuni…
USF-MAE: Ultrasound Self-Supervised Foundation Model with Masked Autoencoding
Department of Systems and Computer Engineering, Carleton University（系统与计算机工程系，卡尔顿大学）；Department of Clinical Science and Translational Medicine, University of Ottawa（临床科学与转化医学系，渥太华大学）；Department of Obstetrics and Gynecology, University of Ottawa（妇产科系，渥太华大学）；School of Epidemiology and Public Health, University of Ottawa（流行病学与公共卫生学院，渥太华大学）；Department of Methodological and Implementation Research, Ottawa Hospital Research Institute（方法学与实施研究系，渥太华医院研究学院）；Department of Acute Care Research, Ottawa Hospital Research Institute（急症护理研究系，渥太华医院研究学院）
University of Alberta（阿尔伯塔大学）；CHU Hospital（里昂大学医疗中心）
Intravascular Ultrasound (IVUS) is an intra-operative imaging modality that facilitates observing and appraising the vessel wall structure of the human coronary arteries. Segmentation of arterial wall boundaries from the IVUS images is not only crucial for quantitative analysis of the vessel walls and plaque characteristics, but is also necessary for generating 3D reconstructed models of the artery. The aim of this study is twofold. Firstly, we investigate the feasibility of using a recently proposed region detector, namely Extremal Region of Extremum Level (EREL) to delineate the luminal and …
IntraVascular UltraSound (IVUS) is one of the most effective imaging modalities that provides assistance to experts in order to diagnose and treat cardiovascular diseases. We address a central problem in IVUS image analysis with Fully Convolutional Network (FCN): automatically delineate the lumen and media-adventitia borders in IVUS images, which is crucial to shorten the diagnosis process or benefits a faster and more accurate 3D reconstruction of the artery. Particularly, we propose an FCN architecture, called IVUS-Net, followed by a post-processing contour extraction step, in order to autom…
Eindhoven University of Technology（埃因霍温理工大学）；Shandong University of Science and Technology（山东科技大学）；Philips Research（飞利浦研究院）
Catheter segmentation in 3D ultrasound is important for computer-assisted cardiac intervention. However, a large amount of labeled images are required to train a successful deep convolutional neural network (CNN) to segment the catheter, which is expensive and time-consuming. In this paper, we propose a novel catheter segmentation approach, which requests fewer annotations than the supervised learning method, but nevertheless achieves better performance. Our scheme considers a deep Q learning as the pre-localization step, which avoids voxel-level annotation and which can efficiently localize t…
Deep learning models, e.g. supervised Encoder-Decoder style networks, exhibit promising performance in medical image segmentation, but come with a high labelling cost. We propose TriSegNet, a semi-supervised semantic segmentation framework. It uses triple-view feature learning on a limited amount of labelled data and a large amount of unlabeled data. The triple-view architecture consists of three pixel-level classifiers and a low-level shared-weight learning module. The model is first initialized with labelled data. Label processing, including data perturbation, confidence label voting and unc…
Towards Enhanced Analysis of Lung Cancer Lesions in EBUS-TBNA -- A Semi-Supervised Video Object Detection Method
National Yang Ming Chiao Tung University（阳明交通大学）；National Taiwan University Cancer Center（台湾大学癌症中心）；National Taiwan University Hospital（台湾大学医院）；National Taiwan University Hsin-Chu Hospital（台湾大学新竹医院）
VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification
BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院生物医学工程与影像研究所）；University of Oklahoma（俄克拉荷马大学）；NVIDIA（英伟达公司）；Erasmus University Rotterdam（伊拉斯姆斯大学鹿特丹分校）；East River Medical Imaging（东河医学影像中心）；Cornell Medicine（康奈尔医学院）；Windreich Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院温赖希人工智能与人类健康系）
