Recent advances in deep learning have achieved promising performance for medical image analysis, while in most cases ground-truth annotations from human experts are necessary to train the deep model. In practice, such annotations are expensive to collect and can be scarce for medical imaging applications. Therefore, there is significant interest in learning representations from unlabelled raw data. In this paper, we propose a self-supervised learning approach to learn meaningful and transferable representations from medical imaging video without any type of human annotation. We assume that in order to learn such a representation, the model should identify anatomical structures from the unlabelled data. Therefore we force the model to address anatomy-aware tasks with free supervision from the data itself. Specifically, the model is designed to correct the order of a reshuffled video clip and at the same time predict the geometric transformation applied to the video clip. Experiments on fetal ultrasound video show that the proposed approach can effectively learn meaningful and strong representations, which transfer well to downstream tasks like standard plane detection and saliency prediction.
Carnegie Mellon University（卡内基梅隆大学）；Louisiana State University（路易斯安那州立大学）；Cosmeticsurg.net, LLC（Cosmeticsurg.net有限责任公司）
With the onset of the COVID-19 pandemic, ultrasound has emerged as an effective tool for bedside monitoring of patients. Due to this, a large amount of lung ultrasound scans have been made available which can be used for AI based diagnosis and analysis. Several AI-based patient severity scoring models have been proposed that rely on scoring the appearance of the ultrasound scans. AI models are trained using ultrasound-appearance severity scores that are manually labeled based on standardized visual features. We address the challenge of labeling every ultrasound frame in the video clips. Our co…
Indian Institute of Technology Palakkad（印度理工学院帕拉卡德分校）；University of Alberta（阿尔伯塔大学）；Hospital Universitario Puerta de Hierro（铁门大学医院）；Government Medical College Thiruvananthapuram（特里凡得琅政府医学院）；Sree Chitra Tirunal Institute for Medical Sciences & Technology（斯里奇特拉蒂鲁纳尔医学科学与技术研究所）
Most applications of deep learning techniques in medical imaging are supervised and require a large number of labeled data which is expensive and requires many hours of careful annotation by experts. In this paper, we propose an unsupervised, physics driven domain specific transporter framework with an attention mechanism to identify relevant key points with applications in ultrasound imaging. The proposed framework identifies key points that provide a concise geometric representation highlighting regions with high structural variation in ultrasound videos. We incorporate physics driven domain…
Massachusetts General Hospital（麻省总医院）；Massachusetts Institute of Technology（麻省理工学院）
Modern deep learning algorithms geared towards clinical adaption rely on a significant amount of high fidelity labeled data. Low-resource settings pose challenges like acquiring high fidelity data and becomes the bottleneck for developing artificial intelligence applications. Ultrasound images, stored in Digital Imaging and Communication in Medicine (DICOM) format, have additional metadata data corresponding to ultrasound image parameters and medical exams. In this work, we leverage DICOM metadata from ultrasound images to help learn representations of the ultrasound image. We demonstrate that…
The Efficacy of Semantics-Preserving Transformations in Self-Supervised Learning for Medical Ultrasound
Cheriton School of Computer Science, University of Waterloo（滑铁卢大学计算机科学学院）；Department of Systems Design Engineering, University of Waterloo（滑铁卢大学系统设计工程系）；Schulich School of Medicine and Dentistry, Western University（西部大学施乐希医学与牙科学校）
Video is an essential imaging modality for diagnostics, e.g. in ultrasound imaging, for endoscopy, or movement assessment. However, video hasn't received a lot of attention in the medical image analysis community. In the clinical practice, it is challenging to utilise raw diagnostic video data efficiently as video data takes a long time to process, annotate or audit. In this paper we introduce a novel, fully automatic video summarization method that is tailored to the needs of medical video data. Our approach is framed as reinforcement learning problem and produces agents focusing on the prese…
Intra-video Positive Pairs in Self-Supervised Learning for Ultrasound
Cheriton School of Computer Science（谢里顿计算机科学学院）；University of Waterloo（滑铁卢大学）；Department of Systems Design Engineering（系统设计工程系）；Division of Critical Care Medicine（重症医学科）；Western University（西安大略大学）
Indian Institute of Technology（印度理工学院）；University of Alberta（阿尔伯塔大学）；Hospital Universitario Puerta de Hierro（普埃塔德耶罗大学医院）；Government Medical College（政府医学院）；Sree Chitra Tirunal Institute of Medical Sciences and Technology（斯里奇特拉图鲁纳尔医学科学与技术研究所）；Bhagwan Mahaveer Jain Hospital（巴格万马哈维尔耆那医院）
The COVID-19 pandemic has highlighted the need for a tool to speed up triage in ultrasound scans and provide clinicians with fast access to relevant information. The proposed video-summarization technique is a step in this direction that provides clinicians access to relevant key-frames from a given ultrasound scan (such as lung ultrasound) while reducing resource, storage and bandwidth requirements. We propose a new unsupervised reinforcement learning (RL) framework with novel rewards that facilitates unsupervised learning avoiding tedious and impractical manual labelling for summarizing ultr…
Auto-US: An Ultrasound Video Diagnosis Agent Using Video Classification Framework and LLMs
The Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging（安徽省级国际联合先进技术医学影像研究中心）；Anhui University（安徽大学）；School of First Clinical Medicine（第一临床医学院）；Anhui University of Science and Technology（安徽理工大学）；School of Medicine（医学院）；The First Hospital（第一医院）
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…
In medical imaging, manual annotations can be expensive to acquire and sometimes infeasible to access, making conventional deep learning-based models difficult to scale. As a result, it would be beneficial if useful representations could be derived from raw data without the need for manual annotations. In this paper, we propose to address the problem of self-supervised representation learning with multi-modal ultrasound video-speech raw data. For this case, we assume that there is a high correlation between the ultrasound video and the corresponding narrative speech audio of the sonographer. I…
Fetal brain magnetic resonance imaging (MRI) offers exquisite images of the developing brain but is not suitable for anomaly screening. For this ultrasound (US) is employed. While expert sonographers are adept at reading US images, MR images are much easier for non-experts to interpret. Hence in this paper we seek to produce images with MRI-like appearance directly from clinical US images. Our own clinical motivation is to seek a way to communicate US findings to patients or clinical professionals unfamiliar with US, but in medical image analysis such a capability is potentially useful, for in…
Generative deep learning for foundational video translation in ultrasound
Department of Medicine, Division of Cardiology（医学系，心脏病科）；Bakar Computational Health Sciences Institute（Bakar计算健康科学研究所）；University of California, San Francisco（加州大学旧金山分校）；UCSF-UC Berkeley Joint Program in Computational Precision Health（UCSF-伯克利计算精准健康联合项目）；Department of Radiology, Center for Intelligent Imaging（放射科，智能成像中心）
Cross-Modal Ultrasound-MRI Learning for Fetal Brain Ventricular Volumetry and Abnormality Screening
Harvard Medical School（哈佛医学院）；Shenzhen University（深圳大学）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）；School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）；School of Biomedical Engineering and Informatics, Nanjing Medical University（南京医科大学生物医学工程与信息学院）
Ultrasound image quality has continually been improving. However, when needles or other metallic objects are operating inside the tissue, the resulting reverberation artifacts can severely corrupt the surrounding image quality. Such effects are challenging for existing computer vision algorithms for medical image analysis. Needle reverberation artifacts can be hard to identify at times and affect various pixel values to different degrees. The boundaries of such artifacts are ambiguous, leading to disagreement among human experts labeling the artifacts. We propose a weakly- and semi-supervised,…
HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation
University of Information Technology（信息科技大学）；Ho Chi Minh University of Technology（胡志明市技术大学）；University of Science（科学大学）；Vietnam National University（越南国家大学）；Boston University（波士顿大学）；Taipei Medical University（台北医学大学）；Posts and Telecommunications Institute of Technology（邮电技术学院）；New Mexico State University（新墨西哥州立大学）
Shanghai Institute for Advanced Communication and Data Science（上海先进通信与数据科学研究院）；The First Affiliated Hospital of Anhui Medical University（安徽医科大学第一附属医院）；Fudan University Shanghai Cancer Center（复旦大学附属肿瘤医院）；Shanghai Medical College, Fudan University（复旦大学上海医学院）；School of Science, Shanghai University（上海大学理学院）
Elastography ultrasound (EUS) provides additional bio-mechanical in-formation about lesion for B-mode ultrasound (BUS) in the diagnosis of breast cancers. However, joint utilization of both BUS and EUS is not popular due to the lack of EUS devices in rural hospitals, which arouses a novel modality im-balance problem in computer-aided diagnosis (CAD) for breast cancers. Current transfer learning (TL) pay little attention to this special issue of clinical modality imbalance, that is, the source domain (EUS modality) has fewer labeled samples than those in the target domain (BUS modality). Moreov…
Temporal Representation Learning for Real-Time Ultrasound Analysis
Department of Computer Science, ETH Zurich, Switzerland（苏黎世联邦理工学院计算机科学系）；Department of Biomedical Engineering, University of Basel, Switzerland（巴塞尔大学生物医学工程系）
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…
Fudan University（复旦大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Shenzhen Research Institute of Big Data（深圳市大数据研究院）；Southern University of Science and Technology（南方科技大学）
Most deep neural networks (DNNs) based ultrasound (US) medical image analysis models use pretrained backbones (e.g., ImageNet) for better model generalization. However, the domain gap between natural and medical images causes an inevitable performance bottleneck. To alleviate this problem, an US dataset named US-4 is constructed for direct pretraining on the same domain. It contains over 23,000 images from four US video sub-datasets. To learn robust features from US-4, we propose an US semi-supervised contrastive learning method, named USCL, for pretraining. In order to avoid high similarities…
Variable-frame CNNLSTM for Breast Nodule Classification using Ultrasound Videos
Beijing Normal University（北京师范大学）；Xi’an Jiaotong University（西安交通大学）；The First Affiliated Hospital of Xi’an Jiaotong University（西安交通大学第一附属医院）；Xiangya Hospital, Central South University（中南大学湘雅医院）；Frontline Intelligent Technology (Nanjing) Co., Ltd.（南京前沿智能科技有限公司）；The Second Hospital of Hebei Medical University（河北医科大学第二医院）
Detecting acoustic shadows in ultrasound images is important in many clinical and engineering applications. Real-time feedback of acoustic shadows can guide sonographers to a standardized diagnostic viewing plane with minimal artifacts and can provide additional information for other automatic image analysis algorithms. However, automatically detecting shadow regions using learning-based algorithms is challenging because pixel-wise ground truth annotation of acoustic shadows is subjective and time consuming. In this paper we propose a weakly supervised method for automatic confidence estimatio…
Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
Department of Engineering Science, University of Oxford（工程科学系，牛津大学）；Nuffield Department of Women’s and Reproductive Health, University of Oxford（妇女与生殖健康系，牛津大学）；Fundamental AI Lab, University of Technology Nuremberg（基础人工智能实验室，纽伦堡技术大学）；University of Amsterdam（阿姆斯特丹大学）
Weakly Supervised Spatial Grounding for Discriminative Attention-Based Ultrasound-Histopathology Alignment in Prostate Cancer Grading
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute（向量研究所）；Ordensklinikum Linz（林茨教团医院）；University of Alberta（阿尔伯塔大学）；Exact Imaging（Exact Imaging公司）
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-…
Blind Restoration of High-Resolution Ultrasound Video
Department of Mathematics, City University of Hong Kong（香港城市大学数学系）；Hong Kong Centre for Cerebro-cardiovascular Health Engineering（香港脑心血管健康工程中心）；Department of the Arts, University of Bologna（博洛尼亚大学艺术系）；Department of Computer Science and Engineering, University of Bologna（博洛尼亚大学计算机科学与工程系）；Department of Operations and Risk Management and School of Data Science, Lingnan University（岭南大学运营与风险管理系及数据科学学院）
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, …
Sano Centre for Computational Medicine（萨诺计算医学中心）；Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学研究所）；The Medical Centre of Postgraduate Education（研究生教育医学中心）；Poznan University of Medical Sciences（波兹南医科大学）；Medical University of Warsaw（华沙医科大学）；Warsaw University of Technology（华沙理工大学）
Predicting fetal weight at birth is an important aspect of perinatal care, particularly in the context of antenatal management, which includes the planned timing and the mode of delivery. Accurate prediction of weight using prenatal ultrasound is challenging as it requires images of specific fetal body parts during advanced pregnancy which is difficult to capture due to poor quality of images caused by the lack of amniotic fluid. As a consequence, predictions which rely on standard methods often suffer from significant errors. In this paper we propose the Residual Transformer Module which exte…
Cochin University of Science and Technology（科钦科技大学）；Indian Institute of Technology Palakkad（帕拉卡德印度理工学院）
In the recent past with the rapid surge of COVID-19 infections, lung ultrasound has emerged as a fast and powerful diagnostic tool particularly for continuous and periodic monitoring of the lung. There have been many attempts towards severity classification, segmentation and detection of key landmarks in the lung. Leveraging the progress, an automated lung ultrasound video analysis package is presented in this work, which can provide summary of key frames in the video, flagging of the key frames with lung infection and options to automatically detect and segment the lung landmarks. The integra…
Guy’s and St Thomas’ NHS Foundation Trust（盖伊和圣托马斯国民保健服务基金会信托）；King’s College London（伦敦国王学院）；King’s College Hospital NHS Foundation Trust（国王学院医院国民保健服务基金会信托）
Lung ultrasound (LUS) imaging is used to assess lung abnormalities, including the presence of B-line artefacts due to fluid leakage into the lungs caused by a variety of diseases. However, manual detection of these artefacts is challenging. In this paper, we propose a novel methodology to automatically detect and localize B-lines in LUS videos using deep neural networks trained with weak labels. To this end, we combine a convolutional neural network (CNN) with a long short-term memory (LSTM) network and a temporal attention mechanism. Four different models are compared using data from 60 patie…
VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videos
Dept. of Biomedical Informatics \& Data Science, Yale University, New Haven, USA Yale Biomedical Imaging Institute, Yale University, New Haven, USA Dept. of Biomedical Engineering, University of Basel, Allschwil, Switzerland Dept. of Radiology \& Biomedical Imaging, Yale University, New Haven, USA Dept. of Biomedical Engineering, Yale University, New Haven, USA
Faculty of Engineering and Applied Sciences, Memorial University（纪念大学工程与应用科学学院）；Faculty of Medicine, Memorial University（纪念大学医学院）
Detection of relative changes in circulating blood volume is important to guide resuscitation and manage a 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 the cross-sectional area (CSA) of the internal jugular vein (IJV) from ultrasound images. However, accurate segmentation and tracking of the IJV in ultrasound imaging is a challenging task and is significantly influenced by a number of parameters such as the image quality, shape, and temporal variation. In …
Frontline Intelligent Technology (Nanjing) Co.,Ltd.（南京锋线智能科技有限公司）；Xiangya Hospital, Central South University（中南大学湘雅医院）
Ultrasound examination is widely used in the clinical diagnosis of thyroid nodules (benign/malignant). However, the accuracy relies heavily on radiologist experience. Although deep learning techniques have been investigated for thyroid nodules recognition. Current solutions are mainly based on static ultrasound images, with limited temporal information used and inconsistent with clinical diagnosis. This paper proposes a novel method for the automated recognition of thyroid nodules through an exhaustive exploration of ultrasound videos and key-frames. We first propose a detection-localization f…
School of Electrical Engineering and Computer Science, University of Ottawa（渥太华大学电气工程与计算机科学学院）
The progress of deep convolutional neural networks has been successfully exploited in various real-time computer vision tasks such as image classification and segmentation. Owing to the development of computational units, availability of digital datasets, and improved performance of deep learning models, fully automatic and accurate tracking of tongue contours in real-time ultrasound data became practical only in recent years. Recent studies have shown that the performance of deep learning techniques is significant in the tracking of ultrasound tongue contours in real-time applications such as…
National Research Council Canada（加拿大国家研究委员会）；University of Waterloo（滑铁卢大学）
Besides vaccination, as an effective way to mitigate the further spread of COVID-19, fast and accurate screening of individuals to test for the disease is yet necessary to ensure public health safety. We propose COVID-Net UV, an end-to-end hybrid spatio-temporal deep neural network architecture, to detect COVID-19 infection from lung point-of-care ultrasound videos captured by convex transducers. COVID-Net UV comprises a convolutional neural network that extracts spatial features and a recurrent neural network that learns temporal dependence. After careful hyperparameter tuning, the network ac…
Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；University of Michigan（密歇根大学）；Columbia University in the City of New York（纽约哥伦比亚大学）；National University of Defense Technology（国防科技大学）
A challenge in speech production research is to predict future tongue movements based on a short period of past tongue movements. This study tackles speaker-dependent tongue motion prediction problem in unlabeled ultrasound videos with convolutional long short-term memory (ConvLSTM) networks. The model has been tested on two different ultrasound corpora. ConvLSTM outperforms 3-dimensional convolutional neural network (3DCNN) in predicting the 9\textsuperscript{th} frames based on 8 preceding frames, and also demonstrates good capacity to predict only the tongue contours in future frames. Furth…
Anhui University of Technology（安徽工业大学）；Aberystwyth University（阿伯里斯特威斯大学）
Due to the limitations of sensors, the transmission medium and the intrinsic properties of ultrasound, the quality of ultrasound imaging is always not ideal, especially its low spatial resolution. To remedy this situation, deep learning networks have been recently developed for ultrasound image super-resolution (SR) because of the powerful approximation capability. However, most current supervised SR methods are not suitable for ultrasound medical images because the medical image samples are always rare, and usually, there are no low-resolution (LR) and high-resolution (HR) training pairs in r…
Semi-supervised learning methods have achieved excellent performance on standard benchmark datasets using very few labelled images. Anatomy classification in fetal 2D ultrasound is an ideal problem setting to test whether these results translate to non-ideal data. Our results indicate that inclusion of a challenging background class can be detrimental and that semi-supervised learning mostly benefits classes that are already distinct, sometimes at the expense of more similar classes.
Sano Centre for Computational Medicine（萨诺计算医学中心）；Warsaw University of Technology（华沙理工大学）；Fetai Health Ltd.（Fetai健康有限公司）；Medical University of Warsaw（华沙医科大学）；Tooploox（Tooploox公司）
In this paper, we propose an end-to-end multi-task neural network called FetalNet with an attention mechanism and stacked module for spatio-temporal fetal ultrasound scan video analysis. Fetal biometric measurement is a standard examination during pregnancy used for the fetus growth monitoring and estimation of gestational age and fetal weight. The main goal in fetal ultrasound scan video analysis is to find proper standard planes to measure the fetal head, abdomen and femur. Due to natural high speckle noise and shadows in ultrasound data, medical expertise and sonographic experience are requ…
Is Two-shot All You Need? A Label-efficient Approach for Video Segmentation in Breast Ultrasound
Guangdong Key Laboratory of Biomedical Measurements and Ultrasound Imaging（广东省生物医学测量与超声成像重点实验室）；School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University（深圳大学医学部生物医学工程学院）；Shenzhen University（深圳大学）
Shenzhen University（深圳大学）；Shenzhen RayShape Medical Technology Co., Ltd（深圳瑞影医疗科技有限公司）；Huizhou Central People’s Hospital（惠州市中心人民医院）
Ultrasound (US) is widely used for its advantages of real-time imaging, radiation-free and portability. In clinical practice, analysis and diagnosis often rely on US sequences rather than a single image to obtain dynamic anatomical information. This is challenging for novices to learn because practicing with adequate videos from patients is clinically unpractical. In this paper, we propose a novel framework to synthesize high-fidelity US videos. Specifically, the synthesis videos are generated by animating source content images based on the motion of given driving videos. Our highlights are th…
Korea University（高丽大学）；Hankik University of Foreign Studies（韩国外国语大学）
We propose a method for effectively utilizing weakly annotated image data in an object detection tasks of breast ultrasound images. Given the problem setting where a small, strongly annotated dataset and a large, weakly annotated dataset with no bounding box information are available, training an object detection model becomes a non-trivial problem. We suggest a controlled weight for handling the effect of weakly annotated images in a two stage object detection model. We~also present a subsequent active learning scheme for safely assigning weakly annotated images a strong annotation using the …
