A large amount of manual segmentation is typically required to train a robust segmentation network so that it can segment objects of interest in a new imaging modality. The manual efforts can be alleviated if the manual segmentation in one imaging modality (e.g., CT) can be utilized to train a segmentation network in another imaging modality (e.g., CBCT/MRI/PET). In this work, we developed an anatomy-constrained contrastive synthetic segmentation network (AccSeg-Net) to train a segmentation network for a target imaging modality without using its ground truth. Specifically, we proposed to use anatomy-constraint and patch contrastive learning to ensure the anatomy fidelity during the unsupervised adaptation, such that the segmentation network can be trained on the adapted image with correct anatomical structure/content. The training data for our AccSeg-Net consists of 1) imaging data paired with segmentation ground-truth in source modality, and 2) unpaired source and target modality imaging data. We demonstrated successful applications on CBCT, MRI, and PET imaging data, and showed superior segmentation performances as compared to previous methods.
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…
University of Pittsburgh（匹兹堡大学）；Boston University（波士顿大学）
Large-scale volumetric medical images with annotation are rare, costly, and time prohibitive to acquire. Self-supervised learning (SSL) offers a promising pre-training and feature extraction solution for many downstream tasks, as it only uses unlabeled data. Recently, SSL methods based on instance discrimination have gained popularity in the medical imaging domain. However, SSL pre-trained encoders may use many clues in the image to discriminate an instance that are not necessarily disease-related. Moreover, pathological patterns are often subtle and heterogeneous, requiring the ability of the…
Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；The First Affiliated Hospital of College of Medicine, Zhejiang University（浙江大学医学院附属第一医院）；Hupan Lab（虎盘实验室）
Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising
Department of Electrical and Computer Engineering, The University of Hong Kong（香港大学电子与计算机工程系）；Department of Biomedical Engineering, Duke University（达特茅斯大学生物医学工程系）
Anatomy-Informed Neural Networks: Encoding Anatomic Priors in Loss and Architecture, with an SE(3) Formulation of Guidewire-Induced Aortoiliac Deformation
Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the hypothesis that leveraging multiple modalities can lead to better recognition. Since manual annotation of input data is expensive and time-consuming, the emphasis is made on self-supervised methods which can learn useful feature representations without any ground truth labels. We extend a number of recent contrastive self-supervised approaches for the task of Huma…
ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University（复旦大学类脑智能科学与技术研究院）；School of Cyber Science and Engineering, Sichuan University（四川大学网络空间安全学院）
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
We propose Few-Example Clustering (FEC), a novel algorithm that performs contrastive learning to cluster few examples. Our method is composed of the following three steps: (1) generation of candidate cluster assignments, (2) contrastive learning for each cluster assignment, and (3) selection of the best candidate. Based on the hypothesis that the contrastive learner with the ground-truth cluster assignment is trained faster than the others, we choose the candidate with the smallest training loss in the early stage of learning in step (3). Extensive experiments on the \textit{mini}-ImageNet and…
Animal pose estimation has recently come into the limelight due to its application in biology, zoology, and aquaculture. Deep learning methods have effectively been applied to human pose estimation. However, the major bottleneck to the application of these methods to animal pose estimation is the unavailability of sufficient quantities of labeled data. Though there are ample quantities of unlabelled data publicly available, it is economically impractical to label large quantities of data for each animal. In addition, due to the wide variety of body shapes in the animal kingdom, the transfer of…
JD AI Research（京东人工智能研究院）；SUN YAT-SEN UNIVERSITY（中山大学）；University of Science and Technology of China（中国科学技术大学）
Unsupervised learning is just at a tipping point where it could really take off. Among these approaches, contrastive learning has seen tremendous progress and led to state-of-the-art performance. In this paper, we construct a novel probabilistic graphical model that effectively incorporates the low rank promoting prior into the framework of contrastive learning, referred to as LORAC. In contrast to the existing conventional self-supervised approaches that only considers independent learning, our hypothesis explicitly requires that all the samples belonging to the same instance class lie on the…
Yale University（耶鲁大学）；Yale School of Medicine（耶鲁大学医学院）；University of Science and Technology of China（中国科学技术大学）；Suzhou Institute for Advanced Research, University of Science and Technology of China（中国科学技术大学苏州高等研究院）；Chinese Academy of Sciences（中国科学院）
Multimodal image registration has many applications in diagnostic medical imaging and image-guided interventions, such as Transcatheter Arterial Chemoembolization (TACE) of liver cancer guided by intraprocedural CBCT and pre-operative MR. The ability to register peri-procedurally acquired diagnostic images into the intraprocedural environment can potentially improve the intra-procedural tumor targeting, which will significantly improve therapeutic outcomes. However, the intra-procedural CBCT often suffers from suboptimal image quality due to lack of signal calibration for Hounsfield unit, limi…
École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds. Despite promising progress, existing representations learned with neural networks still struggle to generalize in closed-loop predictions (e.g., output colliding trajectories). This issue largely arises from the non-i.i.d. nature of sequential prediction in conjunction with ill-distributed training data. Intuitively, if the training data only comes from human behaviors in safe spaces, i.e., from "positive" examples, it is dif…
Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Method
Chair for AI for Image-Guided Diagnosis and Therapy, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany（人工智能辅助影像引导诊断与治疗研究所，慕尼黑技术大学（TUM）及慕尼黑技术大学医院，慕尼黑，德国）；Munich Center for Machine Learning (MCML), Munich, Germany（慕尼黑机器学习中心，慕尼黑，德国）；Chair for AI in Healthcare and Medicine, Technical University of Munich (TUM) and TUM University Hospital, Munich, Germany（人工智能在医疗与健康领域研究所，慕尼黑技术大学（TUM）及慕尼黑技术大学医院，慕尼黑，德国）；Department of Radiation Oncology, TUM University Hospital, Munich, Germany（放射肿瘤科，慕尼黑技术大学医院，慕尼黑，德国）；Chair for Computer Vision and Artificial Intelligence, Technical University of Munich (TUM), Munich, Germany（计算机视觉与人工智能研究所，慕尼黑技术大学（TUM），慕尼黑，德国）；Stanford Center for Artificial Intelligence in Medicine and Imaging, Stanford University, Stanford, CA, USA（斯坦福大学人工智能在医学与影像中心，斯坦福大学，斯坦福，CA，美国）；Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Munich, Germany（德国转化癌症研究联盟（DKTK），慕尼黑合作伙伴站点，慕尼黑，德国）；Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Helmholtz Center Munich, Munich, Germany（放射医学研究所（IRM），辐射科学部门（DRS），海德堡慕尼黑研究中心，慕尼黑，德国）
Recent advancements in explainable machine learning provide effective and faithful solutions for interpreting model behaviors. However, many explanation methods encounter efficiency issues, which largely limit their deployments in practical scenarios. Real-time explainer (RTX) frameworks have thus been proposed to accelerate the model explanation process by learning a one-feed-forward explainer. Existing RTX frameworks typically build the explainer under the supervised learning paradigm, which requires large amounts of explanation labels as the ground truth. Considering that accurate explanati…
Uncovering Capabilities of Model Pruning in Graph Contrastive Learning
State Key Laboratory of Complex & Critical Software Environment, Beihang University（北京航空航天大学复杂与关键软件环境国家重点实验室）；School of Statistics and Mathematics, Central University of Finance and Economics（中央财经大学统计与数学学院）
Beijing University of Posts and Telecommunications（北京邮电大学）；Hong Kong Baptist University（香港浸会大学）；Jilin University（吉林大学）
Massive false rumors emerging along with breaking news or trending topics severely hinder the truth. Existing rumor detection approaches achieve promising performance on the yesterday's news, since there is enough corpus collected from the same domain for model training. However, they are poor at detecting rumors about unforeseen events especially those propagated in different languages due to the lack of training data and prior knowledge (i.e., low-resource regimes). In this paper, we propose an adversarial contrastive learning framework to detect rumors by adapting the features learned from …
In search of truth: Evaluating concordance of AI-based anatomy segmentation models
RWTH Aachen University（亚琛工业大学）；Brigham and Women’s Hospital（布里格姆妇女医院）；PixelMed Publishing；University Hospital of Basel（巴塞尔大学医院）；Ludwig Maximilian University Munich（慕尼黑路德维希-马克西米利安大学）；NVIDIA（英伟达）；German Cancer Research Center (DKFZ)（德国癌症研究中心）；University of Zurich（苏黎世大学）；Isomics Inc（Isomics公司）
Massive rumors usually appear along with breaking news or trending topics, seriously hindering the truth. Existing rumor detection methods are mostly focused on the same domain, and thus have poor performance in cross-domain scenarios due to domain shift. In this work, we propose an end-to-end instance-wise and prototype-wise contrastive learning model with a cross-attention mechanism for cross-domain rumor detection. The model not only performs cross-domain feature alignment but also enforces target samples to align with the corresponding prototypes of a given source domain. Since target labe…
Training deep learning models on cardiac magnetic resonance imaging (CMR) can be a challenge due to the small amount of expert generated labels and inherent complexity of data source. Self-supervised contrastive learning (SSCL) has recently been shown to boost performance in several medical imaging tasks. However, it is unclear how much the pre-trained representation reflects the primary organ of interest compared to spurious surrounding tissue. In this work, we evaluate the optimal method of incorporating prior knowledge of anatomy into a SSCL training paradigm. Specifically, we evaluate usin…
Recovering binary programs' call graphs is crucial for inter-procedural analysis tasks and applications based on them.transfer One of the core challenges is recognizing targets of indirect calls (i.e., indirect callees). Existing solutions all have high false positives and negatives, making call graphs inaccurate. In this paper, we propose a new solution Callee combining transfer learning and contrastive learning. The key insight is that, deep neural networks (DNNs) can automatically identify patterns concerning indirect calls, which can be more efficient than designing approximation algorithm…
AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Images
School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；Shanghai Eye Diseases Prevention and Treatment Center, Shanghai Eye Hospital（上海市眼病防治中心、上海眼科医院）；School of Communication and Electronic Engineering, East China Normal University（华东师范大学通信与电子工程学院）
Anatomy-Aware Text-Visual Fusion with Dual-Perspective Prompts for Fine-Grained Lumbar Spine Segmentation
College of Computer and Data Science（计算机与数据科学学院）；Shandong Technology and Business University（山东科技商务大学）；Engineering Research Center of Big Data Intelligence (Fuzhou University)（大数据智能工程研究中心（福州大学））；The Chinese University of Hong Kong（香港中文大学）；Case Western Reserve University（凯斯西储大学）
University of Electronic Science and Technology of China（电子科技大学）；Shanghai AI Lab（上海人工智能实验室）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）；ShanghaiTech University（上海科技大学）；West China Hospital, Sichuan University（四川大学华西医院）
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for medical image segmentation, yet need plenty of manual annotations for training. Semi-Supervised Learning (SSL) methods are promising to reduce the requirement of annotations, but their performance is still limited when the dataset size and the number of annotated images are small. Leveraging existing annotated datasets with similar anatomical structures to assist training has a potential for improving the model's performance. However, it is further challenged by the cross-anatomy domain shift due to the differe…
Johns Hopkins University（约翰斯·霍普金斯大学）；Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）；Auris Health, Inc.（奥里斯健康公司）；Johns Hopkins Medicine（约翰斯·霍普金斯医学院）；Nara Institute of Science and Technology（奈良科学技术研究所）；University of Texas（德克萨斯大学）；Texas Orthopedics（德克萨斯骨科医院）
Fluoroscopy is the standard imaging modality used to guide hip surgery and is therefore a natural sensor for computer-assisted navigation. In order to efficiently solve the complex registration problems presented during navigation, human-assisted annotations of the intraoperative image are typically required. This manual initialization interferes with the surgical workflow and diminishes any advantages gained from navigation. We propose a method for fully automatic registration using annotations produced by a neural network. Neural networks are trained to simultaneously segment anatomy and ide…
University of Waterloo（滑铁卢大学）；Suez Canal University（苏伊士运河大学）
Quantifying the accuracy of segmentation and manual delineation of organs, tissue types and tumors in medical images is a necessary measurement that suffers from multiple problems. One major shortcoming of all accuracy measures is that they neglect the anatomical significance or relevance of different zones within a given segment. Hence, existing accuracy metrics measure the overlap of a given segment with a ground-truth without any anatomical discrimination inside the segment. For instance, if we understand the rectal wall or urethral sphincter as anatomical zones, then current accuracy measu…
Biomedical Image Analysis Group, Imperial College London, UK（帝国理工学院伦敦生物医学图像分析组）
Real-world settings often do not allow acquisition of high-resolution volumetric images for accurate morphological assessment and diagnostic. In clinical practice it is frequently common to acquire only sparse data (e.g. individual slices) for initial diagnostic decision making. Thereby, physicians rely on their prior knowledge (or mental maps) of the human anatomy to extrapolate the underlying 3D information. Accurate mental maps require years of anatomy training, which in the first instance relies on normative learning, i.e. excluding pathology. In this paper, we leverage Bayesian Deep Learn…
Chalmers University of Technology（查尔姆斯理工大学）；James Cook University（詹姆斯库克大学）；La Trobe University（乐卓博大学）；Beihang University（北京航空航天大学）；Vitalent Consulting（Vitalent咨询公司）；Silo AI
The automotive mmWave radar plays a key role in advanced driver assistance systems (ADAS) and autonomous driving. Deep learning-based instance segmentation enables real-time object identification from the radar detection points. In the conventional training process, accurate annotation is the key. However, high-quality annotations of radar detection points are challenging to achieve due to their ambiguity and sparsity. To address this issue, we propose a contrastive learning approach for implementing radar detection points-based instance segmentation. We define the positive and negative sample…
University of California, Irvine（加州大学欧文分校）；Lenovo Research（联想研究院）；Deepvoxel Inc（深度体素公司）；Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属上海第一人民医院）；Tencent Medical AI Lab（腾讯医疗人工智能实验室）
Methods: Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT images as input and generating masks of all OARs of interest in one shot. AnatomyNet is built upon the popular 3D U-net architecture, but extends it in three important ways: 1) a new encoding scheme to allow auto-segmentation on whole-volume CT images instead of local patches or subsets of slices, 2) incorporating 3D squeeze-and-excitation residual blocks in encoding layers for better feature representation, and 3) a new loss function combining…
In training machine learning models for land cover semantic segmentation there is a stark contrast between the availability of satellite imagery to be used as inputs and ground truth data to enable supervised learning. While thousands of new satellite images become freely available on a daily basis, getting ground truth data is still very challenging, time consuming and costly. In this paper we present Embedding Earth a self-supervised contrastive pre-training method for leveraging the large availability of satellite imagery to improve performance on downstream dense land cover classification …
Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding
DAMO Academy, Alibaba Group（达摩院（阿里巴巴集团））；The First Affiliated Hospital of College of Medicine, Zhejiang University（浙江大学医学院附属第一医院）；Zhejiang University（浙江大学）；Westlake University（西湖大学）
We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain. A key to domain adaptive semantic segmentation is to learn domain-invariant and discriminative features without target ground-truth labels. To this end, we propose a bi-directional pixel-prototype contrastive learning framework that minimizes intra-class variations of features for the same object class, while maximizing inter-class variations for different ones, regardless of domains. Specifically, our f…
IMT Atlantique（IMT大西洋高等矿业电信学校）；LaTIM UMR 1101, Inserm（LaTIM（法国国家健康与医学研究院1101联合研究单位））；Centre Hospitalier Régional et Universitaire (CHRU) Brest（布雷斯特大学中心医院）；SCMIA, Symbiosis International University（共生国际大学SCMIA）
Automatic segmentation of magnetic resonance (MR) images is crucial for morphological evaluation of the pediatric musculoskeletal system in clinical practice. However, the accuracy and generalization performance of individual segmentation models are limited due to the restricted amount of annotated pediatric data. Hence, we propose to train a segmentation model on multiple datasets, arising from different parts of the anatomy, in a multi-task and multi-domain learning framework. This approach allows to overcome the inherent scarcity of pediatric data while benefiting from a more robust shared …
Quantitative Metrics for Benchmarking Medical Image Harmonization
Children’s National Hospital（儿童国家医院）；Children’s Hospital of Philadelphia（费城儿童医院）；School of Medicine and Health Sciences, George Washington University（乔治华盛顿大学医学与健康科学学院）
PAII Inc.（PAII 公司）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Rochester（罗切斯特大学）；Chang Gung Memorial Hospital（长庚纪念医院）；Ping An Technology（平安科技）
Visual cues of enforcing bilaterally symmetric anatomies as normal findings are widely used in clinical practice to disambiguate subtle abnormalities from medical images. So far, inadequate research attention has been received on effectively emulating this practice in CAD methods. In this work, we exploit semantic anatomical symmetry or asymmetry analysis in a complex CAD scenario, i.e., anterior pelvic fracture detection in trauma PXRs, where semantically pathological (refer to as fracture) and non-pathological (e.g., pose) asymmetries both occur. Visually subtle yet pathologically critical f…
Training supervised image synthesis models requires a critic to compare two images: the ground truth to the result. Yet, this basic functionality remains an open problem. A popular line of approaches uses the L1 (mean absolute error) loss, either in the pixel or the feature space of pretrained deep networks. However, we observe that these losses tend to produce overly blurry and grey images, and other techniques such as GANs need to be employed to fight these artifacts. In this work, we introduce an information theory based approach to measuring similarity between two images. We argue that a g…
IMT Atlantique（大西洋国立高等矿业电信学校）；LaTIM UMR 1101, Inserm（法国国家健康与医学研究院LaTIM UMR 1101实验室）；Centre Hospitalier Régional et Universitaire (CHRU) de Brest（布雷斯特大学区域中心医院）；Fondation ILDYS（ILDYS基金会）；Symbiosis Center for Medical Image Analysis, Symbiosis International University（共生国际大学共生医学图像分析中心）
Clinical diagnosis of the pediatric musculoskeletal system relies on the analysis of medical imaging examinations. In the medical image processing pipeline, semantic segmentation using deep learning algorithms enables an automatic generation of patient-specific three-dimensional anatomical models which are crucial for morphological evaluation. However, the scarcity of pediatric imaging resources may result in reduced accuracy and generalization performance of individual deep segmentation models. In this study, we propose to design a novel multi-task, multi-domain learning framework in which a …
OPPO US Research Center（OPPO美国研究中心）；Innopeak Technology（Innopeak科技公司）
Synthetic datasets are often used to pretrain end-to-end optical flow networks, due to the lack of a large amount of labeled, real-scene data. But major drops in accuracy occur when moving from synthetic to real scenes. How do we better transfer the knowledge learned from synthetic to real domains? To this end, we propose CLIP-FLow, a semi-supervised iterative pseudo-labeling framework to transfer the pretraining knowledge to the target real domain. We leverage large-scale, unlabeled real data to facilitate transfer learning with the supervision of iteratively updated pseudo-ground truth label…
