Eliminating Registration Bias in Synthetic CT Generation: A Physics-Based Simulation Framework
organization= Medical University of Vienna, Department of Radiation Oncology , city= Vienna , country= Austria；organization= Christian Doppler Laboratory for Image；Knowledge Driven Precision Radiation Oncology, Medical University of Vienna , city= Vienna , country= Austria；organization= University of Applied Sciences Wiener Neustadt, Competence Center for Preclinical Imaging \& Biomedical Engineering , city= Wiener Neustadt , country= Austria
Lukas Zimmermann, Michael Rauter, Maximilian Schmid, Dietmar Georg, Barbara Knäusl
监督性合成CT生成从CBCT需要注册的训练对，但单独获取的扫描之间的完美注册仍然无法实现。这种注册偏差会传播到训练模型中，并腐蚀标准评估指标。这可能表明，优越的基准性能可能表示更好的注册伪影再现而非解剖保真度。我们提出基于物理的CBCT模拟，通过构造来提供几何对齐的训练对，并结合使用几何对齐指标与输入CBCT进行评估，而不是有偏的地面真实值。在两个独立的盆腔数据集上，训练合成数据的模型在几何对齐方面表现更优（归一化互信息：0.31 vs 0.22），尽管传统强度评分较低。强度指标显示了对变形注册数据的逆相关性，而归一化互信息在不同注册方法中一致预测了观察者的偏好（rho = 0.31，p < 0.001）。临床观察者在87%的情况下更喜欢合成训练输出，这表明几何保真度，而不是与有偏地面真实值的强度一致，符合临床需求。
英文摘要：
Supervised synthetic CT generation from CBCT requires registered training pairs, yet perfect registration between separately acquired scans remains unattainable. This registration bias propagates into trained models and corrupts standard evaluation metrics. This may suggest that superior benchmark performance indicates better reproduction of registration artifacts rather than anatomical fidelity. We propose physics-based CBCT simulation to provide geometrically aligned training pairs by construction, combined with evaluation using geometric alignment metrics against input CBCT rather than biased ground truth. On two independent pelvic datasets, models trained on synthetic data achieved superior geometric alignment (Normalized Mutual Information: 0.31 vs 0.22) despite lower conventional intensity scores. Intensity metrics showed inverted correlations with clinical assessment for deformably registered data, while Normalized Mutual Information consistently predicted observer preference across registration methodologies (rho = 0.31, p < 0.001). Clinical observers preferred synthetic-trained outputs in 87% of cases, demonstrating that geometric fidelity, not intensity agreement with biased ground truth, aligns with clinical requirements.
University of Copenhagen（哥本哈根大学）；Biomediq A/S；Lundbeck（灵北）
Template estimation plays a crucial role in computational anatomy since it provides reference frames for performing statistical analysis of the underlying anatomical population variability. While building models for template estimation, variability in sites and image acquisition protocols need to be accounted for. To account for such variability, we propose a generative template estimation model that makes simultaneous inference of both bias fields in individual images, deformations for image registration, and variance hyperparameters. In contrast, existing maximum a posterori based methods ne…
Overlap Bias Matching is Necessary for Point Cloud Registration
School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件学院）；School of Computer and Information Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to solve this problem but their training can be affected by biases that decrease their efficiency. In this paper, we introduce a new training procedure that confronts the algorithm to its own mistakes while explicitly attempting to minimize the number of switches, which results in better training. We propose an iterative scheme of building a rich training set and using it to learn a scoring function that is an explicit pro…
University of Science and Technology of China（中国科学技术大学）；National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）
Recent methods focus on learning a unified semantic-aligned visual representation to transfer knowledge between two domains, while ignoring the effect of semantic-free visual representation in alleviating the biased recognition problem. In this paper, we propose a novel Domain-aware Visual Bias Eliminating (DVBE) network that constructs two complementary visual representations, i.e., semantic-free and semantic-aligned, to treat seen and unseen domains separately. Specifically, we explore cross-attentive second-order visual statistics to compact the semantic-free representation, and design an a…
National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；USTC（中国科学技术大学）
Transductive Zero-shot learning (ZSL) targets to recognize the unseen categories by aligning the visual and semantic information in a joint embedding space. There exist four kinds of domain biases in Transductive ZSL, i.e., visual bias and semantic bias between two domains and two visual-semantic biases in respective seen and unseen domains, but existing work only focuses on the part of them, which leads to severe semantic ambiguity during the knowledge transfer. To solve the above problem, we propose a novel Attribute-Induced Bias Eliminating (AIBE) module for Transductive ZSL. Specifically, …
Distribution-to-distribution (D2D) point cloud registration techniques such as the Normal Distributions Transform (NDT) can align point clouds sampled from unstructured scenes and provide accurate bounds of their own solution error covariance -- an important feature for safety-of-life navigation tasks. D2D methods rely on the assumption of a static scene and are therefore susceptible to bias from range-shadowing, self-occlusion, moving objects, and distortion artifacts as the recording device moves between frames. Deep Learning-based approaches can achieve higher accuracy in dynamic scenes by …
This paper introduces a class of mixed-effects models for joint modeling of spatially correlated intensity variation and warping variation in 2D images. Spatially correlated intensity variation and warp variation are modeled as random effects, resulting in a nonlinear mixed-effects model that enables simultaneous estimation of template and model parameters by optimization of the likelihood function. We propose an algorithm for fitting the model which alternates estimation of variance parameters and image registration. This approach avoids the potential estimation bias in the template estimate …
University of California, San Francisco（加州大学旧金山分校）；Weill Institute for Neurosciences（威尔神经科学研究所）；Iran Science and Technology University（伊朗科技大学）；Sharif University of Technology（谢里夫理工大学）
Spatially-varying intensity noise is a common source of distortion in medical images. Bias field noise is one example of such a distortion that is often present in the magnetic resonance (MR) images or other modalities such as retina images. In this paper, we first show that the bias field noise can be considerably reduced using Empirical Mode Decomposition (EMD) technique. EMD is a multi-resolution tool that decomposes a signal into several principle patterns and residual components. We show that the spatially-varying noise is highly expressed in the residual component of the EMD and could be…
Vehicle re-identification (reID) often requires recognize a target vehicle in large datasets captured from multi-cameras. It plays an important role in the automatic analysis of the increasing urban surveillance videos, which has become a hot topic in recent years. However, the appearance of vehicle images is easily affected by the environment that various illuminations, different backgrounds and viewpoints, which leads to the large bias between different cameras. To address this problem, this paper proposes a cross-camera adaptation framework (CCA), which smooths the bias by exploiting the co…
Vision-Language Pre-training (VLP) models have achieved state-of-the-art performance in numerous cross-modal tasks. Since they are optimized to capture the statistical properties of intra- and inter-modality, there remains risk to learn social biases presented in the data as well. In this work, we (1) introduce a counterfactual-based bias measurement \emph{CounterBias} to quantify the social bias in VLP models by comparing the [MASK]ed prediction probabilities of factual and counterfactual samples; (2) construct a novel VL-Bias dataset including 24K image-text pairs for measuring gender bias i…
Medical Informatics Laboratory, Queen’s University（女王大学医学信息学实验室）；Radiology Department, Brigham and Women’s Hospital, Harvard Medical School（哈佛医学院布莱根妇女医院放射科）；Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究生院）；Department of Electrical and Computer Engineering, University of British Columbia（英属哥伦比亚大学电气与计算机工程系）
Deep metrics have been shown effective as similarity measures in multi-modal image registration; however, the metrics are currently constructed from aligned image pairs in the training data. In this paper, we propose a strategy for learning such metrics from roughly aligned training data. Symmetrizing the data corrects bias in the metric that results from misalignment in the data (at the expense of increased variance), while random perturbations to the data, i.e. dithering, ensures that the metric has a single mode, and is amenable to registration by optimization. Evaluation is performed on th…
Erasmus MC（伊拉斯姆斯医学中心）；Delft University of Technology（代尔夫特理工大学）
Analysis of longitudinal changes in imaging studies often involves both segmentation of structures of interest and registration of multiple timeframes. The accuracy of such analysis could benefit from a tailored framework that jointly optimizes both tasks to fully exploit the information available in the longitudinal data. Most learning-based registration algorithms, including joint optimization approaches, currently suffer from bias due to selection of a fixed reference frame and only support pairwise transformations. We here propose an analytical framework based on an unbiased learning strat…
Institute of Medical Informatics, Universität zu Lübeck（吕贝克大学医学信息学研究所）
Multimodal image registration is a very challenging problem for deep learning approaches. Most current work focuses on either supervised learning that requires labelled training scans and may yield models that bias towards annotated structures or unsupervised approaches that are based on hand-crafted similarity metrics and may therefore not outperform their classical non-trained counterparts. We believe that unsupervised domain adaptation can be beneficial in overcoming the current limitations for multimodal registration, where good metrics are hard to define. Domain adaptation has so far been…
WarpPINN: Cine-MR image registration with physics-informed neural networks
University of Bath（巴斯大学）；Pontificia Universidad Católica de Valparaíso（瓦尔帕莱索天主大学）；Millennium Institute for Intelligent Healthcare Engineering（千年智能医疗工程研究所）；Pontificia Universidad Católica de Chile（智利天主大学）
University of Copenhagen（哥本哈根大学）；Technical University of Denmark（丹麦技术大学）
Geometric alignment appears in a variety of applications, ranging from domain adaptation, optimal transport, and normalizing flows in machine learning; optical flow and learned augmentation in computer vision and deformable registration within biomedical imaging. A recurring challenge is the alignment of domains whose topology is not the same; a problem that is routinely ignored, potentially introducing bias in downstream analysis. As a first step towards solving such alignment problems, we propose an unsupervised algorithm for the detection of changes in image topology. The model is based on …
