results: 这种方法可以准确地检测模型预测结果中的不确定性,并且可以用来自动检测质量问题。通过使用误差度量,可以衡量自动分割的质量。Abstract
The application of deep learning models to large-scale data sets requires means for automatic quality assurance. We have previously developed a fully automatic algorithm for carotid artery wall segmentation in black-blood MRI that we aim to apply to large-scale data sets. This method identifies nested artery walls in 3D patches centered on the carotid artery. In this study, we investigate to what extent the uncertainty in the model predictions for the contour location can serve as a surrogate for error detection and, consequently, automatic quality assurance. We express the quality of automatic segmentations using the Dice similarity coefficient. The uncertainty in the model's prediction is estimated using either Monte Carlo dropout or test-time data augmentation. We found that (1) including uncertainty measurements did not degrade the quality of the segmentations, (2) uncertainty metrics provide a good proxy of the quality of our contours if the center found during the first step is enclosed in the lumen of the carotid artery and (3) they could be used to detect low-quality segmentations at the participant level. This automatic quality assurance tool might enable the application of our model in large-scale data sets.
摘要
aplicación de modelos de aprendizaje profundo a conjuntos de datos a gran escala requiere medios para la calidad automática. hemos desarrollado anteriormente un algoritmo completamente automático para la segmentación de las paredes de la arteria carótida en imágenes de resonancia magnética negra que nos gustaría aplicar a conjuntos de datos a gran escala. este método identifica las paredes de la arteria en 3D centradas en la arteria carótida. en este estudio, investigamos hasta qué punto la incertidumbre en las predicciones del modelo para el lugar de la contornación puede servir como un substituto para la detección de errores y, por lo tanto, como una calidad automática. expresamos la calidad de las segmentaciones automáticas utilizando el coeficiente de similitud de Dice. la incertidumbre en las predicciones del modelo se estima utilizando either la técnica de dropout Monte Carlo o la augmentación de datos en tiempo de prueba. encontramos que (1) incluyendo mediciones de incertidumbre no degradó la calidad de las segmentaciones, (2) los métricas de incertidumbre proporcionan un buen sustituto de la calidad de nuestros contornos si el centro encontrado durante la primera etapa está en el lumen de la arteria carótida y (3) pueden ser utilizados para detectar segmentaciones de baja calidad en el nivel del participante. esta herramienta de calidad automática podría permitir la aplicación de nuestro modelo en conjuntos de datos a gran escala.
INR-LDDMM: Fluid-based Medical Image Registration Integrating Implicit Neural Representation and Large Deformation Diffeomorphic Metric Mapping
results: 这篇论文在一个包含50名病人的CT-CBCT dataset上进行验证,以 dice 系数作为评估指标,与现有方法相比,其方法实现了顶尖性能。Abstract
We propose a flow-based registration framework of medical images based on implicit neural representation. By integrating implicit neural representation and Large Deformable Diffeomorphic Metric Mapping (LDDMM), we employ a Multilayer Perceptron (MLP) as a velocity generator while optimizing velocity and image similarity. Moreover, we adopt a coarse-to-fine approach to address the challenge of deformable-based registration methods dropping into local optimal solutions, thus aiding the management of significant deformations in medical image registration. Our algorithm has been validated on a paired CT-CBCT dataset of 50 patients,taking the dice coefficient of transferred annotations as an evaluation metric. Compared to existing methods, our approach achieves the state-of-the-art performance.
摘要
我们提出一种基于隐藏神经表示的医学图像注册框架。通过结合隐藏神经表示和大型可变拟合度量测量(LDDMM),我们使用多层感知器(MLP)作为速度生成器,同时优化速度和图像相似性。此外,我们采用一种层次递进方法,以解决医学图像注册方法中的重要形变挑战,从而帮助管理大的形变。我们的算法在一个包含50名病人的CT-CBCT对应数据集上进行了验证,并根据 transferred 注释的锥积率作为评价指标。相比现有方法,我们的方法实现了状态机器的性能。Note: "隐藏神经表示" (implicit neural representation) is a literal translation of "implicit neural network" in Chinese, but it is not a commonly used term in the field. A more common term would be "神经网络模型" (neural network model).
Quantitative Susceptibility Mapping through Model-based Deep Image Prior (MoDIP)
results: 实验结果表明,MoDIP在不同扫描参数下解决QSM束缚倒转问题时表现出色,比超vised深度学习和传统迭代方法提高了32%以上的准确率。同时,它也比传统DIP基本方法更快速,可以在4.5分钟内完成3D高分辨率图像重建。Abstract
The data-driven approach of supervised learning methods has limited applicability in solving dipole inversion in Quantitative Susceptibility Mapping (QSM) with varying scan parameters across different objects. To address this generalization issue in supervised QSM methods, we propose a novel training-free model-based unsupervised method called MoDIP (Model-based Deep Image Prior). MoDIP comprises a small, untrained network and a Data Fidelity Optimization (DFO) module. The network converges to an interim state, acting as an implicit prior for image regularization, while the optimization process enforces the physical model of QSM dipole inversion. Experimental results demonstrate MoDIP's excellent generalizability in solving QSM dipole inversion across different scan parameters. It exhibits robustness against pathological brain QSM, achieving over 32% accuracy improvement than supervised deep learning and traditional iterative methods. It is also 33% more computationally efficient and runs 4 times faster than conventional DIP-based approaches, enabling 3D high-resolution image reconstruction in under 4.5 minutes.
摘要
supervised learning方法的数据驱动方法在不同物体的扫描参数下解决量子感知地图(QSM)中的电pole反转问题具有限制。为了解决普通化问题在超级vised QSM方法中,我们提出了一种新的无需训练的模型基于方法called MoDIP(模型基于深度图像先验)。MoDIP包括一个小型、未训练的网络和数据准确优化(DFO)模块。网络会 converges到一个临时状态,作为图像REGULARIZATION的隐藏先验,而优化过程会实现QSM电pole反转的物理模型。实验结果表明MoDIP在不同扫描参数下解决QSM电pole反转问题 exhibits excellent generalizability。它对于肿瘤脑QSM具有32%的准确性提升,比超级vised深度学习和传统迭代方法更加稳定。它还比折衣DIP基本方法33%更快速,可以在4.5分钟内完成3D高分辨率图像重建。
Causal SAR ATR with Limited Data via Dual Invariance
results: 实验结果显示,提出的方法在三个benchmark datasets中表现出色。Abstract
Synthetic aperture radar automatic target recognition (SAR ATR) with limited data has recently been a hot research topic to enhance weak generalization. Despite many excellent methods being proposed, a fundamental theory is lacked to explain what problem the limited SAR data causes, leading to weak generalization of ATR. In this paper, we establish a causal ATR model demonstrating that noise $N$ that could be blocked with ample SAR data, becomes a confounder with limited data for recognition. As a result, it has a detrimental causal effect damaging the efficacy of feature $X$ extracted from SAR images, leading to weak generalization of SAR ATR with limited data. The effect of $N$ on feature can be estimated and eliminated by using backdoor adjustment to pursue the direct causality between $X$ and the predicted class $Y$. However, it is difficult for SAR images to precisely estimate and eliminated the effect of $N$ on $X$. The limited SAR data scarcely powers the majority of existing optimization losses based on empirical risk minimization (ERM), thus making it difficult to effectively eliminate $N$'s effect. To tackle with difficult estimation and elimination of $N$'s effect, we propose a dual invariance comprising the inner-class invariant proxy and the noise-invariance loss. Motivated by tackling change with invariance, the inner-class invariant proxy facilitates precise estimation of $N$'s effect on $X$ by obtaining accurate invariant features for each class with the limited data. The noise-invariance loss transitions the ERM's data quantity necessity into a need for noise environment annotations, effectively eliminating $N$'s effect on $X$ by cleverly applying the previous $N$'s estimation as the noise environment annotations. Experiments on three benchmark datasets indicate that the proposed method achieves superior performance.
摘要
射频 Synthetic aperture radar自动目标识别(SAR ATR)在有限数据情况下已经是最近的热点研究,以增强弱化。 despite many excellent methods being proposed, a fundamental theory is lacked to explain what problem the limited SAR data causes, leading to weak generalization of ATR. In this paper, we establish a causal ATR model demonstrating that noise $N$ that could be blocked with ample SAR data, becomes a confounder with limited data for recognition. As a result, it has a detrimental causal effect damaging the efficacy of feature $X$ extracted from SAR images, leading to weak generalization of SAR ATR with limited data. The effect of $N$ on feature can be estimated and eliminated by using backdoor adjustment to pursue the direct causality between $X$ and the predicted class $Y$. However, it is difficult for SAR images to precisely estimate and eliminated the effect of $N$ on $X$. The limited SAR data scarcely powers the majority of existing optimization losses based on empirical risk minimization (ERM), thus making it difficult to effectively eliminate $N$'s effect. To tackle with difficult estimation and elimination of $N$'s effect, we propose a dual invariance comprising the inner-class invariant proxy and the noise-invariance loss. Motivated by tackling change with invariance, the inner-class invariant proxy facilitates precise estimation of $N$'s effect on $X$ by obtaining accurate invariant features for each class with the limited data. The noise-invariance loss transitions the ERM's data quantity necessity into a need for noise environment annotations, effectively eliminating $N$'s effect on $X$ by cleverly applying the previous $N$'s estimation as the noise environment annotations. Experiments on three benchmark datasets indicate that the proposed method achieves superior performance.
Unveiling Causalities in SAR ATR: A Causal Interventional Approach for Limited Data
results: 我们的方法可以在有限 SAR 数据的情况下寻找真正的 causality 关系 между SAR 图像和对应的类别,并且在 MSTAR 和 OpenSARship 数据集上进行了实验和比较,证明了我们的方法的有效性。Abstract
Synthetic aperture radar automatic target recognition (SAR ATR) methods fall short with limited training data. In this letter, we propose a causal interventional ATR method (CIATR) to formulate the problem of limited SAR data which helps us uncover the ever-elusive causalities among the key factors in ATR, and thus pursue the desired causal effect without changing the imaging conditions. A structural causal model (SCM) is comprised using causal inference to help understand how imaging conditions acts as a confounder introducing spurious correlation when SAR data is limited. This spurious correlation among SAR images and the predicted classes can be fundamentally tackled with the conventional backdoor adjustments. An effective implement of backdoor adjustments is proposed by firstly using data augmentation with spatial-frequency domain hybrid transformation to estimate the potential effect of varying imaging conditions on SAR images. Then, a feature discrimination approach with hybrid similarity measurement is introduced to measure and mitigate the structural and vector angle impacts of varying imaging conditions on the extracted features from SAR images. Thus, our CIATR can pursue the true causality between SAR images and the corresponding classes even with limited SAR data. Experiments and comparisons conducted on the moving and stationary target acquisition and recognition (MSTAR) and OpenSARship datasets have shown the effectiveness of our method with limited SAR data.
摘要
Synthetic aperture radar自动目标识别(SAR ATR)方法受限于训练数据的量。在这封信中,我们提出了一个 causal interventional ATR 方法(CIATR),以解决SAR数据的限制,从而探索隐藏的 causality 中的因素。我们使用 causal inference 来理解对于 ATR 的影像条件是否导致杂散相关,并且使用常见的后门调整来解决这种杂散相关。我们首先使用数据扩展,使用空间频率域混合变换估计对 SAR 图像的可能影响。接着,我们引入了混合相似度量表示法,以衡量和抑制不同影像条件对抽出的特征之间的结构和向量角影响。因此,我们的 CIATR 可以在有限 SAR 数据的情况下,追求真正的 causality zwischen SAR 图像和相应的类别。实验和比较在 MSTAR 和 OpenSARship 数据集上显示了我们的方法的有效性。
SAMedOCT: Adapting Segment Anything Model (SAM) for Retinal OCT
results: 研究发现,适应SAM模型在大规模公共数据集上的Retouch挑战中表现出色,对多种retinal疾病、液体室和设备制造商进行了全面的评估。然而,在某些情况下,适应SAM模型仍迟于现有的标准方法。研究发现,适应SAM模型具有良好的适应性和稳定性,表明它可以作为retinal OCT图像分析中的一种有用工具。Abstract
The Segment Anything Model (SAM) has gained significant attention in the field of image segmentation due to its impressive capabilities and prompt-based interface. While SAM has already been extensively evaluated in various domains, its adaptation to retinal OCT scans remains unexplored. To bridge this research gap, we conduct a comprehensive evaluation of SAM and its adaptations on a large-scale public dataset of OCTs from RETOUCH challenge. Our evaluation covers diverse retinal diseases, fluid compartments, and device vendors, comparing SAM against state-of-the-art retinal fluid segmentation methods. Through our analysis, we showcase adapted SAM's efficacy as a powerful segmentation model in retinal OCT scans, although still lagging behind established methods in some circumstances. The findings highlight SAM's adaptability and robustness, showcasing its utility as a valuable tool in retinal OCT image analysis and paving the way for further advancements in this domain.
摘要
《Segment Anything Model(SAM)在图像分割领域已经受到了广泛关注,因为它的出色性能和提示式界面。尽管SAM已经在不同领域进行了广泛的评估,但它在Retinal OCT扫描图像中的适应性仍然未得到了评估。为了填补这个研究漏洞,我们进行了大规模的公共数据集上的SAM和其变体的全面评估。我们的评估覆盖了多种Retinal疾病、液体腔和设备生产厂商,与现有的Retinal液体分割方法进行比较。通过我们的分析,我们发现了适应SAM的效果是在Retinal OCT扫描图像中的强大分割模型,虽然在某些情况下仍落后于已知方法。这些发现抛光了SAM的适应性和稳定性,展示了它作为Retinal OCT图像分析中的有价值工具,并为此领域的进一步发展开辟了道路。》
Advancing Intra-operative Precision: Dynamic Data-Driven Non-Rigid Registration for Enhanced Brain Tumor Resection in Image-Guided Neurosurgery
paper_authors: Nikos Chrisochoides, Andriy Fedorov, Fotis Drakopoulos, Andriy Kot, Yixun Liu, Panos Foteinos, Angelos Angelopoulos, Olivier Clatz, Nicholas Ayache, Peter M. Black, Alex J. Golby, Ron Kikinis
for: used to improve the accuracy of brain tumor removal during neurosurgery
methods: uses Dynamic Data-Driven Non-Rigid Registration (NRR) to adjust pre-operative image data for intra-operative brain shift
results: enables NRR results to be delivered within clinical time constraints while leveraging Distributed Computing and Machine Learning to enhance registration accuracyAbstract
During neurosurgery, medical images of the brain are used to locate tumors and critical structures, but brain tissue shifts make pre-operative images unreliable for accurate removal of tumors. Intra-operative imaging can track these deformations but is not a substitute for pre-operative data. To address this, we use Dynamic Data-Driven Non-Rigid Registration (NRR), a complex and time-consuming image processing operation that adjusts the pre-operative image data to account for intra-operative brain shift. Our review explores a specific NRR method for registering brain MRI during image-guided neurosurgery and examines various strategies for improving the accuracy and speed of the NRR method. We demonstrate that our implementation enables NRR results to be delivered within clinical time constraints while leveraging Distributed Computing and Machine Learning to enhance registration accuracy by identifying optimal parameters for the NRR method. Additionally, we highlight challenges associated with its use in the operating room.
摘要
在神经外科过程中,医疗图像被用来确定肿瘤和重要结构,但脑组织变化使得先前的图像数据无法准确地remove肿瘤。实时图像跟踪这些变化,但不能取代先前的数据。为解决这个问题,我们使用动态数据驱动非固定均衡(NRR),一种复杂和时间消耗的图像处理操作,用于调整先前的图像数据,以 comptefor intra-operative brain shift。我们的文章探讨了一种NRR方法,用于在图像导航神经外科中 регистрироваbrain MRI,并评估了不同的策略来提高NRR方法的准确性和速度。我们示示了我们的实现可以在临床时间限制下提供NRR结果,同时利用分布式计算和机器学习来提高注射准确性。此外,我们还 highlighted the challenges associated with its use in the operating room.
JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer
results: 对于多种质量因素和图像Content,our proposed DCTransformer能够提供更高的恢复效果,比如现有状态的JPEG风损除法。Abstract
JPEG compression adopts the quantization of Discrete Cosine Transform (DCT) coefficients for effective bit-rate reduction, whilst the quantization could lead to a significant loss of important image details. Recovering compressed JPEG images in the frequency domain has attracted more and more attention recently, in addition to numerous restoration approaches developed in the pixel domain. However, the current DCT domain methods typically suffer from limited effectiveness in handling a wide range of compression quality factors, or fall short in recovering sparse quantized coefficients and the components across different colorspace. To address these challenges, we propose a DCT domain spatial-frequential Transformer, named as DCTransformer. Specifically, a dual-branch architecture is designed to capture both spatial and frequential correlations within the collocated DCT coefficients. Moreover, we incorporate the operation of quantization matrix embedding, which effectively allows our single model to handle a wide range of quality factors, and a luminance-chrominance alignment head that produces a unified feature map to align different-sized luminance and chrominance components. Our proposed DCTransformer outperforms the current state-of-the-art JPEG artifact removal techniques, as demonstrated by our extensive experiments.
摘要