Identification of tumor margins is essential for surgical decision-making for glioblastoma patients and provides reliable assistance for neurosurgeons. Despite improvements in deep learning architectures for tumor segmentation over the years, creating a fully autonomous system suitable for clinical floors remains a formidable challenge because the model predictions have not yet reached the desired level of accuracy and generalizability for clinical applications. Generative modeling techniques have seen significant improvements in recent times. Specifically, Generative Adversarial Networks (GANs) and Denoising-diffusion-based models (DDPMs) have been used to generate higher-quality images with fewer artifacts and finer attributes. In this work, we introduce a framework called Re-Diffinet for modeling the discrepancy between the outputs of a segmentation model like U-Net and the ground truth, using DDPMs. By explicitly modeling the discrepancy, the results show an average improvement of 0.55\% in the Dice score and 16.28\% in HD95 from cross-validation over 5-folds, compared to the state-of-the-art U-Net segmentation model.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
Neural Networks
·
Networking
·
全
·
3D
·
A vascular synthetic model for improved aneurysm segmentation and detection via Deep Neural Networks
We hereby present a full synthetic model, able to mimic the various constituents of the cerebral vascular tree: the cerebral arteries, the bifurcations and the intracranial aneurysms. By building this model, our goal was to provide a substantial dataset of brain arteries which could be used by a 3D Convolutional Neural Network (CNN) to either segment or detect/recognize various vascular diseases (such as artery dissection/thrombosis) or even some portions of the cerebral vasculature, such as the bifurcations or aneurysms. In this study, we will particularly focus on Intra-Cranial Aneurysm (ICA) detection and segmentation. The cerebral aneurysms most often occur on a particular structure of the vascular tree named the Circle of Willis. Various studies have been conducted to detect and monitor the ICAs and those based on Deep Learning (DL) achieve the best performances. Specifically, in this work, we propose a full synthetic 3D model able to mimic the brain vasculature as acquired by Magnetic Resonance Angiography (MRA), and more particularly the Time Of Flight (TOF) principle. Among the various MRI modalities, the MRA-TOF allows to have a relatively good rendering of the blood vessels and is non-invasive (no contrast liquid injection). Our model has been designed to simultaneously mimic the arteries geometry, the ICA shape and the background noise. The geometry of the vascular tree is modeled thanks to an interpolation with 3D Spline functions, and the statistical properties of the background MRI noise is collected from MRA acquisitions and reproduced within the model. In this work, we thoroughly describe the synthetic vasculature model, we build up a neural network designed for ICA segmentation and detection, and finally, we carry out an in-depth evaluation of the performance gap gained thanks to the synthetic model data augmentation.
Energy-efficient spikformer has been proposed by integrating the biologically plausible spiking neural network (SNN) and artificial Transformer, whereby the Spiking Self-Attention (SSA) is used to achieve both higher accuracy and lower computational cost. However, it seems that self-attention is not always necessary, especially in sparse spike-form calculation manners. In this paper, we innovatively replace vanilla SSA (using dynamic bases calculating from Query and Key) with spike-form Fourier Transform, Wavelet Transform, and their combinations (using fixed triangular or wavelets bases), based on a key hypothesis that both of them use a set of basis functions for information transformation. Hence, the Fourier-or-Wavelet-based spikformer (FWformer) is proposed and verified in visual classification tasks, including both static image and event-based video datasets. The FWformer can achieve comparable or even higher accuracies ($0.4\%$-$1.5\%$), higher running speed ($9\%$-$51\%$ for training and $19\%$-$70\%$ for inference), reduced theoretical energy consumption ($20\%$-$25\%$), and reduced GPU memory usage ($4\%$-$26\%$), compared to the standard spikformer. Our result indicates the continuous refinement of new Transformers, that are inspired either by biological discovery (spike-form), or information theory (Fourier or Wavelet Transform), is promising.
Selective inference methods are developed for group lasso estimators for use with a wide class of distributions and loss functions. The method includes the use of exponential family distributions, as well as quasi-likelihood modeling for overdispersed count data, for example, and allows for categorical or grouped covariates as well as continuous covariates. A randomized group-regularized optimization problem is studied. The added randomization allows us to construct a post-selection likelihood which we show to be adequate for selective inference when conditioning on the event of the selection of the grouped covariates. This likelihood also provides a selective point estimator, accounting for the selection by the group lasso. Confidence regions for the regression parameters in the selected model take the form of Wald-type regions and are shown to have bounded volume. The selective inference method for grouped lasso is illustrated on data from the national health and nutrition examination survey while simulations showcase its behaviour and favorable comparison with other methods.
We describe fast algorithms for approximating the connection coefficients between a family of orthogonal polynomials and another family with a polynomially or rationally modified measure. The connection coefficients are computed via infinite-dimensional banded matrix factorizations and may be used to compute the modified Jacobi matrices all in linear complexity with respect to the truncation degree. A family of orthogonal polynomials with modified classical weights is constructed that support banded differentiation matrices, enabling sparse spectral methods with modified classical orthogonal polynomials.
The advent of ChatGPT and similar large language models (LLMs) has revolutionized the human-AI interaction and information-seeking process. Leveraging LLMs as an alternative to search engines, users can now access summarized information tailored to their queries, significantly reducing the cognitive load associated with navigating vast information resources. This shift underscores the potential of LLMs in redefining information access paradigms. Drawing on the foundation of task-focused information retrieval and LLMs' task planning ability, this research extends the scope of LLM capabilities beyond routine task automation to support users in navigating long-term and significant life tasks. It introduces the GOLF framework (Goal-Oriented Long-term liFe tasks), which focuses on enhancing LLMs' ability to assist in significant life decisions through goal orientation and long-term planning. The methodology encompasses a comprehensive simulation study to test the framework's efficacy, followed by model and human evaluations to develop a dataset benchmark for long-term life tasks, and experiments across different models and settings. By shifting the focus from short-term tasks to the broader spectrum of long-term life goals, this research underscores the transformative potential of LLMs in enhancing human decision-making processes and task management, marking a significant step forward in the evolution of human-AI collaboration.
It is essential to efficiently solve multiscale flows covering the continuum regime to the rarefied regime. The explicit form of Grad's 13 moments distribution function-based moment gas kinetic solver (G13-MGKS) has been proposed in our previous work [Comput. Math. Appl., 137 (2023), pp. 112-125], which demonstrates the potential for efficiently simulating continuum flows accurately and presenting reasonable predictions for rarefied flows at moderate Knudsen numbers on structured meshes. To further extend the solver's applicability to unstructured meshes, we propose the simplified version of the Grad's 13 moments distribution function-based moment gas kinetic solver (SG13-MGKS) with an explicit form of the numerical flux in the present paper. The Shakhov collision model has been adopted and validated within the framework of SG13-MGKS to ensure the correct Prandtl number in the simulation. Additionally, a simplified treatment for the numerical fluxes has been adopted to minimize the need for complex calculations of the gradient of integral coefficients. The performance of SG13-MGKS has been evaluated in numerical cases of Couette flow with temperature differences, flow passing through a NACA0012 airfoil, and pressure-driven flow in a variable-diameter circular pipe. Our results demonstrate that SG13-MGKS can achieve reasonably accurate computational results at Knudsen numbers below 0.2. Benefiting from the avoidance of discretization in velocity space, G13-MGKS is able to be two orders of magnitude faster compared to the conventional discrete velocity method. Furthermore, the simplified form of numerical fluxes and the fewer gradients of integration coefficients enable the performance of SG13-MGKS on unstructured grids with a saving of about 4 times the computation time and 3 times the memory cost compared to the previous version of G13-MGKS.
The numerical approximation of dynamic poroelasticity, modeling flow in deformable porous media, by a family of continuous space-time finite element methods is investigated. Equal order approximation in space without any further stabilization is used for the displacement and pore pressure variable. Optimal order $L^\infty(L^2)$ error estimates are proved and numerically confirmed.
We prove the uniform convergence of the geometric multigrid V-cycle for hybrid high-order (HHO) and other discontinuous skeletal methods. Our results generalize previously established results for HDG methods, and our multigrid method uses standard smoothers and local solvers that are bounded, convergent, and consistent. We use a weak version of elliptic regularity in our proofs. Numerical experiments confirm our theoretical results.
Reed--Solomon codes are a classic family of error-correcting codes consisting of evaluations of low-degree polynomials over a finite field on some sequence of distinct field elements. They are widely known for their optimal unique-decoding capabilities, but their list-decoding capabilities are not fully understood. Given the prevalence of Reed-Solomon codes, a fundamental question in coding theory is determining if Reed--Solomon codes can optimally achieve list-decoding capacity. A recent breakthrough by Brakensiek, Gopi, and Makam, established that Reed--Solomon codes are combinatorially list-decodable all the way to capacity. However, their results hold for randomly-punctured Reed--Solomon codes over an exponentially large field size $2^{O(n)}$, where $n$ is the block length of the code. A natural question is whether Reed--Solomon codes can still achieve capacity over smaller fields. Recently, Guo and Zhang showed that Reed--Solomon codes are list-decodable to capacity with field size $O(n^2)$. We show that Reed--Solomon codes are list-decodable to capacity with linear field size $O(n)$, which is optimal up to the constant factor. We also give evidence that the ratio between the alphabet size $q$ and code length $n$ cannot be bounded by an absolute constant. Our techniques also show that random linear codes are list-decodable up to (the alphabet-independent) capacity with optimal list-size $O(1/\varepsilon)$ and near-optimal alphabet size $2^{O(1/\varepsilon^2)}$, where $\varepsilon$ is the gap to capacity. As far as we are aware, list-decoding up to capacity with optimal list-size $O(1/\varepsilon)$ was previously not known to be achievable with any linear code over a constant alphabet size (even non-constructively). Our proofs are based on the ideas of Guo and Zhang, and we additionally exploit symmetries of reduced intersection matrices.
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern 1) a taxonomy and extensive overview of the state-of-the-art, 2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner, 3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time, and storage.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191