results: 对比预训练的SAM和nnUNetv2，改进后的SAM在脑肿划分精度方面显示了显著提高，而nnUNetv2在总划分精度方面赢得了比较高的分数。然而，改进后的SAM在挑战性较高的案例中表现更为稳定，尤其是在 Hausdorff 距离95%的情况下。Abstract
Brain tumor segmentation presents a formidable challenge in the field of Medical Image Segmentation. While deep-learning models have been useful, human expert segmentation remains the most accurate method. The recently released Segment Anything Model (SAM) has opened up the opportunity to apply foundation models to this difficult task. However, SAM was primarily trained on diverse natural images. This makes applying SAM to biomedical segmentation, such as brain tumors with less defined boundaries, challenging. In this paper, we enhanced SAM's mask decoder using transfer learning with the Decathlon brain tumor dataset. We developed three methods to encapsulate the four-dimensional data into three dimensions for SAM. An on-the-fly data augmentation approach has been used with a combination of rotations and elastic deformations to increase the size of the training dataset. Two key metrics: the Dice Similarity Coefficient (DSC) and the Hausdorff Distance 95th Percentile (HD95), have been applied to assess the performance of our segmentation models. These metrics provided valuable insights into the quality of the segmentation results. In our evaluation, we compared this improved model to two benchmarks: the pretrained SAM and the widely used model, nnUNetv2. We find that the improved SAM shows considerable improvement over the pretrained SAM, while nnUNetv2 outperformed the improved SAM in terms of overall segmentation accuracy. Nevertheless, the improved SAM demonstrated slightly more consistent results than nnUNetv2, especially on challenging cases that can lead to larger Hausdorff distances. In the future, more advanced techniques can be applied in order to further improve the performance of SAM on brain tumor segmentation.
摘要
脑肿分割是医学图像分割领域中的一大挑战。深度学习模型已经在此领域中发挥了作用，但是人工专家分割仍然是最准确的方法。最近发布的Segment Anything Model（SAM）已经开创了应用基础模型在这个难题上的可能性。然而，SAM主要在多样的自然图像上进行训练，这使得将SAM应用于生物医学分割，如脑肿诊断，变得更加困难。在这篇论文中，我们提高了SAM的面 máscara解码器使用基于Transfer Learning的Decathlon脑肿数据集。我们开发出了三种方法来封装四维数据到三维数据中，以便在SAM上进行分割。我们采用了在线数据增强策略，结合旋转和弹性变形来增加训练集的大小。我们使用了Dice相似度系数（DSC）和 Hausdorff距离95%（HD95）两个关键指标来评估我们的分割模型的性能。这两个指标为我们提供了有价值的分割结果评估方法。在我们的评估中，我们比较了我们改进的SAM模型与预训练的SAM模型以及广泛使用的nnUNetv2模型。我们发现，改进后的SAM模型在脑肿分割任务中显著提高了性能，而nnUNetv2模型在整体分割精度方面超过了改进后的SAM模型。然而，改进后的SAM模型在挑战性较高的案例中表现更为一致，尤其是在可能导致更大的 Hausdorff 距离的情况下。未来，我们可以采用更高级的技术来进一步提高SAM模型在脑肿分割任务中的性能。
Dipole-Spread Function Engineering for 6D Super-Resolution Microscopy
results: 论文还详细介绍了一些实际应用，包括生物学应用，以及未来技术的发展和挑战。Abstract
Fluorescent molecules are versatile nanoscale emitters that enable detailed observations of biophysical processes with nanoscale resolution. Because they are well-approximated as electric dipoles, imaging systems can be designed to visualize their 3D positions and 3D orientations, so-called dipole-spread function (DSF) engineering, for 6D super-resolution single-molecule orientation-localization microscopy (SMOLM). We review fundamental image-formation theory for fluorescent di-poles, as well as how phase and polarization modulation can be used to change the image of a dipole emitter produced by a microscope, called its DSF. We describe several methods for designing these modulations for optimum performance, as well as compare recently developed techniques, including the double-helix, tetrapod, crescent, and DeepSTORM3D learned point-spread functions (PSFs), in addition to the tri-spot, vortex, pixOL, raPol, CHIDO, and MVR DSFs. We also cover common imaging system designs and techniques for implementing engineered DSFs. Finally, we discuss recent biological applications of 6D SMOLM and future challenges for pushing the capabilities and utility of the technology.
摘要
fluorescent分子是一种 versatile nanoscale发射器，可以允许详细地观察生物物理过程，resolution nanoscale.因为它们可以被视为电动 polarization dipole， therefore imaging system can be designed to visualize their 3D positions and 3D orientations, so-called dipole-spread function (DSF) engineering, for 6D super-resolution single-molecule orientation-localization microscopy (SMOLM).我们将评论基本的图像形成理论 для fluorescent di-poles，以及如何使用阶段和 polarization 模ulation change the image of a dipole emitter produced by a microscope, called its DSF。我们将描述一些设计这些模ulation的方法，以及最近开发的技术，包括double-helix, tetrapod, crescent, and DeepSTORM3D learned point-spread functions (PSFs), in addition to the tri-spot, vortex, pixOL, raPol, CHIDO, and MVR DSFs。我们还将讨论一些通用的 imaging system designs and techniques for implementing engineered DSFs。最后，我们将讨论最近的生物应用和未来挑战，以推动技术的能力和实用性。
Efficient Predictive Coding of Intra Prediction Modes
results: 在HEVC标准下，我们的方法可以实现显著的比特率减少，同时保持JEM编码器的编码效率，这些结果表明了我们的方法在压缩效率方面的潜在提升。Abstract
The high efficiency video coding (HEVC) standard and the joint exploration model (JEM) codec incorporate 35 and 67 intra prediction modes (IPMs) respectively, which are essential for efficient compression of Intra coded blocks. These IPMs are transmitted to the decoder through a coding scheme. In our paper, we present an innovative approach to construct a dedicated coding scheme for IPM based on contextual information. This approach comprises three key steps: prediction, clustering, and coding, each of which has been enhanced by introducing new elements, namely, labels for prediction, tests for clustering, and codes for coding. In this context, we have proposed a method that utilizes a genetic algorithm to minimize the rate cost, aiming to derive the most efficient coding scheme while leveraging the available labels, tests, and codes. The resulting coding scheme, expressed as a binary tree, achieves the highest coding efficiency for a given level of complexity. In our experimental evaluation under the HEVC standard, we observed significant bitrate gains while maintaining coding efficiency under the JEM codec. These results demonstrate the potential of our approach to improve compression efficiency, particularly under the HEVC standard, while preserving the coding efficiency of the JEM codec.
摘要
高效视频编码（HEVC）标准和联合探索模型（JEM）编码器共有35和67内部预测模式（IPM），这些IPM是为高效压缩内部块的必需组成部分。这些IPM通过编码方案传输到解码器。在我们的论文中，我们提出了一种创新的方法，基于上下文信息来构建专门的编码方案。这种方法包括三个关键步骤：预测、聚类和编码，每一步都通过引入新的元素来增强，例如标签 для预测、测试 для聚类和编码。在这个上下文中，我们提出了一种使用遗传算法来最小化比特成本，以 derivate最高效的编码方案，同时利用可用的标签、测试和编码。结果表明，该编码方案，表示为二进制树，在给定的复杂度下实现了最高的编码效率。在我们的实验中，使用HEVC标准，我们观察到了显著的比特率减少，同时保持JEM编码器的编码效率。这些结果表明了我们的方法的潜在提高压缩效率，特别是在HEVC标准下，而且不会削弱JEM编码器的编码效率。
Longitudinal Volumetric Study for the Progression of Alzheimer’s Disease from Structural MR Images
paper_authors: Prayas Sanyal, Srinjay Mukherjee, Arkapravo Das, Anindya Sen
for: This paper aims to survey imaging biomarkers corresponding to the progression of Alzheimer’s Disease (AD).
methods: The pipeline implemented includes modern pre-processing techniques such as spatial image registration, skull stripping, and inhomogeneity correction. The segmentation of tissue classes is done using an unsupervised learning approach based on intensity histogram information.
results: The study found that the structural change in the form of volumes of cerebrospinal fluid (CSF), grey matter (GM), and white matter (WM) can be used to track the progression of Alzheimer’s Disease (AD). The segmented features provide insights such as atrophy, increase or intolerable shifting of GM, WM and CSF, which can help in future research for automated analysis of Alzheimer’s detection with clinical domain explainability.Here is the same information in Simplified Chinese text:
results: 研究发现，CSF、GM和WM的体积变化可以跟踪阿尔茨heimer病（AD）的进行。 segmented 特征提供了衰竭、增加或不具适应的GM、WM和CSF的信息，可以帮助未来研究自动化阿尔茨heimer 检测，并提供临床领域可解释的解释。Abstract
Alzheimer's Disease (AD) is primarily an irreversible neurodegenerative disorder affecting millions of individuals today. The prognosis of the disease solely depends on treating symptoms as they arise and proper caregiving, as there are no current medical preventative treatments. For this purpose, early detection of the disease at its most premature state is of paramount importance. This work aims to survey imaging biomarkers corresponding to the progression of Alzheimer's Disease (AD). A longitudinal study of structural MR images was performed for given temporal test subjects selected randomly from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The pipeline implemented includes modern pre-processing techniques such as spatial image registration, skull stripping, and inhomogeneity correction. The temporal data across multiple visits spanning several years helped identify the structural change in the form of volumes of cerebrospinal fluid (CSF), grey matter (GM), and white matter (WM) as the patients progressed further into the disease. Tissue classes are segmented using an unsupervised learning approach using intensity histogram information. The segmented features thus extracted provide insights such as atrophy, increase or intolerable shifting of GM, WM and CSF and should help in future research for automated analysis of Alzheimer's detection with clinical domain explainability.
摘要
阿尔茨海默病 (AD) 是一种主要是不可逆的脑组织衰退病种，影响了数百万人今天。这种病的诊断和治疗几乎完全依赖于病人的症状和照顾，没有现有的医学预防性治疗。因此，早期发现病种的症状非常重要。本研究的目的是对阿尔茨海默病的发展进行快照。使用ADNI数据库中随机选择的测试对象，我们实施了一种 longitudinal 的 MR 成像数据集，并应用现代的预处理技术，包括空间尺寸对齐、脑骨剥除和不均匀性 corrections。通过多个访问的时间跨度，我们发现了病人的结构变化，包括脑液（CSF）、灰 mater（GM）和白 matter（WM）的体积。使用无监督学习方法，我们对尺寸信息进行分类，并提取了相应的特征，如衰退、灰 mater 和 WM 的增加或不可接受的移动。这些特征提供了关于阿尔茨海默病的早期诊断和自动分析的Future研究中的解释。