Supervised machine learning-based medical image computing applications necessitate expert label curation, while unlabelled image data might be relatively abundant. Active learning methods aim to prioritise a subset of available image data for expert annotation, for label-efficient model training. We develop a controller neural network that measures priority of images in a sequence of batches, as in batch-mode active learning, for multi-class segmentation tasks. The controller is optimised by rewarding positive task-specific performance gain, within a Markov decision process (MDP) environment that also optimises the task predictor. In this work, the task predictor is a segmentation network. A meta-reinforcement learning algorithm is proposed with multiple MDPs, such that the pre-trained controller can be adapted to a new MDP that contains data from different institutes and/or requires segmentation of different organs or structures within the abdomen. We present experimental results using multiple CT datasets from more than one thousand patients, with segmentation tasks of nine different abdominal organs, to demonstrate the efficacy of the learnt prioritisation controller function and its cross-institute and cross-organ adaptability. We show that the proposed adaptable prioritisation metric yields converging segmentation accuracy for the novel class of kidney, unseen in training, using between approximately 40\% to 60\% of labels otherwise required with other heuristic or random prioritisation metrics. For clinical datasets of limited size, the proposed adaptable prioritisation offers a performance improvement of 22.6\% and 10.2\% in Dice score, for tasks of kidney and liver vessel segmentation, respectively, compared to random prioritisation and alternative active sampling strategies.

Three-dimensional (3D) freehand ultrasound (US) reconstruction without a tracker can be advantageous over its two-dimensional or tracked counterparts in many clinical applications. In this paper, we propose to estimate 3D spatial transformation between US frames from both past and future 2D images, using feed-forward and recurrent neural networks (RNNs). With the temporally available frames, a further multi-task learning algorithm is proposed to utilise a large number of auxiliary transformation-predicting tasks between them. Using more than 40,000 US frames acquired from 228 scans on 38 forearms of 19 volunteers in a volunteer study, the hold-out test performance is quantified by frame prediction accuracy, volume reconstruction overlap, accumulated tracking error and final drift, based on ground-truth from an optical tracker. The results show the importance of modelling the temporal-spatially correlated input frames as well as output transformations, with further improvement owing to additional past and/or future frames. The best performing model was associated with predicting transformation between moderately-spaced frames, with an interval of less than ten frames at 20 frames per second (fps). Little benefit was observed by adding frames more than one second away from the predicted transformation, with or without LSTM-based RNNs. Interestingly, with the proposed approach, explicit within-sequence loss that encourages consistency in composing transformations or minimises accumulated error may no longer be required. The implementation code and volunteer data will be made publicly available ensuring reproducibility and further research.

在医学图像分析中需要进行几次学习的能力是对支持图像数据的有效利用，该数据被标记为对新类进行分类或细分新类，该任务否则需要更多的培训图像和专家注释。这项工作描述了一种完全3D原型的几种分段算法，因此，训练有素的网络可以有效地适应培训中缺乏的临床有趣结构，仅使用来自不同研究所的几个标记图像。首先，为了弥补机构在新型类别的情节适应中的广泛认识的空间变异性，新型的空间注册机制被整合到原型学习中，由分割头和空间对齐模块组成。其次，为了帮助训练观察到的不完美比对，提出了支持掩模调节模块，以进一步利用支持图像中可用的注释。使用589个骨盆T2加权MR图像的数据集分割了八个对介入计划的解剖结构的应用，该实验是针对介入八个机构的八个解剖结构的应用。结果证明了3D公式中的每种，空间登记和支持掩模条件的功效，所有这些条件都独立或集体地做出了积极的贡献。与先前提出的2D替代方案相比，不管支持数据来自相同还是不同的机构，都具有统计学意义的少量分割性能。

在这项工作中，我们考虑了成对的跨模式图像注册的任务，这可能会受益于仅利用培训时间可用的其他图像，而这些图像从与注册的图像不同。例如，我们专注于对准主体内的多参数磁共振（MPMR）图像，在T2加权（T2W）扫描和具有高B值（DWI $ _ {high-b} $）的T2加权（T2W）扫描和扩散加权扫描之间。为了在MPMR图像中应用局部性肿瘤，由于相应的功能的可用性，因此认为具有零B值（DWI $ _ {B = 0} $）的扩散扫描被认为更易于注册到T2W。我们使用仅训练成像模态DWI $ _ {b = 0} $从特权模式算法中提出了学习，以支持具有挑战性的多模式注册问题。我们根据356名前列腺癌患者的369组3D多参数MRI图像提出了实验结果图像对，与注册前7.96毫米相比。结果还表明，与经典的迭代算法和其他具有/没有其他方式的经典基于测试的基于学习的方法相比，提出的基于学习的注册网络具有可比或更高准确性的有效注册。这些比较的算法也未能在此具有挑战性的应用中产生DWI $ _ {High-B} $和T2W之间的任何明显改进的对齐。

如果可疑的术前磁共振（MR）图像在超声引导的活检手术过程中，在超声引导的活检程序中，在临床上具有重要意义的前列腺癌有更好的机会进行采样。但是，活检程序的诊断准确性受到操作员依赖性技能和取样目标的经验的限制，这是一个顺序决策过程，涉及导航超声探针并为潜在的多个目标放置一系列采样针。这项工作旨在学习强化学习（RL）政策，以优化2D超声视图和活检针相对于指导模板的连续定位的行为，以便可以有效地进行MR目标进行有效且充分的采样。我们首先将任务作为马尔可夫决策过程（MDP）制定，并构建一个环境，该环境可以根据其解剖结构和从MR图像得出的病变来实际上为个别患者执行靶向动作。因此，在每次活检程序之前，可以通过奖励MDP环境中的阳性采样来优化患者特定的政策。五十四名前列腺癌患者的实验结果表明，拟议的RL学习政策的平均命中率为93％，平均癌症核心长度为11 mm，与人类设计的两种替代基线策略相比，没有手工设计奖励直接最大化这些临床相关指标。也许更有趣的是，发现RL代理商学习了适应病变大小的策略，在该病变大小上，针对小病变的针头的扩散优先考虑。此类策略以前尚未在临床实践中报告或普遍采用，而是与直观设计的策略相比，导致了总体上的靶向性能。

在面孔和机构的3D生成模型中学习解除一致，可解释和结构化的潜在代表仍然是一个开放的问题。当需要对身份特征的控制时，问题特别严重。在本文中，我们提出了一种直观但有效的自我监督方法来训练3D形变形自动化器（VAE），鼓励身份特征的解开潜在表示。通过在不同形状上交换任意特征来造成迷你批处理允许定义利用潜在表示中已知差异和相似性的损耗功能。在3D网眼上进行的实验结果表明，最先进的潜在解剖学方法无法解散面部和身体的身份特征。我们所提出的方法适当地解耦了这些特征的产生，同时保持了良好的表示和重建能力。

Microswimmers can acquire information on the surrounding fluid by sensing mechanical queues. They can then navigate in response to these signals. We analyse this navigation by combining deep reinforcement learning with direct numerical simulations to resolve the hydrodynamics. We study how local and non-local information can be used to train a swimmer to achieve particular swimming tasks in a non-uniform flow field, in particular a zig-zag shear flow. The swimming tasks are (1) learning how to swim in the vorticity direction, (2) the shear-gradient direction, and (3) the shear flow direction. We find that access to lab frame information on the swimmer's instantaneous orientation is all that is required in order to reach the optimal policy for (1,2). However, information on both the translational and rotational velocities seem to be required to achieve (3). Inspired by biological microorganisms we also consider the case where the swimmers sense local information, i.e. surface hydrodynamic forces, together with a signal direction. This might correspond to gravity or, for micro-organisms with light sensors, a light source. In this case, we show that the swimmer can reach a comparable level of performance as a swimmer with access to lab frame variables. We also analyse the role of different swimming modes, i.e. pusher, puller, and neutral swimmers.

Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and representation learning, where Vector Quantization is more commonly employed. In this work, we attempt to bring these lines of research closer by revisiting vector quantization for image compression. We build upon the VQ-VAE framework and introduce several modifications. First, we replace the vanilla vector quantizer by a product quantizer. This intermediate solution between vector and scalar quantization allows for a much wider set of rate-distortion points: It implicitly defines high-quality quantizers that would otherwise require intractably large codebooks. Second, inspired by the success of Masked Image Modeling (MIM) in the context of self-supervised learning and generative image models, we propose a novel conditional entropy model which improves entropy coding by modelling the co-dependencies of the quantized latent codes. The resulting PQ-MIM model is surprisingly effective: its compression performance on par with recent hyperprior methods. It also outperforms HiFiC in terms of FID and KID metrics when optimized with perceptual losses (e.g. adversarial). Finally, since PQ-MIM is compatible with image generation frameworks, we show qualitatively that it can operate under a hybrid mode between compression and generation, with no further training or finetuning. As a result, we explore the extreme compression regime where an image is compressed into 200 bytes, i.e., less than a tweet.

Utilizing the latest advances in Artificial Intelligence (AI), the computer vision community is now witnessing an unprecedented evolution in all kinds of perception tasks, particularly in object detection. Based on multiple spatially separated perception nodes, Cooperative Perception (CP) has emerged to significantly advance the perception of automated driving. However, current cooperative object detection methods mainly focus on ego-vehicle efficiency without considering the practical issues of system-wide costs. In this paper, we introduce VINet, a unified deep learning-based CP network for scalable, lightweight, and heterogeneous cooperative 3D object detection. VINet is the first CP method designed from the standpoint of large-scale system-level implementation and can be divided into three main phases: 1) Global Pre-Processing and Lightweight Feature Extraction which prepare the data into global style and extract features for cooperation in a lightweight manner; 2) Two-Stream Fusion which fuses the features from scalable and heterogeneous perception nodes; and 3) Central Feature Backbone and 3D Detection Head which further process the fused features and generate cooperative detection results. A cooperative perception platform is designed and developed for CP dataset acquisition and several baselines are compared during the experiments. The experimental analysis shows that VINet can achieve remarkable improvements for pedestrians and cars with 2x less system-wide computational costs and 12x less system-wide communicational costs.

Neural networks have revolutionized the area of artificial intelligence and introduced transformative applications to almost every scientific field and industry. However, this success comes at a great price; the energy requirements for training advanced models are unsustainable. One promising way to address this pressing issue is by developing low-energy neuromorphic hardware that directly supports the algorithm's requirements. The intrinsic non-volatility, non-linearity, and memory of spintronic devices make them appealing candidates for neuromorphic devices. Here we focus on the reservoir computing paradigm, a recurrent network with a simple training algorithm suitable for computation with spintronic devices since they can provide the properties of non-linearity and memory. We review technologies and methods for developing neuromorphic spintronic devices and conclude with critical open issues to address before such devices become widely used.