By utilizing only depth information, the paper introduces a novel but efficient local planning approach that enhances not only computational efficiency but also planning performances for memoryless local planners. The sampling is first proposed to be based on the depth data which can identify and eliminate a specific type of in-collision trajectories in the sampled motion primitive library. More specifically, all the obscured primitives' endpoints are found through querying the depth values and excluded from the sampled set, which can significantly reduce the computational workload required in collision checking. On the other hand, we furthermore propose a steering mechanism also based on the depth information to effectively prevent an autonomous vehicle from getting stuck when facing a large convex obstacle, providing a higher level of autonomy for a planning system. Our steering technique is theoretically proved to be complete in scenarios of convex obstacles. To evaluate effectiveness of the proposed DEpth based both Sampling and Steering (DESS) methods, we implemented them in the synthetic environments where a quadrotor was simulated flying through a cluttered region with multiple size-different obstacles. The obtained results demonstrate that the proposed approach can considerably decrease computing time in local planners, where more trajectories can be evaluated while the best path with much lower cost can be found. More importantly, the success rates calculated by the fact that the robot successfully navigated to the destinations in different testing scenarios are always higher than 99.6% on average.

Artificial Intelligence (AI) has become commonplace to solve routine everyday tasks. Because of the exponential growth in medical imaging data volume and complexity, the workload on radiologists is steadily increasing. We project that the gap between the number of imaging exams and the number of expert radiologist readers required to cover this increase will continue to expand, consequently introducing a demand for AI-based tools that improve the efficiency with which radiologists can comfortably interpret these exams. AI has been shown to improve efficiency in medical-image generation, processing, and interpretation, and a variety of such AI models have been developed across research labs worldwide. However, very few of these, if any, find their way into routine clinical use, a discrepancy that reflects the divide between AI research and successful AI translation. To address the barrier to clinical deployment, we have formed MONAI Consortium, an open-source community which is building standards for AI deployment in healthcare institutions, and developing tools and infrastructure to facilitate their implementation. This report represents several years of weekly discussions and hands-on problem solving experience by groups of industry experts and clinicians in the MONAI Consortium. We identify barriers between AI-model development in research labs and subsequent clinical deployment and propose solutions. Our report provides guidance on processes which take an imaging AI model from development to clinical implementation in a healthcare institution. We discuss various AI integration points in a clinical Radiology workflow. We also present a taxonomy of Radiology AI use-cases. Through this report, we intend to educate the stakeholders in healthcare and AI (AI researchers, radiologists, imaging informaticists, and regulators) about cross-disciplinary challenges and possible solutions.

This paper proposes a perception and path planning pipeline for autonomous racing in an unknown bounded course. The pipeline was initially created for the 2021 evGrandPrix autonomous division and was further improved for the 2022 event, both of which resulting in first place finishes. Using a simple LiDAR-based perception pipeline feeding into an occupancy grid based expansion algorithm, we determine a goal point to drive. This pipeline successfully achieved reliable and consistent laps in addition with occupancy grid algorithm to know the ways around a cone-defined track with an averaging speeds of 6.85 m/s over a distance 434.2 meters for a total lap time of 63.4 seconds.

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated to the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required for eliciting accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review, we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models

In this paper, deep-learning-based approaches namely fine-tuning of pretrained convolutional neural networks (VGG16 and VGG19), and end-to-end training of a developed CNN model, have been used in order to classify X-Ray images into four different classes that include COVID-19, normal, opacity and pneumonia cases. A dataset containing more than 20,000 X-ray scans was retrieved from Kaggle and used in this experiment. A two-stage classification approach was implemented to be compared to the one-shot classification approach. Our hypothesis was that a two-stage model will be able to achieve better performance than a one-shot model. Our results show otherwise as VGG16 achieved 95% accuracy using one-shot approach over 5-fold of training. Future work will focus on a more robust implementation of the two-stage classification model Covid-TSC. The main improvement will be allowing data to flow from the output of stage-1 to the input of stage-2, where stage-1 and stage-2 models are VGG16 models fine-tuned on the Covid-19 dataset.

In the human brain, essential iron molecules for proper neurological functioning exist in transferrin (tf) and ferritin (Fe3) forms. However, its unusual increment manifests iron overload, which reacts with hydrogen peroxide. This reaction will generate hydroxyl radicals, and irons higher oxidation states. Further, this reaction causes tissue damage or cognitive decline in the brain and also leads to neurodegenerative diseases. The susceptibility difference due to iron overload within the volume of interest (VOI) responsible for field perturbation of MRI and can benefit in estimating the neural disorder. The quantitative susceptibility mapping (QSM) technique can estimate susceptibility alteration and assist in quantifying the local tissue susceptibility differences. It has attracted many researchers and clinicians to diagnose and detect neural disorders such as Parkinsons, Alzheimers, Multiple Sclerosis, and aging. The paper presents a systematic review illustrating QSM fundamentals and its processing steps, including phase unwrapping, background field removal, and susceptibility inversion. Using QSM, the present work delivers novel predictive biomarkers for various neural disorders. It can strengthen new researchers fundamental knowledge and provides insight into its applicability for cognitive decline disclosure. The paper discusses the future scope of QSM processing stages and their applications in identifying new biomarkers for neural disorders.

The demonstrated success of transfer learning has popularized approaches that involve pretraining models from massive data sources and subsequent finetuning towards a specific task. While such approaches have become the norm in fields such as natural language processing, implementation and evaluation of transfer learning approaches for chemistry are in the early stages. In this work, we demonstrate finetuning for downstream tasks on a graph neural network (GNN) trained over a molecular database containing 2.7 million water clusters. The use of Graphcore IPUs as an AI accelerator for training molecular GNNs reduces training time from a reported 2.7 days on 0.5M clusters to 1.2 hours on 2.7M clusters. Finetuning the pretrained model for downstream tasks of molecular dynamics and transfer to a different potential energy surface took only 8.3 hours and 28 minutes, respectively, on a single GPU.

Structural alterations have been thoroughly investigated in the brain during the early onset of schizophrenia (SCZ) with the development of neuroimaging methods. The objective of the paper is an efficient classification of SCZ in 2 different classes: Cognitive Normal (CN), and SCZ using magnetic resonance imaging (MRI) images. This paper proposed a lightweight 3D convolutional neural network (CNN) based framework for SCZ diagnosis using MRI images. In the proposed model, lightweight 3D CNN is used to extract both spatial and spectral features simultaneously from 3D volume MRI scans, and classification is done using an ensemble bagging classifier. Ensemble bagging classifier contributes to preventing overfitting, reduces variance, and improves the model's accuracy. The proposed algorithm is tested on datasets taken from three benchmark databases available as open-source: MCICShare, COBRE, and fBRINPhase-II. These datasets have undergone preprocessing steps to register all the MRI images to the standard template and reduce the artifacts. The model achieves the highest accuracy 92.22%, sensitivity 94.44%, specificity 90%, precision 90.43%, recall 94.44%, F1-score 92.39% and G-mean 92.19% as compared to the current state-of-the-art techniques. The performance metrics evidenced the use of this model to assist the clinicians for automatic accurate diagnosis of SCZ.

Leveraging shared learning through Massively Multilingual Models, state-of-the-art machine translation models are often able to adapt to the paucity of data for low-resource languages. However, this performance comes at the cost of significantly bloated models which are not practically deployable. Knowledge Distillation is one popular technique to develop competitive, lightweight models: In this work, we first evaluate its use to compress MT models focusing on languages with extremely limited training data. Through our analysis across 8 languages, we find that the variance in the performance of the distilled models due to their dependence on priors including the amount of synthetic data used for distillation, the student architecture, training hyperparameters and confidence of the teacher models, makes distillation a brittle compression mechanism. To mitigate this, we explore the use of post-training quantization for the compression of these models. Here, we find that while distillation provides gains across some low-resource languages, quantization provides more consistent performance trends for the entire range of languages, especially the lowest-resource languages in our target set.

最近，分布式的半监督学习（DSSL）算法表明，它们在利用未标记的样本优于互连网络方面的有效性，在这些网络上，代理无法彼此共享其原始数据，并且只能与邻居传达非敏感信息。但是，现有的DSSL算法无法应对数据不确定性，并且可能会遭受高度计算和通信开销问题的困扰。为了解决这些问题，我们提出了一个分布式的半监督模糊回归（DSFR）模型，该模型具有模糊的规则和插值一致性正则化（ICR）。 ICR最近是针对半监督问题的，可以迫使决策边界通过稀疏的数据区域，从而增加模型的鲁棒性。但是，尚未考虑其在分布式方案中的应用。在这项工作中，我们提出了分布式模糊C均值（DFCM）方法和分布式插值一致性正则化（DICR）（DICR）构建在众所周知的乘数交替方向方法上，以分别定位DSFR的先行和结果组件中的参数。值得注意的是，DSFR模型的收敛非常快，因为它不涉及后传播过程，并且可扩展到从DFCM和DICR的利用率中受益的大规模数据集。人工和现实世界数据集的实验结果表明，就损失价值和计算成本而言，提出的DSFR模型可以比最新的DSSL算法获得更好的性能。