Role of neutrophil myeloperoxidase in the development and progression of high-altitude pulmonary edema.

BACKGROUND: Neutrophil infiltration and hypoxic pulmonary vasoconstriction induced by hypobaric hypoxic stress are vital in high-altitude pulmonary edema (HAPE). Myeloperoxidase (MPO), an important enzyme in neutrophils, is associated with inflammation and oxidative stress and is also involved in the regulation of nitric oxide synthase (NOS), an enzyme that catalyzes the production of the vasodilatory factor nitric oxide (NO). However, the role of neutrophil MPO in HAPE's progression is still uncertain. Therefore, we hypothesize that MPO is involved in the development of HAPE via NOS. METHODS: In Xining, China (altitude: 2260 m), C57BL/6 N wild-type and mpo-/- mice served as normoxic controls, while a hypobaric chamber simulated 7000 m altitude for hypoxia. L-NAME, a nitric oxide synthase (NOS) inhibitor to inhibit NO production, was the experimental drug, and D-NAME, without NOS inhibitory effects, was the control. After measuring pulmonary artery pressure (PAP), samples were collected and analyzed for blood neutrophils, oxidative stress, inflammation, vasoactive substances, pulmonary alveolar-capillary barrier permeability, and lung tissue morphology. RESULTS: Wild-type mice's lung injury scores, permeability, and neutrophil counts rose at 24 and 48 h of hypoxia exposure. Under hypoxia, PAP increased from 12.89 ± 1.51 mmHg under normoxia to 20.62 ± 3.33 mmHg significantly in wild-type mice and from 13.24 ± 0.79 mmHg to 16.50 ± 2.07 mmHg in mpo-/- mice. Consistent with PAP, inducible NOS activity, lung permeability, lung injury scores, oxidative stress response, and inflammation showed more significant increases in wild-type mice than in mpo-/- mice. Additionally, endothelial NOS activity and NO levels decreased more pronouncedly in wild-type mice than in mpo-/- mice. NOS inhibition during hypoxia led to more significant increases in PAP, permeability, and lung injury scores compared to the drug control group, especially in wild-type mice. CONCLUSION: MPO knockout reduces oxidative stress and inflammation to preserve alveolar-capillary barrier permeability and limits the decline in endothelial NOS activity to reduce PAP elevation during hypoxia. MPO inhibition emerges as a prospective therapeutic strategy for HAPE, offering avenues for precise interventions.

Adversarial and Random Transformations for Robust Domain Adaptation and Generalization.

Data augmentation has been widely used to improve generalization in training deep neural networks. Recent works show that using worst-case transformations or adversarial augmentation strategies can significantly improve accuracy and robustness. However, due to the non-differentiable properties of image transformations, searching algorithms such as reinforcement learning or evolution strategy have to be applied, which are not computationally practical for large-scale problems. In this work, we show that by simply applying consistency training with random data augmentation, state-of-the-art results on domain adaptation (DA) and generalization (DG) can be obtained. To further improve the accuracy and robustness with adversarial examples, we propose a differentiable adversarial data augmentation method based on spatial transformer networks (STNs). The combined adversarial and random-transformation-based method outperforms the state-of-the-art on multiple DA and DG benchmark datasets. Furthermore, the proposed method shows desirable robustness to corruption, which is also validated on commonly used datasets.

Pedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison.

Despite all the significant advances in pedestrian detection brought by computer vision for driving assistance, it is still a challenging problem. One reason is the extremely varying lighting conditions under which such a detector should operate, namely day and nighttime. Recent research has shown that the combination of visible and non-visible imaging modalities may increase detection accuracy, where the infrared spectrum plays a critical role. The goal of this paper is to assess the accuracy gain of different pedestrian models (holistic, part-based, patch-based) when training with images in the far infrared spectrum. Specifically, we want to compare detection accuracy on test images recorded at day and nighttime if trained (and tested) using (a) plain color images; (b) just infrared images; and (c) both of them. In order to obtain results for the last item, we propose an early fusion approach to combine features from both modalities. We base the evaluation on a new dataset that we have built for this purpose as well as on the publicly available KAIST multispectral dataset.

Recognizing Actions Through Action-Specific Person Detection.

Action recognition in still images is a challenging problem in computer vision. To facilitate comparative evaluation independently of person detection, the standard evaluation protocol for action recognition uses an oracle person detector to obtain perfect bounding box information at both training and test time. The assumption is that, in practice, a general person detector will provide candidate bounding boxes for action recognition. In this paper, we argue that this paradigm is suboptimal and that action class labels should already be considered during the detection stage. Motivated by the observation that body pose is strongly conditioned on action class, we show that: 1) the existing state-of-the-art generic person detectors are not adequate for proposing candidate bounding boxes for action classification; 2) due to limited training examples, the direct training of action-specific person detectors is also inadequate; and 3) using only a small number of labeled action examples, the transfer learning is able to adapt an existing detector to propose higher quality bounding boxes for subsequent action classification. To the best of our knowledge, we are the first to investigate transfer learning for the task of action-specific person detection in still images. We perform extensive experiments on two benchmark data sets: 1) Stanford-40 and 2) PASCAL VOC 2012. For the action detection task (i.e., both person localization and classification of the action performed), our approach outperforms methods based on general person detection by 5.7% mean average precision (MAP) on Stanford-40 and 2.1% MAP on PASCAL VOC 2012. Our approach also significantly outperforms the state of the art with a MAP of 45.4% on Stanford-40 and 31.4% on PASCAL VOC 2012. We also evaluate our action detection approach for the task of action classification (i.e., recognizing actions without localizing them). For this task, our approach, without using any ground-truth person localization at test time, outperforms on both data sets state-of-the-art methods, which do use person locations.

Domain Adaptation of Deformable Part-Based Models.

The accuracy of object classifiers can significantly drop when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, adapting the classifiers to the scenario in which they must operate is of paramount importance. We present novel domain adaptation (DA) methods for object detection. As proof of concept, we focus on adapting the state-of-the-art deformable part-based model (DPM) for pedestrian detection. We introduce an adaptive structural SVM (A-SSVM) that adapts a pre-learned classifier between different domains. By taking into account the inherent structure in feature space (e.g., the parts in a DPM), we propose a structure-aware A-SSVM (SA-SSVM). Neither A-SSVM nor SA-SSVM needs to revisit the source-domain training data to perform the adaptation. Rather, a low number of target-domain training examples (e.g., pedestrians) are used. To address the scenario where there are no target-domain annotated samples, we propose a self-adaptive DPM based on a self-paced learning (SPL) strategy and a Gaussian Process Regression (GPR). Two types of adaptation tasks are assessed: from both synthetic pedestrians and general persons (PASCAL VOC) to pedestrians imaged from an on-board camera. Results show that our proposals avoid accuracy drops as high as 15 points when comparing adapted and non-adapted detectors.