Explore the vast range of titles available.

Object detection using remote sensing data is a key task of the perception systems of self-driving vehicles. While many generic deep learning architectures have been proposed for this problem, there is little guidance on their suitability when using them in a particular scenario such as autonomous driving. In this work, we aim to assess the performance of existing 2D detection systems on a multi-class problem (vehicles, pedestrians, and cyclists) with images obtained from the on-board camera sensors of a car. We evaluate several one-stage (RetinaNet, FCOS, and YOLOv3) and two-stage (Faster R-CNN) deep learning meta-architectures under different image resolutions and feature extractors (ResNet, ResNeXt, Res2Net, DarkNet, and MobileNet). These models are trained using transfer learning and compared in terms of both precision and efficiency, with special attention to the real-time requirements of this context. For the experimental study, we use the Waymo Open Dataset, which is the largest existing benchmark. Despite the rising popularity of one-stage detectors, our findings show that two-stage detectors still provide the most robust performance. Faster R-CNN models outperform one-stage detectors in accuracy, being also more reliable in the detection of minority classes. Faster R-CNN Res2Net-101 achieves the best speed/accuracy tradeoff but needs lower resolution images to reach real-time speed. Furthermore, the anchor-free FCOS detector is a slightly faster alternative to RetinaNet, with similar precision and lower memory usage.

The application of plant growth-promoting rhizobacteria (PGPR) in the field has been hampered by a number of gaps in the knowledge of the mechanisms that improve plant growth, health, and production. These gaps include (i) the ability of PGPR to colonize the rhizosphere of plants and (ii) the ability of bacterial strains to thrive under different environmental conditions. In this review, different strategies of PGPR to colonize the rhizosphere of host plants are summarized and the advantages of having highly competitive strains are discussed. Some mechanisms exhibited by PGPR to colonize the rhizosphere include recognition of chemical signals and nutrients from root exudates, antioxidant activities, biofilm production, bacterial motility, as well as efficient evasion and suppression of the plant immune system. Moreover, many PGPR contain secretion systems and produce antimicrobial compounds, such as antibiotics, volatile organic compounds, and lytic enzymes that enable them to restrict the growth of potentially phytopathogenic microorganisms. Finally, the ability of PGPR to compete and successfully colonize the rhizosphere should be considered in the development and application of bioinoculants.

Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these types of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.

Background: Immune checkpoint inhibitors (ICI) have represented a revolution in the treatment of non-small-cell lung cancer (NSCLC). To improve these results, combined approaches are being tested. The addition of stereotactic ablative radiotherapy (SABR) to ICI seems promising. A systematic review was performed in order to assess the safety and efficacy of SABR-ICI combination. Material and Methods: MEDLINE databases from 2009 to March 3, 2019 were reviewed to obtain English language studies reporting clinical outcomes of the combination of ICI-SABR in NSCLC. 18 out of the 429 initial results fulfilled the inclusion criteria and were selected for review. Results: Eighteen articles, including six prospective studies, describing 1736 patients treated with an ICI-SABR combination fulfilled the selection criteria. The reported mean rates for local control and distant/abscopal response rates were 71% and 41%, respectively. Eleven studies reported progression-free survival and overall survival, with a mean of 4.6 and 12.4 months, respectively. Toxicity rates were consistent with the ones attributable to ICI treatment alone. Conclusions: The ICI-SABR combination has a good safety profile and achieves high rates of local control and greater chances of obtaining abscopal responses than SABR alone, with a relevant impact on PFS. More studies are needed to improve patient selection for an optimal benefit from this approach.

Mounting an effective immune response against cancer requires the activation of innate and adaptive immune cells. Metastatic melanoma is the most aggressive form of skin cancer. While immunotherapies have shown a remarkable success in melanoma treatment, patients develop resistance by mechanisms that include the establishment of an immune suppressive tumor microenvironment. Thus, understanding how metastatic melanoma cells suppress the immune system is vital to develop effective immunotherapies against this disease. In this study, we find that macrophages (MOs) and dendritic cells (DCs) are suppressed in metastatic melanoma and that the Ig-CDR-based peptide C36L1 is able to restore MOs and DCs' antitumorigenic and immunogenic functions and to inhibit metastatic growth in lungs. Specifically, C36L1 treatment is able to repolarize M2-like immunosuppressive MOs into M1-like antitumorigenic MOs, and increase the number of immunogenic DCs, and activated cytotoxic T cells, while reducing the number of regulatory T cells and monocytic myeloid-derived suppressor cells in metastatic lungs. Mechanistically, we find that C36L1 directly binds to the MIF receptor CD74 which is expressed on MOs and DCs, disturbing CD74 structural dynamics and inhibiting MIF signaling on these cells. Interfering with MIF-CD74 signaling on MOs and DCs leads to a decrease in the expression of immunosuppressive factors from MOs and an increase in the capacity of DCs to activate cytotoxic T cells. Our findings suggest that interfering with MIF-CD74 immunosuppressive signaling in MOs and DCs, using peptide-based immunotherapy can restore the antitumor immune response in metastatic melanoma. Our study provides the rationale for further development of peptide-based therapies to restore the antitumor immune response in metastatic melanoma.

Dipeptidyl peptidase-4 (DPP-4) is a target to treat type II diabetes mellitus. Therefore, it is important to understand the structural aspects of this enzyme and its interaction with drug candidates. This study involved molecular dynamics simulations, normal mode analysis, binding site detection and analysis of molecular interactions to understand the protein dynamics. We identified some DPP-4 functional motions contributing to the exposure of the binding sites and twist movements revealing how the two enzyme chains are interconnected in their bioactive form, which are defined as chains A (residues 40–767) and B (residues 40–767). By understanding the enzyme structure, its motions and the regions of its binding sites, it will be possible to contribute to the design of new DPP-4 inhibitors as drug candidates to treat diabetes.

Many receptors elicit signal transduction by activating multiple intracellular pathways. This transduction can be triggered by a non-specific ligand, which simultaneously activates all the signaling pathways of the receptors. However, the binding of one biased ligand preferentially trigger one pathway over another, in a process called biased signaling. The identification the functional motions related to each of these distinct pathways has a direct impact on the development of new effective and specific drugs. We show here how to detect specific functional motions by considering the case of the NGF/TrkA-Ig2 complex. NGF-mediated TrkA receptor activation is dependent on specific structural motions that trigger the neuronal growth, development, and survival of neurons in nervous system. The R221W mutation in the ngf gene impairs nociceptive signaling. We discuss how the large-scale structural effects of this mutation lead to the suppression of collective motions necessary to induce TrkA activation of nociceptive signaling. Our results suggest that subtle changes in the NGF interaction network due to the point mutation are sufficient to inhibit the motions of TrkA receptors putatively linked to nociception. The methodological approach presented in this article, based jointly on the normal mode analysis and the experimentally observed functional alterations due to point mutations provides an essential tool to reveal the structural changes and motions linked to the disease, which in turn could be necessary for a drug design study.

Background: Patients bearing large-volume, bulky primary or relapsed tumors, are usually referred to palliative low-dose radiotherapy with very poor results. Lattice Radiation Therapy (LRT) is able to produce a high number of high-dose foci or vortexes (multiple SBRT treatments), separated by low-dose zones (valleys). Treatment planning on vortex placing, valley definition, and dose administered depends on individual decisions of the treating team. The aim of our study is to assess for the first time the possibility of a dense fractionated LRT within the target volume. Methods: A total of 22 treatments in 20 patients were performed in the frame of a prospective observational study of fractionated LRT ongoing in our institution. According to our aim of achieving dense LRT, no GTV contraction was considered to create the LRTV (GTV is equal to LRTV). The vortexes were segmented as 1 cm diameter at a 1.5 cm vortex-to-vortex distance. Dose prescription to the vortexes per fraction was 12 Gy. Results: The vortex/LRTV ratio was 7.38 ± 2.13% (3.4–10.40%, median 7.60%). Mean dose to the vortex volume was 11.90 ± 0.09 Gy (11.70–12.10 Gy, median 11.90 Gy). Mean dose administered to the valley volume was 8.29 ± 0.70 (7.05–9.51 Gy, median 8.29 Gy). Valley/vortex (peak) dose ratio (VPDR) was 69.40 ± 6.02% (59.00–79.80%, median 69.70%). The mean peripheral tumor dose was 5.11 ± 0.8710 Gy (3.16–6.78 Gy, median 5.18 Gy). Conclusions: Our dense LRT schedule fulfilled most of the recommended guidelines for LRT, increasing the high dose points without risking the dose to the surrounding tissues. Further analysis of feasibility and safety are needed to secure the clinical relevance of our proposed protocol.

Grade II gliomas are slowly growing primary brain tumors that affect mostly young patients. Cytotoxic therapies (radiotherapy and/or chemotherapy) are used initially only for patients having a bad prognosis. These therapies are planned following the \"maximum dose in minimum time\" principle, i. e. the same schedule used for high-grade brain tumors in spite of their very different behavior. These tumors transform after a variable time into high-grade gliomas, which significantly decreases the patient's life expectancy. In this paper we study mathematical models describing the growth of grade II gliomas in response to radiotherapy. We find that protracted metronomic fractionations, i.e. therapeutical schedules enlarging the time interval between low-dose radiotherapy fractions, may lead to a better tumor control without an increase in toxicity. Other non-standard fractionations such as protracted or hypoprotracted schemes may also be beneficial. The potential survival improvement depends on the tumor's proliferation rate and can be even of the order of years. A conservative metronomic scheme, still being a suboptimal treatment, delays the time to malignant progression by at least one year when compared to the standard scheme.

Background In recent years, attempts have been made to incorporate patients' experiences into healthcare processes, to complement clinical indicators, with what are known as patient‐reported outcome measures (PROMs) and patient‐reported experience measures (PREMs). While the research into PROMs is more developed, the application of PREMs faces some difficulties. The incorporation of emotional indicators into assessments of the experience is an area that remains to be explored. Objectives This study proposes a new technique to analyse the emotions experienced by patients during the care process, examines how these emotions influence their satisfaction and propose that if healthcare services focus more on patients' emotions, they can improve the effectiveness of the sector. Methods The first, qualitative stage, gathered data from patients to design a patient journey (PJ). The PJ was then reproduced as a video. In a subsequent, quantitative stage, the video was shown to experimental participants, and their emotions were measured through facial expression analysis and a questionnaire. Results A new technique to gather emotional data showed that the emotions patients experience do not affect their satisfaction with their clinical care or the physical aspects of the process. However, their emotions did affect their satisfaction with people and organizations. Conclusions The importance of the emotional component of patients' experiences was underlined. Therefore, healthcare organizations should take account of this dimension, as well as the cognitive, to increase patient satisfaction and improve their care processes. Understanding the impact of the emotions identified at the subconscious level can help improve the patient experience. A new methodology was applied that may help health professionals to collect emotional data about patients' experiences and to develop PREMs. Patient/Public Contribution Patients were involved in all stages of this research. In the exploratory phase, some helped define the touchpoints of the PJ. The data from the subsequent experimental phase were collected from another group, and the emotions they experienced were identified through the analysis of their facial expressions. Based on the results of this study, a working group including patients has been established to work on improvements in the PJ.