Knowledge Distillation for Traversable Region Detection of LiDAR Scan in Off-Road Environments.

In this study, we propose a knowledge distillation (KD) method for segmenting off-road environment range images. Unlike urban environments, off-road terrains are irregular and pose a higher risk to hardware. Therefore, off-road self-driving systems are required to be computationally efficient. We used LiDAR point cloud range images to address this challenge. The three-dimensional (3D) point cloud data, which are rich in detail, require substantial computational resources. To mitigate this problem, we employ a projection method to convert the image into a two-dimensional (2D) image format using depth information. Our soft label-based knowledge distillation (SLKD) effectively transfers knowledge from a large teacher network to a lightweight student network. We evaluated SLKD using the RELLIS-3D off-road environment dataset, measuring the performance with respect to the mean intersection of union (mIoU) and GPU floating point operations per second (GFLOPS). The experimental results demonstrate that SLKD achieves a favorable trade-off between mIoU and GFLOPS when comparing teacher and student networks. This approach shows promise for enabling efficient off-road autonomous systems with reduced computational costs.

Effects of Cyclooxygenase-2 in Canine Melanoma-derived Extracellular Vesicles on Tumor Microenvironment In Vitro.

BACKGROUND/AIM: Tumor cell-derived extracellular vesicles (TEVs) promote tumor growth and metastasis; thus, they have drawn the attention of researchers. TEVs regulate the tumor microenvironment by facilitating crosstalk between immune and stromal cells. Macrophages are one of the key components involved in malignant behavior in melanomas. Generally, when activated, macrophages polarize into M1 (pro-inflammatory) or M2 (anti-inflammatory, pro-tumor) phenotypes. However, the role of canine melanoma-derived EVs in macrophage polarization is elusive. In this study, we aimed to analyze the pro- and anti-inflammatory cytokines that are common markers for M1 or M2 macrophages in vitro. MATERIALS AND METHODS: The analysis was performed under coculture conditions of canine melanoma-derived (LMeC) EVs with canine macrophages (DH82). Quantitative reverse transcription polymerase chain reaction, western blotting, and immunofluorescence were used. RESULTS: Canine melanoma-derived EVs polarized M1 macrophages (inducible nitric oxide synthase, tumor necrosis factor α) into M2 macrophages [cluster of differentiation (CD)206, interleukin-10] and cyclooxygenase-2 is a major factor in macrophage polarization in canine melanoma-derived EVs. Furthermore, we also found that melanoma-derived EVs induced the expression of angiogenic cytokines (vascular endothelial growth factor, transforming growth factor ß) in endothelial cells. CONCLUSION: Melanoma-derived EVs perform an immunomodulatory function and can be used as targets in anti-inflammatory treatment.

Isolated hypoaldosteronism managed by DOCP in a dog with chronic kidney disease and hypercortisolism.

A 13-year-old spayed female Schnauzer dog with chronic kidney disease (CKD; International Renal Interest Society stage 2, non-proteinuric, normotensive), diabetes mellitus, hypercortisolism and myxomatous mitral valve degeneration (American College of Veterinary Internal Medicine stage B2) presented with electrolyte imbalance that had progressed to hyperkalaemia and hyponatremia, with a sodium to potassium (Na:K) ratio of 19.6. Cortisol levels after the adrenocorticotropic hormone stimulation test were within the therapeutic range, but aldosterone levels were below the reference range; hence, isolated hypoaldosteronism was diagnosed. After administration of deoxycorticosterone pivalate (DOCP), the electrolyte imbalance improved with a Na:K ratio of 27.7. This is the first report of the management of isolated hypoaldosteronism and hypercortisolism using trilostane and DOCP in a dog. This case highlights the importance of recognizing isolated hypoaldosteronism after long-term treatment with trilostane in a canine patient with CKD.

Analysis of Relationship between Electroencephalograms and Subjective Measurements for In-Vehicle Information System: A Preliminary Study.

In this study, we explored the relationship between objective and subjective measures for usability evaluation in in-vehicle infotainment systems (IVISs). As a case study, four displays were evaluated based on cluster location and display orientation (that is, front-horizontal, front-vertical, right-horizontal, and right-vertical). Thirty-six participants performed tasks to manipulate the functions of the IVISs and data were collected through an electroencephalogram (EEG) sensor and questionnaire items. We analysed a model that estimated EEG-based objective indicators from subjective indicators. As a result, the objective indicators reflected the subjective indicators and were considered to explain the driver's cognitive state. Although EEG data were collected from only four participants, this study proposed an experimental design that could be applied to the analysis of the relationship between the subject's evaluation and EEG signals, as a preliminary study. We expect the experimental design and results of this study to be useful in analysing objective and subjective measures of usability evaluation.