Search Results (3)

The aim of the study was to assess the usefulness of IRT measurements of selected regions of interest (ROI), i.e., the eyeball and the nose of whippet dogs, before and after coursing competitions taking place in various environmental conditions, thereby enabling the assessment of well-being and the level of heat stress. The research was carried out over two different periods with different thermal humidity indexes (THIs). In the first period, the THI was 59.27 (Run 1), while in the second period, the THI was 63.77 (Run 2). The experimental subjects comprised 111 sighthound-type dogs—whippets—that were photographed with a thermal imaging camera to determine their eye temperature (ET) and nose temperature (NT). The average minimum and maximum eye temperatures were statistically lower after running in both measurements. Increased minimum and maximum nose temperatures were also demonstrated after both runs. The nasal temperature values were statistically higher for Run 2, for which the THI was higher, compared to Run 1. Eyeball temperature may be a marker of thermoregulation ability, regardless of the ambient temperature. The value of ETmax decreased on average by 2.23 °C and 0.4 °C, while NTmax increased uniformly by 2 °C after both runs. A correlation was found between the IRT measurements and physiological indicators. Full article

Hematological indices play a prognostic role in human osteosarcoma (OSA), but data are limited in dogs. The aim of this retrospective multicentric cohort study was to investigate the prognostic significance of pre-operative hematological/inflammatory indices in a cohort of client-owned dogs with appendicular OSA receiving standardized treatment. Cut-offs associated with progression-free survival (PFS) for pre-operative hematological values/ratios were established using the minimal p-value approach. Historical prognostic factors were also assessed. Statistical analyses were performed for the whole population and after the exclusion of sighthounds. Fifty-nine dogs were included (13 were sighthounds). Multivariable analysis revealed that a low neutrophil count (<4.37 × 10⁹/L, HR0.28, CI 95% 0.13–0.61, p = 0.001), a high red blood cell count (≥7.91, HR3.5, CI 95% 1.56–7.9, p = 0.002), and a proximal humerus location (HR3.0, CI 95% 1.48–6.1, p = 0.002) were associated with shorter PFS. In the sighthound-only population, only OSA location was significantly associated with PFS in univariable analysis. When sighthounds were excluded, a low neutrophil count, a low monocyte count, and a proximal humerus location were associated with shorter PFS, in multivariable analysis. Neutrophil count and possibly monocyte and red blood cell counts can be useful prognostic markers in canine OSA treated with amputation and adjuvant carboplatin. However, not all indices are appropriate in sighthounds. Full article

Automatic License Plate Recognition (ALPR) has remained an active research topic for years due to various applications, especially in Intelligent Transportation Systems (ITS). This paper presents an efficient ALPR technique based on deep learning, which accurately performs license plate (LP) recognition tasks in an unconstrained environment, even when trained on a limited dataset. We capture real traffic videos in the city and label the LPs and the alphanumeric characters in the LPs within different frames to generate training and testing datasets. Data augmentation techniques are applied to increase the number of training and testing samples. We apply the transfer learning approach to train the recently released YOLOv5 object detecting framework to detect the LPs and the alphanumerics. Next, we train a convolutional neural network (CNN) to recognize the detected alphanumerics. The proposed technique achieved a recognition rate of 92.8% on a challenging proprietary dataset collected in several jurisdictions of Saudi Arabia. This accuracy is higher than what was achieved on the same dataset by commercially available Sighthound (86%), PlateRecognizer (67%), OpenALPR (77%), and a state-of-the-art recent CNN model (82%). The proposed system also outperformed the existing ALPR solutions on several benchmark datasets. Full article