Scott Faber (fieldheight3)

Herbicide use on boreal transmission line rights-of-way has been relatively limited compared to more temperate regions and therefore challenges exist in estimating and communicating the associated risks. Herbicides directly enter the ecosystem through deposition on vegetation and soils and can be a vector of contamination to browsing herbivores. Triclopyr drift and foliage concentrations were quantified following basal bark (Garlon RTU) and low-volume foliar (Garlon XRT) field treatments to aspen (Populus tremuloides) saplings and willow (Salix bebbiana) shrubs, respectively. Greater drift concentrations localized at the stem base were observed following basal bark treatments. Conversely, concentrations in foliage following the low-volume foliar treatment (DT50 = 5.7 days and DT90 = 34.6 days) were much higher than following basal bark treatment, which also required two days to translocate into the leaves. However, dissipation was rapid from both application methods and triclopyr in foliage was less than 20 μg g-1 a year following application. A risk assessment revealed an acceptable level of risk for acute toxicity to wildlife browsing on contaminated leaves from the residues detected in this study; however, an unacceptable level of risk for chronic toxicity to long-term browsing moose. Site-specific data regarding browsing behaviour on herbicide treated rights-of-ways and species-specific reference values are needed to improve confidence in the tier-two risk assessment. Basal bark application is ideal when stem density is lower and toxic effects for herbivores is of concern and low-volume foliar applications are best suited in areas with higher stem density when off-target herbicide deposition is less acceptable. Brain MRI is one of the most commonly used diagnostic imaging tools to detect neurodegenerative disease. Diagnostic image quality is a key factor to enable robust image analysis algorithms developed for downstream tasks such as segmentation. In clinical practice, one of the main challenges is the presence of image artefacts, which can lead to low diagnostic image quality. In this paper, we propose using dense convolutional neural networks to detect and a residual U-net architecture to correct motion related brain MRI artefacts. We first generate synthetic artefacts using an MR physics based corruption strategy. Then, we use a detection strategy based on dense convolutional neural network to detect artefacts. The detected artefacts are corrected using a residual U-net network trained on corrupted data. Our pipeline for detection and correction of artefacts is capable of reaching not only better quality image quality, but also better segmentation accuracy of stroke segmentation. The algorithm is validated using 28 cases brain MRI stroke segmentation dataset and showed an accuracy of 97.8% for detecting artefacts in our experiments. We also illustrated the improved image quality and segmentation accuracy with the proposed correction algorithm. Ensuring high image quality and high segmentation quality jointly can improve the automatic image analysis pipelines and reduce the influence of low image quality on final prognosis. With this work, we illustrate a performance analysis on brain MRI stroke segmentation. Ensuring high image quality and high segmentation quality jointly can improve the automatic image analysis pipelines and reduce the influence of low image quality on final prognosis. learn more With this work, we illustrate a performance analysis on brain MRI stroke segmentation. Accurate coronary artery tree segmentation can now be developed to assist radiologists in detecting coronary artery disease. In clinical medicine, the noise, low contrast, and uneven intensity of medical images along with complex shapes and vessel bifurcation structures make coronary artery segmentation challenging. In this work, we propose a multiobjective clustering and toroidal mo