•A novel online semi-supervised dictionary update method is proposed.•Cooperated with a pre-trained SVM, the proposed method can dynamically update the appearance dictionary for object tracking.•We ...integrate the proposed dictionary learning method and a sparse-based tracker into a tracking framework.•Results have shown that the proposed framework can outperform several state-of-the-art tracking methods even when drastic appearance variations happen.
It is a challenging task to develop robust object tracking methods to overcome dynamic object appearance and background changes. Online learning-based methods have been widely applied to cope with the challenges. However, online methods suffer from the problem of drifting. Sparse appearance representation has recently shown promising object tracking results. However, it lacks of information update to accurately track objects in long sequences or when object appearance drastically changes. In this paper, we propose a novel framework for tracking objects using a semi-supervised appearance dictionary learning method. Firstly, an object appearance dictionary is learned on the initial frame. Secondly, a graph model is employed in the proposed method for learning new bases when detecting object appearance change. The selected bases automatically replace the current rarely used bases. The proposed method is quantitatively compared with state-of-the-art methods on several challenging data sets. Results have shown that our proposed framework outperforms other methods even when drastic appearance variations happen.
In this study, we propose a novel point cloud based 3D registration and segmentation framework using reinforcement learning. An artificial agent, implemented as a distinct actor based on value ...networks, is trained to predict the optimal piece-wise linear transformation of a point cloud for the joint tasks of registration and segmentation. The actor network estimates a set of plausible actions and the value network aims to select the optimal action for the current observation. Point-wise features that comprise spatial positions (and surface normal vectors in the case of structured meshes), and their corresponding image features, are used to encode the observation and represent the underlying 3D volume. The actor and value networks are applied iteratively to estimate a sequence of transformations that enable accurate delineation of object boundaries. The proposed approach was extensively evaluated in both segmentation and registration tasks using a variety of challenging clinical datasets. Our method has fewer trainable parameters and lower computational complexity compared to the 3D U-Net, and it is independent of the volume resolution. We show that the proposed method is applicable to mono- and multi-modal segmentation tasks, achieving significant improvements over the state-of-the-art for the latter. The flexibility of the proposed framework is further demonstrated for a multi-modal registration application. As we learn to predict actions rather than a target, the proposed method is more robust compared to the 3D U-Net when dealing with previously unseen datasets, acquired using different protocols or modalities. As a result, the proposed method provides a promising multi-purpose segmentation and registration framework, particular in the context of image-guided interventions.
We assess dose and image quality of a state-of-the-art angiographic C-arm system (Axiom Artis dTA, Siemens Medical Solutions, Forchheim, Germany) for three-dimensional neuro-imaging at various dose ...levels and tube voltages and an associated measurement method. Unlike conventional CT, the beam length covers the entire phantom, hence, the concept of computed tomography dose index (CTDI) is not the metric of choice, and one can revert to conventional dosimetry methods by directly measuring the dose at various points using a small ion chamber. This method allows us to define and compute a new dose metric that is appropriate for a direct comparison with the familiar
CTDI
W
of conventional CT. A perception study involving the CATPHAN 600 indicates that one can expect to see at least the
9
mm
inset with 0.5% nominal contrast at the recommended head-scan dose
(
60
mGy
)
when using tube voltages ranging from
70
kVp
to
125
kVp
. When analyzing the impact of tube voltage on image quality at a fixed dose, we found that lower tube voltages gave improved low contrast detectability for small-diameter objects. The relationships between kVp, image noise, dose, and contrast perception are discussed.
Vitamin D has previously been quantified in some plants and algae, particularly in leaves of the Solanaceae family. We measured the vitamin D content of Australian native food plants and ...Australian-grown edible seaweed. Using liquid chromatography with triple quadrupole mass spectrometry, 13 samples (including leaf, fruit, and seed) were analyzed in duplicate for vitamin D₂, vitamin D₃, 25-hydroxyvitamin D₂, and 25-hydroxyvitamin D₃. Five samples contained vitamin D₂: raw wattleseed (
) (0.03 µg/100 g dry weight (DW)); fresh and dried lemon myrtle (
) leaves (0.03 and 0.24 µg/100 g DW, respectively); and dried leaves and berries of Tasmanian mountain pepper (
) (0.67 and 0.05 µg/100 g DW, respectively). Fresh kombu (
) contained vitamin D₃ (0.01 µg/100 g DW). Detected amounts were low; however, it is possible that exposure to ultraviolet radiation may increase the vitamin D content of plants and algae if vitamin D precursors are present.
Cryo-balloon catheters have attracted an increasing amount of interest in the medical community as they can reduce patient risk during left atrial pulmonary vein ablation procedures. As cryo-balloon ...catheters are not equipped with electrodes, they cannot be localized automatically by electro-anatomical mapping systems. As a consequence, X-ray fluoroscopy has remained an important means for guidance during the procedure. Most recently, image guidance methods for fluoroscopy-based procedures have been proposed, but they provide only limited support for cryo-balloon catheters and require significant user interaction. To improve this situation, we propose a novel method for automatic cryo-balloon catheter detection in fluoroscopic images by detecting the cryo-balloon catheter's built-in X-ray marker. Our approach is based on a blob detection algorithm to find possible X-ray marker candidates. Several of these candidates are then excluded using prior knowledge. For the remaining candidates, several catheter specific features are introduced. They are processed using a machine learning approach to arrive at the final X-ray marker position. Our method was evaluated on 75 biplane fluoroscopy images from 40 patients, from two sites, acquired with a biplane angiography system. The method yielded a success rate of 99.0% in plane A and 90.6% in plane B, respectively. The detection achieved an accuracy of 1.00 mm±0.82 mm in plane A and 1.13 mm±0.24 mm in plane B. The localization in 3-D was associated with an average error of 0.36 mm±0.86 mm.
Dietary vitamin D may compensate for inadequate sun exposure; however, there have been few investigations into the vitamin D content of Australian foods. We measured vitamin D₃ and 25-hydroxyvitamin ...D₃ (25(OH)D₃) in four species of white fish (barramundi, basa, hoki and king dory), and chicken eggs (cage and free-range), purchased from five Australian cities. Samples included local, imported and wild-caught fish, and eggs of varying size from producers with a range of hen stocking densities. Raw and cooked samples were analysed using high performance liquid chromatography with photodiode array. Limits of reporting were 0.2 and 0.1 μg/100 g for vitamin D₃ and 25(OH)D₃, respectively. The vitamin D₃ content of cooked white fish ranged from <0.1 to 2.3 μg/100 g, and the 25(OH)D₃ content ranged from 0.3 to 0.7 μg/100 g. The vitamin D₃ content of cooked cage eggs ranged from 0.4 to 0.8 μg/100 g, and the 25(OH)D₃ content ranged from 0.4 to 1.2 μg/100 g. The vitamin D₃ content of cooked free-range eggs ranged from 0.3 to 2.2 μg/100 g, and the 25(OH)D₃ content ranged from 0.5 to 0.8 μg/100 g. If, as has been suggested, 25(OH)D₃ has five times greater bioactivity than vitamin D₃, one cooked serve (100 g) of white fish, and one cooked serve of cage or free-range eggs (120 g) may provide 50% or 100%, respectively, of the current guidelines for the adequate intake of vitamin D (5 µg) for Australians aged 1-50 years.
To assess the potential dietary supply of vitamin D to Australian adults by application of new data for Australian primary foods of animal origin.
New published analytical data on the vitamin D ...contents of Australian primary foods from animal products were obtained and assessed for reliability. Using food consumption data from Australian population dietary surveys for 1995 and 2011-2013, estimates were made of the likely average daily intakes of vitamin D equivalents from these sources by Australian adults.
Meats, chicken, fish, eggs and dairy produce may alone have contributed about 4.2 μg vitamin D equivalents per day to average Australian diets of adults >18 years in 1995 and 4.3 μg in 2011-2013.
Dietary vitamin D intake in Australia is likely to be higher than previously estimated because new data from improved analytical methods reveal the contributions to vitamin D supply from foods of animal origin. Absence of reliable vitamin D data for milk and milk products, and the gaps in vitamin D data for many commonly consumed seafood, poultry, eggs and processed animal products greatly limit estimation of dietary vitamin D intakes by Australians.
For augmented fluoroscopy during cardiac ablation, a preoperatively acquired 3D model of a patient’s left atrium (LA) can be registered to X-ray images recorded during a contrast agent (CA) ...injection. An automatic registration method that works also for small amounts of CA is desired. We propose two similarity measures: The first focuses on edges of the patient anatomy. The second computes a contrast agent distribution estimate (CADE) inside the 3D model and rates its consistency with the CA as seen in biplane fluoroscopic images. Moreover, temporal filtering on the obtained registration results of a sequence is applied using a Markov chain framework. Evaluation was performed on 11 well-contrasted clinical angiographic sequences and 10 additional sequences with less CA. For well-contrasted sequences, the error for all 73 frames was 7.9 ± 6.3 mm and it dropped to 4.6 ± 4.0 mm when registering to an automatically selected, well enhanced frame in each sequence. Temporal filtering reduced the error for all frames from 7.9 ± 6.3 mm to 5.7 ± 4.6 mm. The error was typically higher if less CA was used. A combination of both similarity measures outperforms a previously proposed similarity measure. The mean accuracy for well contrasted sequences is in the range of other proposed manual registration methods.
During x-ray-guided interventional procedures, the medical staff is exposed to scattered ionizing radiation caused by the patient. To increase the staff's awareness of the invisible radiation and ...monitor dose online, computational scatter estimation methods are convenient. However, such methods are usually based on Monte Carlo (MC) simulations, which are inherently computationally expensive. Yet, in the interventional environment, immediate feedback to the personnel is desirable.
. In this work, we propose deep neural networks to mitigate the computational effort of MC simulations. Our learning-based models consider detailed models of the (outer) patient shape and (inner) anatomy, additional objects in the room, and the x-ray tube spectrum to cover imaging settings encountered in real interventional settings. We investigate two cases of scatter prediction. First, we employ network architectures to estimate the full three-dimensional (3D) scatter distribution. Second, we investigate the prediction of two-dimensional (2D) intensity projections that facilitate the intra-procedural visualization.
Depending on the dimensionality of the estimated scatter distribution and the network architecture, the mean relative error of each network is in the range of 12% and 14% compared to MC simulations. However, 3D scatter distributions can be estimated within 60 ms and 2D distributions within 15 ms.
Overall, our method is suitable to support the online assessment of scattered ionizing radiation in the interventional environment and can help to lower the occupational radiation risk.
•A new rapid method to quantify phytosterols in fortified food was developed.•Analysis is based on gas chromatography with flame ionization detection.•The method is more economical, time and labour ...efficient than current methods.•Critical aspects of method validation and uncertainty are reported.•This method can ensure accurate plant sterol fortification for the food industry.
A novel method for the measurement of total phytosterols in fortified food was developed and tested using gas chromatography with flame ionization detection. Unlike existing methods, this technique is capable of simultaneously extracting sterols during saponification thus significantly reducing extraction time and cost. The rapid method is suitable for sterol determination in a range of complex fortified foods including milk, cheese, fat spreads, oils and meat. The main enhancements of this new method include accuracy and precision, robustness, cost effectiveness and labour/time efficiencies. To achieve these advantages, quantification and the critical aspects of saponification were investigated and optimised. The final method demonstrated spiked recoveries in multiple matrices at 85–110% with a relative standard deviation of 1.9% and measurement uncertainty value of 10%.