Determining appropriate spatial resolution of digital elevation model (DEM) is a key step for effective landslide analysis based on remote sensing data. Several studies demonstrated that choosing the ...finest DEM resolution is not always the best solution. Various DEM resolutions can be applicable for diverse landslide applications. Thus, this study aims to assess the influence of special resolution on automatic landslide mapping. Pixel-based approach using parametric and non-parametric classification methods, namely feed forward neural network (FFNN) and maximum likelihood classification (ML), were applied in this study. Additionally, this allowed to determine the impact of used classification method for selection of DEM resolution. Landslide affected areas were mapped based on four DEMs generated at 1 m, 2 m, 5 m and 10 m spatial resolution from airborne laser scanning (ALS) data. The performance of the landslide mapping was then evaluated by applying landslide inventory map and computation of confusion matrix. The results of this study suggests that the finest scale of DEM is not always the best fit, however working at 1 m DEM resolution on micro-topography scale, can show different results. The best performance was found at 5 m DEM-resolution for FFNN and 1 m DEM resolution for results. The best performance was found to be using 5 m DEM-resolution for FFNN and 1 m DEM resolution for ML classification.
Mechanical forces during machine milking induce changes in teat condition which can be differentiated into short-term and long-term changes. Machine milking-induced short-term changes in teat ...condition (STC) are defined as tissue responses to a single milking and have been associated with the risk of new intramammary infection. Albeit, their association with teat characteristics, such as teat-end shape, has not been investigated by rigorous methods. The primary objective was to determine the association of STC, as measured by ultrasonography, with teat-end shape. The second objective was to describe possible differences in the recovery time of teat tissue after machine milking among teats with different teat-end shapes. Holstein cows (n=128) were enrolled in an observational study, housed in free-stall pens with sand bedding and milked three times a day. Ultrasonography of the left front and right hind teat was performed after teat preparation before milking (t−1), immediately after milking (t0) and 1, 3, 5 and 7 h after milking (t1, t3, t5, t7). The teat tissue parameters measured from ultrasound scans were teat canal length, teat-end diameter, teat-end diameter at the midpoint between the distal and proximal end of the teat canal, teat wall thickness, and teat cistern width. Teat-end shape was assessed visually and classified into three categories: pointed, flat and round. Multivariable linear regression analyses showed differences in the relative change of teat tissue parameters (compared with t−1) at t0 among teats with different teat-end shapes, with most parameters showing the largest change for round teats. The premilking values were reached (recovery time) after 7 h in teats with a pointed teat-end shape, whereas recovery time was greater than 7 h in teats with flat and round teat-end shapes. Under the same liner and milking machine conditions, teats with a round teat-end shape had the most severe short-term changes. The results of this observational study indicated that teat-end shape may be one of the factors that contribute to the severity of STC.
Remote sensing techniques are an important tool in fluvial transport monitoring, since they allow for effective evaluation of the volume of transported material. Nevertheless, there is no methodology ...for automatic calculation of movement parameters of individual rocks. These parameters can be determined by point cloud registration. Hence, the goal of this study is to develop a robust algorithm for terrestrial laser scanning point cloud registration. The registration is based on Iterative Closest Point algorithm, which requires well established initial parameters of transformation. Thus, we propose to calculate the initial parameters based on key points representing the maximum of Gaussian curvature. For each key point the set of geometrical features is calculated. The key points are then matched between two point clouds as a nearest neighbor in feature domain. Different combinations of neighborhood sizes, feature subsets, metrics and number of nearest neighbors were tested to obtain the highest ratio between properly and improperly matched key points. Finally, RANSAC algorithm was used to calculate the initial transformation parameters between the point clouds and the ICP algorithm was used for calculation of final transformation parameters. The investigations carried out on sample point clouds representing rocks enabled the adjustment of parameters of the algorithm and showed that the Gaussian curvature can be used as a 3-dimentional key point detector for such objects. The proposed algorithm enabled to register point clouds with the mean distance between point clouds equal to 3 mm.
The Velodyne HDL-32E laser scanner is used more frequently as main mapping sensor in small commercial UASs. However, there is still little information about the actual accuracy of point clouds ...collected with such UASs. This work evaluates empirically the accuracy of the point cloud collected with such UAS. Accuracy assessment was conducted in four aspects: impact of sensors on theoretical point cloud accuracy, trajectory reconstruction quality, and internal and absolute point cloud accuracies. Theoretical point cloud accuracy was evaluated by calculating 3D position error knowing errors of used sensors. The quality of trajectory reconstruction was assessed by comparing position and attitude differences from forward and reverse EKF solution. Internal and absolute accuracies were evaluated by fitting planes to 8 point cloud samples extracted for planar surfaces. In addition, the absolute accuracy was also determined by calculating point 3D distances between LiDAR UAS and reference TLS point clouds. Test data consisted of point clouds collected in two separate flights performed over the same area. Executed experiments showed that in tested UAS, the trajectory reconstruction, especially attitude, has significant impact on point cloud accuracy. Estimated absolute accuracy of point clouds collected during both test flights was better than 10 cm, thus investigated UAS fits mapping-grade category.
Agricultural robotics rely on digital tools and sensor integration in order to improve efficiency and sustainability of cultivations. One part of orchard inventory is the identification of a tree ...trunk i.e. localization and diameter determination. However, this is a challenging task, due to thin trunks, presence of leaves and low branches. In this paper we present a case study for determining these parameters using the example of peach orchard, for which a high-density LiDAR data (over 3000 points/m2) was obtained with a small unmanned aerial system (UAS) during a leafy and leafless season. We applied point thresholding by height and by components of normal vector, in order to identify points reflected from trunks. Alpha-shape algorithm was used to aggregate together points, that belong to the same trunk and their centroid determined the trunk location. Trunk diameters were calculated using two alternative approaches: the Principal Component Analysis (PCA) and circle fit. For the leafy season trunk identification is challenging. Omission errors were caused due to few reflections from trunks and commission errors occurred because of the unfiltered reflections from low branches and young twigs oriented towards the ground. All 194 trunks were identified from data collected during the leafless season. The accuracy of tree location was 0.27 m and the accuracy of diameter determination using PCA was 0.03 m.
Video capsule endoscopy (VCE) is an innovation that has revolutionized care within the field of gastroenterology, but the time needed to read the studies generated has often been cited as an area for ...improvement. With the aid of artificial intelligence, various fields have been able to improve the efficiency of their core processes by reducing the burden of irrelevant stimuli on their human elements. In this study, we have created and trained a convolutional neural network (CNN) capable of significantly reducing capsule endoscopy reading times by eliminating normal parts of the video while retaining abnormal ones. Our model, a variation of ResNet50, was able to reduce VCE video length by 47% on average and capture abnormal segments on VCE with 100% accuracy on three VCE videos as confirmed by the reading physician. The ability to successfully pre-process VCE footage as we have demonstrated will greatly increase the practicality of VCE technology without the expense of hundreds of hours of physician annotated videos.
There is a growing body of clinical and laboratory evidence to support the notion that food allergy plays a role in the pathogenesis of atopic dermatitis (AD). However, the incidence of IgE-mediated ...food allergy in children with AD is not well established.
A prospective study to determine the prevalence of IgE-mediated food hypersensitivity among patients referred to a university-based dermatologist for evaluation of AD.
University hospital pediatric dermatology clinic.
A total of 63 patients with AD were recruited (35 male; 32 white, 24 African-American, 7 Asian).
Patients were assigned an AD symptom score (SCORAD) and were screened for food-specific serum IgE antibodies to six foods (milk, egg, wheat, soy, peanut, fish) known to be the most allergenic in children. The levels of food-specific serum IgE were determined by the CAP System fluoroscein-enzyme immunoassay (CAP); patients with a value >/=0.7 kIUa/L were invited for an additional allergy evaluation. Those with CAP values below the cutoff were considered not food allergic. Patients were considered to be allergic if they met one of the following criteria for at least one food: 1) reaction on food challenge; 2) CAP value more than the 95% confidence interval predictive for a reaction; 3) convincing history of an acute significant (hives, respiratory symptoms) reaction after the isolated ingestion of a food to which there was a positive CAP or prick skin test.
A total of 63 patients (median age, 2.8 years; median SCORAD, 41.1) were recruited; 22 had negative CAP values (without a significant difference in age or SCORAD score, compared with the 41 with positive specific IgE values). Further allergy evaluation was offered to the 41 remaining patients; 10 were lost to follow-up and 31 were evaluated further. Of these, 19 underwent a total of 50 food challenges (36 double-blind, placebo-controlled, and 14 open), with 11 patients experiencing 18 positive challenges (94% with skin reactions). Additionally, 6 patients had a convincing history with a predictive level of IgE; 5 had a convincing history with positive, indeterminate levels of IgE; and 1 had predictive levels of IgE (to egg and peanut) without a history of an acute reaction. Overall, 23/63 (37%; 95% confidence interval, 25% to 50%) had clinically significant IgE-mediated food hypersensitivity without a significant difference in age or symptom score between those with or without food allergy.
Approximately one third of children with refractory, moderate-severe AD have IgE-mediated clinical reactivity to food proteins. The prevalence of food allergy in this population is significantly higher than that in the general population, and an evaluation for food allergy should be considered in these patients.
In order to address a long standing challenge for internal medicine physicians we developed artificial intelligence (AI) models to identify patients at risk of increased mortality. After querying ...2,425 records of patients transferred from non-intensive care units to intensive care units from the Veteran Affairs Corporate Data Warehouse (CDW), we created two datasets. The former used 22 independent variables that included “Length of Hospital Stay” and “Days to Intensive Care Transfer,” and the latter lacked these two variables. Since these two variables are unknown at the time of admission, the second set is more clinically relevant. We trained 16 machine learning models using both datasets. The best-performing models were fine-tuned and evaluated. The LightGBM model achieved the best results for both datasets. The model trained with 22 variables achieved a Receiver Operating Characteristics Curve-Area Under the Curve (ROC-AUC) of 0.89 and an accuracy of 0.72, with a sensitivity of 0.97 and a specificity of 0.68. The model trained with 20 variables achieved a ROC-AUC of 0.86 and an accuracy of 0.71, with a sensitivity of 0.94 and a specificity of 0.67. The top features for the former model included “Total length of Stay,” “Admit to ICU Transfer Days,” and “Lymphocyte Next Lab Value.” For the latter model, the top features included “Lymphocyte First Lab Value,” “Hemoglobin First Lab Value,” and “Hemoglobin Next Lab Value.” Our clinically relevant predictive mortality model can assist providers in optimizing resource utilization when managing large caseloads, particularly during shift changes.
The estimation of dendrometric parameters has become an important issue for agriculture planning and for the efficient management of orchards. Airborne Laser Scanning (ALS) data is widely used in ...forestry and many algorithms for automatic estimation of dendrometric parameters of individual forest trees were developed. Unfortunately, due to significant differences between forest and fruit trees, some contradictions exist against adopting the achievements of forestry science to agricultural studies indiscriminately. In this study we present the methodology to identify individual trees in apple orchard and estimate heights of individual trees, using high-density LiDAR data (3200 points/m2) obtained with Unmanned Aerial Vehicle (UAV) equipped with Velodyne HDL32-E sensor. The processing strategy combines the alpha-shape algorithm, principal component analysis (PCA) and detection of local minima. The alpha-shape algorithm is used to separate tree rows. In order to separate trees in a single row, we detect local minima on the canopy profile and slice polygons from alpha-shape results. We successfully separated 92 % of trees in the test area. 6 % of trees in orchard were not separated from each other and 2 % were sliced into two polygons. The RMSE of tree heights determined from the point clouds compared to field measurements was equal to 0.09 m, and the correlation coefficient was equal to 0.96. The results confirm the usefulness of LiDAR data from UAV platform in orchard inventory.
Digital pathology has transformed the traditional pathology practice of analyzing tissue under a microscope into a computer vision workflow. Whole-slide imaging allows pathologists to view and ...analyze microscopic images on a computer monitor, enabling computational pathology. By leveraging artificial intelligence (AI) and machine learning (ML), computational pathology has emerged as a promising field in recent years. Recently, task-specific AI/ML (eg, convolutional neural networks) has risen to the forefront, achieving above-human performance in many image-processing and computer vision tasks. The performance of task-specific AI/ML models depends on the availability of many annotated training datasets, which presents a rate-limiting factor for AI/ML development in pathology. Task-specific AI/ML models cannot benefit from multimodal data and lack generalization, eg, the AI models often struggle to generalize to new datasets or unseen variations in image acquisition, staining techniques, or tissue types. The 2020s are witnessing the rise of foundation models and generative AI. A foundation model is a large AI model trained using sizable data, which is later adapted (or fine-tuned) to perform different tasks using a modest amount of task-specific annotated data. These AI models provide in-context learning, can self-correct mistakes, and promptly adjust to user feedback. In this review, we provide a brief overview of recent advances in computational pathology enabled by task-specific AI, their challenges and limitations, and then introduce various foundation models. We propose to create a pathology-specific generative AI based on multimodal foundation models and present its potentially transformative role in digital pathology. We describe different use cases, delineating how it could serve as an expert companion of pathologists and help them efficiently and objectively perform routine laboratory tasks, including quantifying image analysis, generating pathology reports, diagnosis, and prognosis. We also outline the potential role that foundation models and generative AI can play in standardizing the pathology laboratory workflow, education, and training.
PDF
