Harnessing AI and robotics in humanitarian assistance and disaster response.

AI and robotics can facilitate humanitarian assistance and disaster response, but partnerships with practitioners are crucial.

Plastic rain in protected areas of the United States.

Eleven billion metric tons of plastic are projected to accumulate in the environment by 2025. Because plastics are persistent, they fragment into pieces that are susceptible to wind entrainment. Using high-resolution spatial and temporal data, we tested whether plastics deposited in wet versus dry conditions have distinct atmospheric life histories. Further, we report on the rates and sources of deposition to remote U.S. conservation areas. We show that urban centers and resuspension from soils or water are principal sources for wet-deposited plastics. By contrast, plastics deposited under dry conditions were smaller in size, and the rates of deposition were related to indices that suggest longer-range or global transport. Deposition rates averaged 132 plastics per square meter per day, which amounts to >1000 metric tons of plastic deposition to western U.S. protected lands annually.

Aromatic donor-acceptor interaction promoted catalyst assemblies for hydrolytic kinetic resolution of epichlorohydrin.

Three generations of Co(iii)-salen complexes containing electron-deficient aromatic moieties (acceptors) have been synthesized. When electron-rich aromatic compounds (donors) were introduced, these complexes were designed to form catalyst assemblies through aromatic donor-acceptor interaction. For all three generations of complexes, the addition of a proper donor led to higher catalytic efficiency in the hydrolytic kinetic resolution (HKR) of epichlorohydrin. The reaction rates are in the following order: Generation 3 > Generation 2 > Generation 1. The aromatic donor-acceptor interaction was verified by NMR spectroscopy and UV-vis absorption spectroscopy studies. These results demonstrated that aromatic donor-acceptor interaction can be a valuable driving force in the assembly of supramolecular catalysts.

Clickstream Analysis for Crowd-Based Object Segmentation with Confidence.

With the rapidly increasing interest in machine learning based solutions for automatic image annotation, the availability of reference annotations for algorithm training is one of the major bottlenecks in the field. Crowdsourcing has evolved as a valuable option for low-cost and large-scale data annotation; however, quality control remains a major issue which needs to be addressed. To our knowledge, we are the first to analyze the annotation process to improve crowd-sourced image segmentation. Our method involves training a regressor to estimate the quality of a segmentation from the annotator's clickstream data. The quality estimation can be used to identify spam and weight individual annotations by their (estimated) quality when merging multiple segmentations of one image. Using a total of 29,000 crowd annotations performed on publicly available data of different object classes, we show that (1) our method is highly accurate in estimating the segmentation quality based on clickstream data, (2) outperforms state-of-the-art methods for merging multiple annotations. As the regressor does not need to be trained on the object class that it is applied to it can be regarded as a low-cost option for quality control and confidence analysis in the context of crowd-based image annotation.

Large-scale medical image annotation with crowd-powered algorithms.

Accurate segmentations in medical images are the foundations for various clinical applications. Advances in machine learning-based techniques show great potential for automatic image segmentation, but these techniques usually require a huge amount of accurately annotated reference segmentations for training. The guiding hypothesis of this paper was that crowd-algorithm collaboration could evolve as a key technique in large-scale medical data annotation. As an initial step toward this goal, we evaluated the performance of untrained individuals to detect and correct errors made by three-dimensional (3-D) medical segmentation algorithms. To this end, we developed a multistage segmentation pipeline incorporating a hybrid crowd-algorithm 3-D segmentation algorithm integrated into a medical imaging platform. In a pilot study of liver segmentation using a publicly available dataset of computed tomography scans, we show that the crowd is able to detect and refine inaccurate organ contours with a quality similar to that of experts (engineers with domain knowledge, medical students, and radiologists). Although the crowds need significantly more time for the annotation of a slice, the annotation rate is extremely high. This could render crowdsourcing a key tool for cost-effective large-scale medical image annotation.

Crowdtruth validation: a new paradigm for validating algorithms that rely on image correspondences.

PURPOSE: Feature tracking and 3D surface reconstruction are key enabling techniques to computer-assisted minimally invasive surgery. One of the major bottlenecks related to training and validation of new algorithms is the lack of large amounts of annotated images that fully capture the wide range of anatomical/scene variance in clinical practice. To address this issue, we propose a novel approach to obtaining large numbers of high-quality reference image annotations at low cost in an extremely short period of time. METHODS: The concept is based on outsourcing the correspondence search to a crowd of anonymous users from an online community (crowdsourcing) and comprises four stages: (1) feature detection, (2) correspondence search via crowdsourcing, (3) merging multiple annotations per feature by fitting Gaussian finite mixture models, (4) outlier removal using the result of the clustering as input for a second annotation task. RESULTS: On average, 10,000 annotations were obtained within 24 h at a cost of $100. The annotation of the crowd after clustering and before outlier removal was of expert quality with a median distance of about 1 pixel to a publically available reference annotation. The threshold for the outlier removal task directly determines the maximum annotation error, but also the number of points removed. CONCLUSIONS: Our concept is a novel and effective method for fast, low-cost and highly accurate correspondence generation that could be adapted to various other applications related to large-scale data annotation in medical image computing and computer-assisted interventions.

Sparse Multidimensional Patient Modeling using Auxiliary Confidence Labels.

In this work, we focus on the problem of learning a classification model that performs inference on patient Electronic Health Records (EHRs). Often, a large amount of costly expert supervision is required to learn such a model. To reduce this cost, we obtain confidence labels that indicate how sure an expert is in the class labels she provides. If meaningful confidence information can be incorporated into a learning method, fewer patient instances may need to be labeled to learn an accurate model. In addition, while accuracy of predictions is important for any inference model, a model of patients must be interpretable so that clinicians can understand how the model is making decisions. To these ends, we develop a novel metric learning method called Confidence bAsed MEtric Learning (CAMEL) that supports inclusion of confidence labels, but also emphasizes interpretability in three ways. First, our method induces sparsity, thus producing simple models that use only a few features from patient EHRs. Second, CAMEL naturally produces confidence scores that can be taken into consideration when clinicians make treatment decisions. Third, the metrics learned by CAMEL induce multidimensional spaces where each dimension represents a different "factor" that clinicians can use to assess patients. In our experimental evaluation, we show on a real-world clinical data set that our CAMEL methods are able to learn models that are as or more accurate as other methods that use the same supervision. Furthermore, we show that when CAMEL uses confidence scores it is able to learn models as or more accurate as others we tested while using only 10% of the training instances. Finally, we perform qualitative assessments on the metrics learned by CAMEL and show that they identify and clearly articulate important factors in how the model performs inference.

Mobile markerless augmented reality and its application in forensic medicine.

PURPOSE: During autopsy, forensic pathologists today mostly rely on visible indication, tactile perception and experience to determine the cause of death. Although computed tomography (CT) data is often available for the bodies under examination, these data are rarely used due to the lack of radiological workstations in the pathological suite. The data may prevent the forensic pathologist from damaging evidence by allowing him to associate, for example, external wounds to internal injuries. To facilitate this, we propose a new multimodal approach for intuitive visualization of forensic data and evaluate its feasibility. METHODS: A range camera is mounted on a tablet computer and positioned in a way such that the camera simultaneously captures depth and color information of the body. A server estimates the camera pose based on surface registration of CT and depth data to allow for augmented reality visualization of the internal anatomy directly on the tablet. Additionally, projection of color information onto the CT surface is implemented. RESULTS: We validated the system in a postmortem pilot study using fiducials attached to the skin for quantification of a mean target registration error of [Formula: see text] mm. CONCLUSIONS: The system is mobile, markerless, intuitive and real-time capable with sufficient accuracy. It can support the forensic pathologist during autopsy with augmented reality and textured surfaces. Furthermore, the system enables multimodal documentation for presentation in court. Despite its preliminary prototype status, it has high potential due to its low price and simplicity.

Use of Liposomal Bupivacaine Instead of an Epidural Can Improve Outcomes Following Total Knee Arthroplasty.

The purpose of this study was to compare periarticular injection of liposomal bupivacaine (LB) to epidural analgesia as part of multimodal pain management strategy for total knee arthroplasty (TKA). A retrospective review of 50 patients undergoing TKA compared 25 patients who received LB to 25 patients who received an epidural. After postoperative day 1, patients who received LB exhibited significantly lower (p < .001) pain scores than those who received an epidural. Patients who received LB also had a significantly shorter length of hospital stay (p < .0001), greater range of motion on postoperative day 1, and walked significantly farther (p < .001) on postoperative day 1. LB appears to provide effective pain control leading to shorter hospital stays and improved early physical function compared with standard pain management with an epidural.