Maintaining environmental sustainability relies on continuously monitoring environmental conditions. Water is an environmental component essential to the survival of all living organisms; hence, to prevent contaminati...
详细信息
ISBN:
(数字)9781728110547
ISBN:
(纸本)9781728110554
Maintaining environmental sustainability relies on continuously monitoring environmental conditions. Water is an environmental component essential to the survival of all living organisms; hence, to prevent contamination and ensure proper water treatment, persistent observations and measurements of water quality are crucial. Traditionally, the procedure for testing the quality of water involved traveling to designated testing sites, manually collecting surface samples, transporting said samples to a laboratory for analysis, analyzing chemicals and microbial contaminants, and publishing the findings with the community. The technological advances in wireless sensor networks bring forth the opportunity for remote measurement and monitoring of water samples. Not only is the presence of the scientist no longer mandatory on the testing site, but the data can also be automatically collected, visualized, monitored, and shared through sensor recordings. These transitions exhibit a much fine-grained level of spatio-temporal information collection and allow for more comprehensive and long-term studies. Three research buoys, designed to be deployed in both shallow freshwater ecosystems and near-shore marine environments, were launched in different locations of South Florida to tackle complex challenges of environmental contamination. The research presented here designs and deploys a water quality monitoring platform for allowing the scientists to analyze better the near-real-time data collected by the buoys and generate insights. We further demonstrate two engaging near-real-time visualization methods developed to disseminate data trends and findings to a wide range of audiences from diverse backgrounds.
Registration of longitudinal brain Magnetic Resonance Imaging (MRI) scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been considerable progress in developing...
详细信息
Registration of longitudinal brain Magnetic Resonance Imaging (MRI) scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been considerable progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The challenge was conducted in conjunction with both the IEEE International Symposium on biomedical Imaging (ISBI) 2022 and the International conference on Medical Image computing and Computer-Assisted Intervention (MICCAI) 2022. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. The training data with their GT annotations, were publicly released to enable the development of registration algorithms. The validation data, without their GT annotations, were also released to allow for algorithmic evaluation prior to the testing phase, which only allowed submission of containerized algorithms for evaluation on hidden hold-out testing data. Quantitative evaluation and ranking was based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency
Anatomy is the branch of biological science in medical education that focuses on structured parts of living things, especially the human body. Traditional teaching methods and learning materials of human body anatomy ...
详细信息
ISBN:
(数字)9781728184081
ISBN:
(纸本)9781728184104
Anatomy is the branch of biological science in medical education that focuses on structured parts of living things, especially the human body. Traditional teaching methods and learning materials of human body anatomy are usually available in the form of textbooks with pictures and images or artificial anatomy mannequins. There are still not enough to help the students in understanding it with actual and accurate knowledge about our human body anatomy. It is because students are challenging in learning the human anatomy body part by through imagining it's real and lack of interaction and hard to understand with those 2D images model on the textbooks. Although there are artificial anatomy mannequins available for learning, it is limited in number and access. Technological developments, especially applications based on 3D, are expected to help the learning process of this science subject. In this study, we proposed to develop an augmented reality (AR) mobile application for learning human anatomy knee and foot through medical 3-dimensional (3D) reconstruction based on medical images. By using this application, students expected can easily understand human anatomy using 3D image visualisation on the mobile computing platform.
Whilst grading neurovascular abnormalities is critical for prompt surgical repair, no statistical markers are currently available for predicting the risk of adverse events, such as stroke, and the overall resilience o...
详细信息
Longitudinal observational and randomized controlled trials (RCT) are widely applied in biomedical behavioral studies and increasingly implemented in smart health systems. These trials frequently produce data that are...
详细信息
Ayurvedic means a science of life and well-being with its unique approaches to social and spiritual life. Especially in Sri Lanka we have our own set of rare Ayurvedic herbs which have been utilized by generations as ...
详细信息
ISBN:
(数字)9781728191058
ISBN:
(纸本)9781728191065
Ayurvedic means a science of life and well-being with its unique approaches to social and spiritual life. Especially in Sri Lanka we have our own set of rare Ayurvedic herbs which have been utilized by generations as medicinal treatments for a variety of diseases. Absence of specialists in this area makes proper identification as well as classification of valuable herbal plants a tedious task, which is essential for better treatment. Hence, a fully automated system for herb detection and classification, information visualization regarding them is highly desirable. There are existing applications which can identify plants with low prediction accuracies, as well as to give information regarding them. However, these applications are based on foreign plant data sets that do not include valuable herbs and shrubs with medicinal qualities. Hence this research proposes an application unique to medicinal plants, which can perform all these functionalities in both online and offline approach. Here, a new Ayurvedic plant dataset prepared from scratch, and preliminary results for classification of 5 types of herbs, compared with several deep Convolutional Neural Network (CNN) models based on transfer learning are presented. Experimental results indicate Marker-based Watershed algorithm as the best object detection algorithm in a complex background, VGG-16 as the best deep CNN classification model which reached a promising testing accuracy of 99.53%, and Seq2Seq LSTM model as the best deep learning model with optimum accuracy in abstractive information summarization.
Intravascular optical coherence tomography can be applied for high-resolution imaging in the coronary arteries with ischemic heart disease. The differentiation of the healthy and diseased vessel wall can be used to as...
详细信息
The particle therapy system simulation framework (PTSIM) is a Geant4 based Monte Carlo simulation software developed for radiation therapy. It has been continuously extending the functions to facilitate advanced resea...
详细信息
The particle therapy system simulation framework (PTSIM) is a Geant4 based Monte Carlo simulation software developed for radiation therapy. It has been continuously extending the functions to facilitate advanced researches in medical physics domain. Consequently, the PTSIM is used in many facilities for verification of treatment plans and quality assurances. In the PTSIM, various types of beam devices are provided as software components named “beam-modules”. The geometry is constructed using a class of the beam-module and the detail geometric parameters in the ASCII data format. This strategy contributed that allows the PTSIM users to easily find the beam-module from the categorized types of beam devices and to develop a rapid prototyping of treatment port in the simulation. However, radiation therapy facilities may introduce variants of existing beam-modules, that may require the implementation of a new class for the beam-module in the PTSIM. In order to respond to such requirements without any coding effort, the interface for the Geometry Description Markup Language (GDML) has been introduced in the PTSIM. The GDML is a specialized XML-based language for an application-independent persistent format. Therefore, it can describe a user-defined complex geometry and exchanging the geometry data file among different facilities. In addition, for the purpose of examining complex geometries, a new interface for the ParaView visualization software has been developed. The interface converts the geometry in the PTSIM to the structured points data in the VTK legacy format. This paper reports on the implementations and the usages of GDML and ParaView interfaces in the PTSIM.
biomedical document classification is a fundamental task in biomedical field. Existing methods do not make full use of the hierarchically semantic structures in biomedical documents which can be utilized to improve th...
详细信息
ISBN:
(数字)9781728108582
ISBN:
(纸本)9781728108599
biomedical document classification is a fundamental task in biomedical field. Existing methods do not make full use of the hierarchically semantic structures in biomedical documents which can be utilized to improve the performance of biomedical document classification. In this paper, according to the hierarchical structures in given biomedical documents, we propose two models for biomedical document classification, which are based on the semantically hierarchical attention mechanism. Specifically, we utilize a hierarchical attention mechanism to model biomedical documents, taking into account simultaneously multiple-level semantic relationships in documents. In addition, an adaptive cost sensitive learning method is proposed to address the data imbalance issue. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed methods.
Breast cancer therapy is particularly complex. Case-based reasoning (CBR) is an approach that can support clinicians when prescribing a therapy, and that is able to explain its recommendation to the clinicians. In a p...
详细信息
Breast cancer therapy is particularly complex. Case-based reasoning (CBR) is an approach that can support clinicians when prescribing a therapy, and that is able to explain its recommendation to the clinicians. In a previous work, we proposed a visual CBR approach for helping clinicians to choose a treatment between four main categories (e.g. surgery, chemotherapy). However, these are broad categories and clinicians need more details about the treatment, e.g. several surgeries exist such as lumpectomy. Here, we extend our visual CBR approach for fully supporting the therapy for breast cancer, using a hierarchical approach: first, decide the category, then decide the exact treatment, etc.
暂无评论