IU Indianapolis ScholarWorks :: Browsing by Subject "Visualization"

Browsing by Subject "Visualization"

Now showing 1 - 10 of 12

Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation
(IEEE, 2021) Jing, Taotao; Ding, Zhengming; Electrical and Computer Engineering, School of Engineering and Technology
Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. Conventional UDA concentrates on extracting domain-invariant features through deep adversarial networks. However, most of them seek to match the different domain feature distributions, without considering the task-specific decision boundaries across various classes. In this paper, we propose a novel Adversarial Dual Distinct Classifiers Network (AD 2 CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries. To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment. Moreover, we naturally design two different structure classifiers to identify the unlabeled target samples over the supervision of the labeled source domain data. Such dual distinct classifiers with various architectures can capture diverse knowledge of the target data structure from different perspectives. Extensive experimental results on several cross-domain visual benchmarks prove the model's effectiveness by comparing it with other state-of-the-art UDA.
Brain explorer for connectomic analysis
(Springer, 2017-08-23) Li, Huang; Fang, Shiaofen; Contreras, Joey A.; West, John D.; Risacher, Shannon L.; Wang, Yang; Sporns, Olaf; Saykin, Andrew J.; Goñi, Joaquín; Shen, Li; Radiology and Imaging Sciences, School of Medicine
Visualization plays a vital role in the analysis of multimodal neuroimaging data. A major challenge in neuroimaging visualization is how to integrate structural, functional, and connectivity data to form a comprehensive visual context for data exploration, quality control, and hypothesis discovery. We develop a new integrated visualization solution for brain imaging data by combining scientific and information visualization techniques within the context of the same anatomical structure. In this paper, new surface texture techniques are developed to map non-spatial attributes onto both 3D brain surfaces and a planar volume map which is generated by the proposed volume rendering technique, spherical volume rendering. Two types of non-spatial information are represented: (1) time series data from resting-state functional MRI measuring brain activation; (2) network properties derived from structural connectivity data for different groups of subjects, which may help guide the detection of differentiation features. Through visual exploration, this integrated solution can help identify brain regions with highly correlated functional activations as well as their activation patterns. Visual detection of differentiation features can also potentially discover image-based phenotypic biomarkers for brain diseases.
Collaborative Visualization Workshop: Engaging People, Perspectives, and Values
(Design Research Society, 2009-08-29) Kooi, Lee van der; Napier, Pamela
During this workshop participants will gain experience through doing collaborative visualization in a team to articulate values and perpectives, and connect facts, thoughts and ideas. They will develop a shared understanding of how their own personal values connect to a design process and the larger social, economic and environmental contexts in which design decisions are made.
Concept embedding-based weighting scheme for biomedical text clustering and visualization
(BioMed Central, 2018-11-01) Luo, Xiao; Shah, Setu; Computer Information and Graphics Technology, School of Engineering and Technology
Biomedical text clustering is a text mining technique used to provide better document search, browsing, and retrieval in biomedical and clinical text collections. In this research, the document representation based on the concept embedding along with the proposed weighting scheme is explored. The concept embedding is learned through the neural networks to capture the associations between the concepts. The proposed weighting scheme makes use of the concept associations to build document vectors for clustering. We evaluate two types of concept embedding and new weighting scheme for text clustering and visualization on two different biomedical text collections. The returned results demonstrate that the concept embedding along with the new weighting scheme performs better than the baseline tf–idf for clustering and visualization. Based on the internal clustering evaluation metric-Davies–Bouldin index and the visualization, the concept embedding generated from aggregated word embedding can form well-separated clusters, whereas the intact concept embedding can better identify more clusters of specific diseases and gain better F-measure.
Critical Assessment of Single-Use Ureteroscopes in an In Vivo Porcine Model
(Hindawi, 2020-04-27) Ceballos, Brian; Nottingham, Charles U.; Bechis, Seth K.; Sur, Roger L.; Matlaga, Brian R.; Krambeck, Amy E.; Urology, School of Medicine
Methods A female pig was placed under general anesthesia and positioned supine, and retrograde access to the renal collecting system was obtained. The LithoVue (Boston Scientific) and Uscope (Pusen Medical) were evaluated by three experienced surgeons, and each surgeon started with a new scope. The following parameters were compared between each ureteroscope: time for navigation to upper and lower pole calyces with and without implements (1.9 F basket, 200 μm laser fiber, and 365 μm laser fiber for upper only) in the working channel and subjective evaluations of maneuverability, irrigant flow through the scope, lever force, ergonomics, and scope optics. Results Navigation to the lower pole calyx was significantly faster with LithoVue compared to Uscope when the working channel was empty (24.3 vs. 49.4 seconds, p < 0.01) and with a 200 μm fiber (63.6 vs. 94.4 seconds, p=0.04), but not with the 1.9 F basket. Navigation to the upper pole calyx was similar for all categories except faster with LithoVue containing the 365 μm fiber (67.1 vs. 99.7 seconds, p=0.02). Subjective assessments of scope maneuverability to upper and lower pole calyces when the scope was empty and with implements favored LithoVue in all categories, as did assessments of irrigant flow, illumination, image quality, and field of view. Both scopes had similar scores of lever force and ergonomics. Conclusions In an in vivo porcine model, the type of single-use ureteroscope employed affected the navigation times and subjective assessments of maneuverability and visualization. In all cases, LithoVue provided either equivalent or superior metrics than Uscope. Further clinical studies are necessary to determine the implications of these findings.
Integrated Visualization of Human Brain Connectome Data
(Springer, 2015-08) Li, Huang; Fang, Shiaofen; Goni, Joaquin; Contreras, Joey A.; Liang, Yanhua; Cai, Chengtao; West, John D.; Risacher, Shannon L.; Wang, Yang; Sporns, Olaf; Saykin, Andrew J.; Shen, Li; Department of Radiology and Imaging Sciences, IU School of Medicine
Visualization plays a vital role in the analysis of multi-modal neuroimaging data. A major challenge in neuroimaging visualization is how to integrate structural, functional and connectivity data to form a comprehensive visual context for data exploration, quality control, and hypothesis discovery. We develop a new integrated visualization solution for brain imaging data by combining scientific and information visualization techniques within the context of the same anatomic structure. New surface texture techniques are developed to map non-spatial attributes onto the brain surfaces from MRI scans. Two types of non-spatial information are represented: (1) time-series data from resting-state functional MRI measuring brain activation; (2) network properties derived from structural connectivity data for different groups of subjects, which may help guide the detection of differentiation features. Through visual exploration, this integrated solution can help identify brain regions with highly correlated functional activations as well as their activation patterns. Visual detection of differentiation features can also potentially discover image based phenotypic biomarkers for brain diseases.
A patient-oriented clinical decision support system for CRC risk assessment and preventative care
(BioMed Central, 2018-12-07) Liu, Jiannan; Li, Chenyang; Xu, Jing; Wu, Huanmei; Biohealth Informatics, School of Informatics and Computing
Colorectal Cancer (CRC) is the third leading cause of cancer death among men and women in the United States. Research has shown that the risk of CRC associates with genetic and lifestyle factors. It is possible to prevent or minimize certain CRC risks by adopting a healthy lifestyle. Existing Clinical Decision Support Systems (CDSS) mainly targeted physicians as the CDSS users. As a result, the availability of patient-oriented CDSS is limited. Our project is to develop patient-oriented CDSS for active CRC management.
Quantifiable Soft Tissue Manipulation (QSTM™) – A novel modality to improve clinical manual therapy with objective metrics
(IEEE Xplore, 2021-11) Bhattacharjee, Abhinaba; Chien, Stanley Y. P.; Anwar, Sohel; Loghmani, Mary. T.; Physical Therapy, School of Health & Human Sciences
Soft Tissue Manipulation (STM), a form of mechanotherapy, offers a clinical modality to examine and treat Neuromusculoskeletal (NMS) pain disorders and dysfunction. The, current STM practice is mostly subjective and reliant on anecdotal patient feedback and lacks quantification with objective metrics. This paper proposes Quantifiable Soft Tissue Manipulation (QSTM™), a sensor based computerized technological advancement in Soft tissue examination and treatment enabling new standard of practice in manual therapy. This novel medical device technology aims to produce optimum STM prescriptions using ergonomic, portable, handheld medical tools with specially contoured tips designed to palpate and assess tissue anomalies of specific musculoskeletal conditions. QSTM™ captures three–dimensional forces and motion of the mechatronic handheld tools to quantify STM treatment parameters, such as (resultant force, force application angle, rate, direction, and treatment time). Clinical practice using QSTM™ facilitates real-time visual feedback of treatment metrics and subsequent treatment documentation for comparison and analysis on a Windows based computer software (Q-Ware©). Pre-clinical testing using the QSTM™ medical device system clearly identifies inconsistencies among practitioners and distinguishes STM practice variabilities. Thus, QSTM™ is an apt tool for soft tissue treatment assessment, analysis, and individualized prescriptions for targeted STM dosing and commercialization.
The role of visualization and 3-D printing in biological data mining
(Springer (Biomed Central Ltd.), 2015) Weiss, Talia L.; Zieselman, Amanda; Hill, Douglas P.; Diamond, Solomon G.; Shen, Li; Saykin, Andrew J.; Moore, Jason H.; Alzheimer’s Disease Neuroimaging Initiative; Department of Radiology and Imaging Sciences, IU School of Medicine
BACKGROUND: Biological data mining is a powerful tool that can provide a wealth of information about patterns of genetic and genomic biomarkers of health and disease. A potential disadvantage of data mining is volume and complexity of the results that can often be overwhelming. It is our working hypothesis that visualization methods can greatly enhance our ability to make sense of data mining results. More specifically, we propose that 3-D printing has an important role to play as a visualization technology in biological data mining. We provide here a brief review of 3-D printing along with a case study to illustrate how it might be used in a research setting. RESULTS: We present as a case study a genetic interaction network associated with grey matter density, an endophenotype for late onset Alzheimer's disease, as a physical model constructed with a 3-D printer. The synergy or interaction effects of multiple genetic variants were represented through a color gradient of the physical connections between nodes. The digital gene-gene interaction network was then 3-D printed to generate a physical network model. CONCLUSIONS: The physical 3-D gene-gene interaction network provided an easily manipulated, intuitive and creative way to visualize the synergistic relationships between the genetic variants and grey matter density in patients with late onset Alzheimer's disease. We discuss the advantages and disadvantages of this novel method of biological data mining visualization.
Towards Fair Cross-Domain Adaptation via Generative Learning
(IEEE, 2021) Wang, Tongxin; Ding, Zhengming; Shao, Wei; Tang, Haixu; Huang, Kun; Medicine, School of Medicine
Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. Existing DA normally assumes the well-labeled source domain is class-wise balanced, which means the size per source class is relatively similar. However, in real-world applications, labeled samples for some categories in the source domain could be extremely few due to the difficulty of data collection and annotation, which leads to decreasing performance over target domain on those few-shot categories. To perform fair cross-domain adaptation and boost the performance on these minority categories, we develop a novel Generative Few-shot Cross-domain Adaptation (GFCA) algorithm for fair cross-domain classification. Specifically, generative feature augmentation is explored to synthesize effective training data for few-shot source classes, while effective cross-domain alignment aims to adapt knowledge from source to facilitate the target learning. Experimental results on two large cross-domain visual datasets demonstrate the effectiveness of our proposed method on improving both few-shot and overall classification accuracy comparing with the state-of-the-art DA approaches.

Browsing by Subject "Visualization"

Results Per Page

Sort Options