T. Karnowski, D. Aykac, L. Giancardo, Y. Li, T. Nichols, K. Fox, S. Garg, K. Tobin, E. Chaum
{"title":"Combining image and non-image data for automatic detection of retina disease in a telemedicine network","authors":"T. Karnowski, D. Aykac, L. Giancardo, Y. Li, T. Nichols, K. Fox, S. Garg, K. Tobin, E. Chaum","doi":"10.1109/BSEC.2011.5872320","DOIUrl":"https://doi.org/10.1109/BSEC.2011.5872320","url":null,"abstract":"A telemedicine network with retina cameras and automated quality control, physiological feature location, and lesion / anomaly detection is a low-cost way of achieving broad-based screening for diabetic retinopathy (DR) and other eye diseases. In the process of a routine eye-screening examination, other non-image data is often available which may be useful in automated diagnosis of disease. In this work, we report on the results of combining this non-image data with image data, using the protocol and processing steps of a prototype system for automated disease diagnosis of retina examinations from a telemedicine network. The system includes quality assessments, automated physiology detection, and automated lesion detection to create an archive of known cases. Non-image data such as diabetes onset date and hemoglobin A1c (HgA1c) for each patient examination are included as well, and the system is used to create a content-based image retrieval engine capable of automated diagnosis of disease into “normal” and “abnormal” categories. The system achieves a sensitivity and specificity of 91.2% and 71.6% using hold-one-out validation testing.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"471 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123449626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. McBride, X. Zhao, T. Nichols, T. Abdul-Ahad, M. Wilson, V. Vagnini, N. Munro, D. Berry, Y. Jiang
{"title":"Classification of traumatic brain injury using support vector machine analysis of event-related Tsallis entropy","authors":"J. McBride, X. Zhao, T. Nichols, T. Abdul-Ahad, M. Wilson, V. Vagnini, N. Munro, D. Berry, Y. Jiang","doi":"10.1109/BSEC.2011.5872318","DOIUrl":"https://doi.org/10.1109/BSEC.2011.5872318","url":null,"abstract":"An estimated 1.4 million Americans suffer from traumatic brain injury (TBI) each year [1]. Current methods of detecting TBI, such as computerized tomography (CT), magnetic resonance imaging (MRI), and Positron Emission Tomography (PET) scanning are time-consuming and expensive [2]. Here, the viability of a potentially more cost-effective means of detecting TBI is presented. Support vector machine (SVM) analyses are employed to classify 15 TBI and 15 normal individuals' EEG recordings taken during a working memory test. The features used by the SVM analyses include different sets of event-related Tsallis entropy functionals. The analyses demonstrate a strong correlation between the event-related functionals (ERFs) and the presence of TBI, attaining classification accuracies as high as 90%.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128573834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Determining toxicant bioavailability using a constitutively bioluminescent human cell line","authors":"Dan M. Close, Ruth Hahn, S. Ripp, G. Sayler","doi":"10.1109/BSEC.2011.5872321","DOIUrl":"https://doi.org/10.1109/BSEC.2011.5872321","url":null,"abstract":"Despite excessive expenditures by governments and private corporations, the toxicological effects of many chemicals and human relevant compounds are not well understood. Current methods for screening the toxicological effects of these chemicals are expensive, time consuming, and have been proven to produce results that must be interpreted with caution when extrapolating to human bioavailability and toxic impact. Here we demonstrate the use of a constitutively bioluminescent human HEK293 cell line expressing the genes of the bacterial luciferase gene cassette as a simple, low cost method for initial screening of toxic compounds. The autonomous nature of the bacterial bioluminescence cassette negates concerns over substrate addition, while providing a facile means for detection of reduced cellular growth or metabolism as a biomarker for toxic chemical exposure.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133991961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shannon P. Quinn, Richard Francis, C. Lo, C. Chennubhotla
{"title":"Novel use of differential image velocity invariants to categorize ciliary motion defects","authors":"Shannon P. Quinn, Richard Francis, C. Lo, C. Chennubhotla","doi":"10.1109/BSEC.2011.5872328","DOIUrl":"https://doi.org/10.1109/BSEC.2011.5872328","url":null,"abstract":"Primary ciliary dyskinesia (PCD) is a disorder characterized by sinopulmonary disease arising from ciliary motion defects in respiratory epithelia. An essential first step in the diagnostic evaluation of PCD is the use of high-speed videomicroscopy to analyze ciliary beat patterns in nasal epithelia biopsies. This includes a quantitative assessment of ciliary beat frequency (CBF, where CBF of < 11 Hz is referred to further diagnosis), followed by a visual examination of ciliary beat patterns to detect the presence of dyskinetic motions, such as stiff, incomplete, wavy and others. Both procedures lack standardized protocols, hence CBF is often counted manually by observing the ciliary image frames in slow motion, while a manual examination of beat patterns is subjective, cumbersome, and error-prone. We are building automated image analysis methods to address this problem. To this end, we report the use of image velocities for measuring CBF and demonstrate the effectiveness of the differential image velocity invariants, curl and deformation, in deconvolving the various motion defects.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127505538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Boosting text extraction from biomedical images using text region detection","authors":"Songhua Xu, M. Krauthammer","doi":"10.1109/BSEC.2011.5872319","DOIUrl":"https://doi.org/10.1109/BSEC.2011.5872319","url":null,"abstract":"In this paper, we show that domain-optimized text detection in biomedical images is important for boosting text extraction recall via off-the-shelf OCR engines. Methodologically, we contrast OCR performance when processing raw biomedical images, compared to preprocessing those images, and performing OCR on detected image text regions only. To quantify OCR extraction results, we rely on a gold standard image text corpus with manually identified image text strings. To demonstrate the positive effect on biomedical image retrieval, we apply image text detection and extraction to a large corpus of biomedical images in the Yale Image Finder system. We show that improved text extraction results in the retrieval of a larger number of relevant images for a set of domain-relevant keyword searches.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"427 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133357516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Zielinski, A. Zielińska, N. Bouaynaya, Justin G. Vaughan, M. Smeltzer
{"title":"Automated biofilm region recognition and morphology quantification from confocal laser scanning microscopy imaging","authors":"J. Zielinski, A. Zielińska, N. Bouaynaya, Justin G. Vaughan, M. Smeltzer","doi":"10.1109/BSEC.2011.5872327","DOIUrl":"https://doi.org/10.1109/BSEC.2011.5872327","url":null,"abstract":"Staphylococcus aureus is an opportunistic human pathogen and a primary cause of nosocomial infections. Its biofilm forming capability is an adaptation strategy utilized by many species of bacteria to overcome stressful environmental conditions and provides both resistance to antimicrobial treatments and protection from the host immune system. This paper addresses a growing demand for an objective, fully automated method of biofilm structure description with standardized parameters that are independent of user input. In this study, we used watershed segmentation to analyze and compare confocal laser scanning microscopy (CLSM) images of two S. aureus strains with different biofilm-forming capabilities. Results are compared with manual calculations as well as the commonly used COMSTAT software.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131573695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cycle detection in speech breathing signals","authors":"Cheng Li, D. Parham, Yanwu Ding","doi":"10.1109/BSEC.2011.5872314","DOIUrl":"https://doi.org/10.1109/BSEC.2011.5872314","url":null,"abstract":"As with any physiological process, breathing behaviors can be represented by time-varying signals. Speech breathing, or breathing behavior that supports speech production, is one particular type of breathing that can be difficult and time-consuming to analyze visually. In this paper, we introduce a novel cycle identification algorithm using MATLAB programming that automatically identifies breath cycles in speech breathing signals. The results of simulations have shown that the proposed algorithm can identify breath cycles correctly and efficiently despite the complexity of speech breathing signals. The use of this algorithm can help researchers and clinicians more easily identify and analyze cycles associated with speech breathing.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127506907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Exploring the potential of collaborative filtering for user-adaptive mammography education","authors":"M. Mazurowski, G. Tourassi","doi":"10.1109/BSEC.2011.5872325","DOIUrl":"https://doi.org/10.1109/BSEC.2011.5872325","url":null,"abstract":"Specialized training in breast imaging is critical to ensure high diagnostic accuracy of the radiologists who read screening mammograms in their daily practice. Previously, we proposed a framework for an individualized computer-aided mammography training system as a time-efficient and effective support for radiology education. The system utilizes the concept of user modeling to adapt the training protocol to meet the individual needs of the radiologists-in-training. User models are derived to predict the difficulty that a previously unseen case will pose to the modeled user. Constructing accurate models of the trainees is crucial for the overall effectiveness of the proposed training. In this paper we explore the potential of collaborative filtering for this task. Collaborative filtering is based on the assumption that the relation between ratings of different users or between ratings of different items observed for previous items will translate to new items and users. In the context of radiology trainee modeling we use this approach to predict errors that the trainees will make for unseen cases. These predicted errors can serve as the basis to identify challenging cases that are expected to be more beneficial when included in the training of a given trainee. We performed an experimental evaluation of the algorithm using data collected at Duke University Medical Center from 10 radiology residents for the problem of determining the malignancy status of masses based on their mammographic appearance. Our experiments showed that the collaborative filtering algorithm is able to distinguish cases of high and low difficulty and therefore demonstrated the promise of this approach in building adaptive computer-aided educational systems in radiology education.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127971130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Elizabeth Vargis, C. Webb, B. Paria, K. Bennett, J. Reese, A. Al-Hendy, A. Mahadevan-Jansen
{"title":"Detecting changes during pregnancy with Raman spectroscopy","authors":"Elizabeth Vargis, C. Webb, B. Paria, K. Bennett, J. Reese, A. Al-Hendy, A. Mahadevan-Jansen","doi":"10.1117/12.843005","DOIUrl":"https://doi.org/10.1117/12.843005","url":null,"abstract":"Preterm labor is the second leading cause of neonatal mortality and leads to a myriad of complications like delayed development and cerebral palsy. Currently, there is no way to accurately predict preterm labor, making its prevention and treatment virtually impossible. While there are some at-risk patients, over half of all preterm births do not fall into any high-risk category. This study seeks to predict and prevent preterm labor by using Raman spectroscopy to detect changes in the cervix during pregnancy. Since Raman spectroscopy has been used to detect cancers in vivo in organs like the cervix and skin, it follows that spectra will change over the course of pregnancy. Previous studies have shown that fluorescence decreased during pregnancy and increased during post-partum exams to pre-pregnancy levels. We believe significant changes will occur in the Raman spectra obtained during the course of pregnancy. In this study, Raman spectra from the cervix of pregnant mice will be acquired. Specific changes that occur due to cervical softening or changes in hormonal levels will be observed to understand the changes that occur before and after labor in the cervix.","PeriodicalId":377652,"journal":{"name":"Proceedings of the 2011 Biomedical Sciences and Engineering Conference: Image Informatics and Analytics in Biomedicine","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125872114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}