The Experts below are selected from a list of 297 Experts worldwide ranked by ideXlab platform
Bin Zheng - One of the best experts on this subject based on the ideXlab platform.
-
optimization of Reference Library used in content based medical image retrieval scheme
Medical Physics, 2007Co-Authors: Sang Cheol Park, Rahul Sukthankar, Lily Mummert, M Satyanarayanan, Bin ZhengAbstract:Building an optimal image Reference Library is a critical step in developing the interactive computer-aided detection and diagnosis (I-CAD) systems of medical images using content-based image retrieval (CBIR) schemes. In this study, the authors conducted two experiments to investigate (1) the relationship between I-CAD performance and size of Reference Library and (2) a new Reference selection strategy to optimize the Library and improve I-CAD performance. The authors assembled a Reference Library that includes 3153 regions of interest (ROI) depicting either malignant masses (1592) or CAD-cued false-positive regions (1561) and an independent testing data set including 200 masses and 200 false-positive regions. A CBIR scheme using a distance-weighted K-nearest neighbor algorithm is applied to retrieve References that are considered similar to the testing sample from the Library. The area under receiver operating characteristic curve (A{sub z}) is used as an index to evaluate the I-CAD performance. In the first experiment, the authors systematically increased Reference Library size and tested I-CAD performance. The result indicates that scheme performance improves initially from A{sub z}=0.715 to 0.874 and then plateaus when the Library size reaches approximately half of its maximum capacity. In the second experiment, based on the hypothesis that a ROI should bemore » removed if it performs poorly compared to a group of similar ROIs in a large and diverse Reference Library, the authors applied a new strategy to identify 'poorly effective' References. By removing 174 identified ROIs from the Reference Library, I-CAD performance significantly increases to A{sub z}=0.914 (p<0.01). The study demonstrates that increasing Reference Library size and removing poorly effective References can significantly improve I-CAD performance.« less
-
Optimization of Reference Library used in content‐based medical image retrieval scheme
Medical Physics, 2007Co-Authors: Sang Cheol Park, Rahul Sukthankar, Lily Mummert, M Satyanarayanan, Bin ZhengAbstract:Building an optimal image Reference Library is a critical step in developing the interactive computer-aided detection and diagnosis (I-CAD) systems of medical images using content-based image retrieval (CBIR) schemes. In this study, the authors conducted two experiments to investigate (1) the relationship between I-CAD performance and size of Reference Library and (2) a new Reference selection strategy to optimize the Library and improve I-CAD performance. The authors assembled a Reference Library that includes 3153 regions of interest (ROI) depicting either malignant masses (1592) or CAD-cued false-positive regions (1561) and an independent testing data set including 200 masses and 200 false-positive regions. A CBIR scheme using a distance-weighted K-nearest neighbor algorithm is applied to retrieve References that are considered similar to the testing sample from the Library. The area under receiver operating characteristic curve (A{sub z}) is used as an index to evaluate the I-CAD performance. In the first experiment, the authors systematically increased Reference Library size and tested I-CAD performance. The result indicates that scheme performance improves initially from A{sub z}=0.715 to 0.874 and then plateaus when the Library size reaches approximately half of its maximum capacity. In the second experiment, based on the hypothesis that a ROI should bemore » removed if it performs poorly compared to a group of similar ROIs in a large and diverse Reference Library, the authors applied a new strategy to identify 'poorly effective' References. By removing 174 identified ROIs from the Reference Library, I-CAD performance significantly increases to A{sub z}=0.914 (p
-
interactive computer aided diagnosis of breast masses computerized selection of visually similar image sets from a Reference Library
Academic Radiology, 2007Co-Authors: Bin Zheng, Claudia Mellothoms, Xiao Hui Wang, Gordon S Abrams, Jules H Sumkin, Denise M Chough, Marie A Ganott, Amy LuAbstract:Rationale and Objectives The clinical utility of interactive computer-aided diagnosis (ICAD) systems depends on clinical relevance and visual similarity between the queried breast lesions and the ICAD-selected Reference regions. The objective of this study is to develop and test a new ICAD scheme that aims improve visual similarity of ICAD-selected Reference regions. Materials and Methods A large and diverse Reference Library involving 3,000 regions of interests was established. For each queried breast mass lesion by the observer, the ICAD scheme segments the lesion, classifies its boundary spiculation level, and computes 14 image features representing the segmented lesion and its surrounding tissue background. A conditioned k-nearest neighbor algorithm is applied to select a set of the 25 most “similar” lesions from the Reference Library. After computing the mutual information between the queried lesion and each of these initially selected 25 lesions, the scheme displays the six Reference lesions with the highest mutual information scores. To evaluate the automated selection process of the six “visually similar” lesions to the queried lesion, we conducted a two-alternative forced-choice observer pReference study using 85 queried mass lesions. Two sets of Reference lesions selected by one new automated ICAD scheme and the other previously reported scheme using a subjective rating method were randomly displayed on the left and right side of the queried lesion. Nine observers were asked to decide for each of the 85 queried lesions which one of the two Reference sets was “more visually similar” to the queried lesion. Results In classification of mass boundary spiculation levels, the overall agreement rate between the automated scheme and an observer is 58.8% (Kappa = 0.31). In observer pReference study, the nine observers preferred on average the Reference lesion sets selected by the automated scheme as being more visually similar than the set selected by the subjective rating approach in 53.2% of the queried lesions. The results were not significantly different for the two methods ( P = .128). Conclusions This study suggests that using the new automated ICAD scheme, the interobserver variability related issues can thus be avoided. Furthermore, the new scheme maintains the similar performance level as the previous scheme using the subjective rating method that can select Reference sets that are significantly more visually similar ( P
Zoe Fisher - One of the best experts on this subject based on the ideXlab platform.
-
LibGuides. Database Tips: Gale Virtual Reference Library Database. What is Gale Virtual Reference Library?.
2010Co-Authors: Zoe FisherAbstract:LibGuides. Database Tips: Gale Virtual Reference Library Database. What is Gale Virtual Reference Library?.
-
LibGuides. Database Tips: Gale Virtual Reference Library Database. Search Within Only One Book.
2010Co-Authors: Zoe FisherAbstract:LibGuides. Database Tips: Gale Virtual Reference Library Database. Search Within Only One Book.
Sang Cheol Park - One of the best experts on this subject based on the ideXlab platform.
-
optimization of Reference Library used in content based medical image retrieval scheme
Medical Physics, 2007Co-Authors: Sang Cheol Park, Rahul Sukthankar, Lily Mummert, M Satyanarayanan, Bin ZhengAbstract:Building an optimal image Reference Library is a critical step in developing the interactive computer-aided detection and diagnosis (I-CAD) systems of medical images using content-based image retrieval (CBIR) schemes. In this study, the authors conducted two experiments to investigate (1) the relationship between I-CAD performance and size of Reference Library and (2) a new Reference selection strategy to optimize the Library and improve I-CAD performance. The authors assembled a Reference Library that includes 3153 regions of interest (ROI) depicting either malignant masses (1592) or CAD-cued false-positive regions (1561) and an independent testing data set including 200 masses and 200 false-positive regions. A CBIR scheme using a distance-weighted K-nearest neighbor algorithm is applied to retrieve References that are considered similar to the testing sample from the Library. The area under receiver operating characteristic curve (A{sub z}) is used as an index to evaluate the I-CAD performance. In the first experiment, the authors systematically increased Reference Library size and tested I-CAD performance. The result indicates that scheme performance improves initially from A{sub z}=0.715 to 0.874 and then plateaus when the Library size reaches approximately half of its maximum capacity. In the second experiment, based on the hypothesis that a ROI should bemore » removed if it performs poorly compared to a group of similar ROIs in a large and diverse Reference Library, the authors applied a new strategy to identify 'poorly effective' References. By removing 174 identified ROIs from the Reference Library, I-CAD performance significantly increases to A{sub z}=0.914 (p<0.01). The study demonstrates that increasing Reference Library size and removing poorly effective References can significantly improve I-CAD performance.« less
-
Optimization of Reference Library used in content‐based medical image retrieval scheme
Medical Physics, 2007Co-Authors: Sang Cheol Park, Rahul Sukthankar, Lily Mummert, M Satyanarayanan, Bin ZhengAbstract:Building an optimal image Reference Library is a critical step in developing the interactive computer-aided detection and diagnosis (I-CAD) systems of medical images using content-based image retrieval (CBIR) schemes. In this study, the authors conducted two experiments to investigate (1) the relationship between I-CAD performance and size of Reference Library and (2) a new Reference selection strategy to optimize the Library and improve I-CAD performance. The authors assembled a Reference Library that includes 3153 regions of interest (ROI) depicting either malignant masses (1592) or CAD-cued false-positive regions (1561) and an independent testing data set including 200 masses and 200 false-positive regions. A CBIR scheme using a distance-weighted K-nearest neighbor algorithm is applied to retrieve References that are considered similar to the testing sample from the Library. The area under receiver operating characteristic curve (A{sub z}) is used as an index to evaluate the I-CAD performance. In the first experiment, the authors systematically increased Reference Library size and tested I-CAD performance. The result indicates that scheme performance improves initially from A{sub z}=0.715 to 0.874 and then plateaus when the Library size reaches approximately half of its maximum capacity. In the second experiment, based on the hypothesis that a ROI should bemore » removed if it performs poorly compared to a group of similar ROIs in a large and diverse Reference Library, the authors applied a new strategy to identify 'poorly effective' References. By removing 174 identified ROIs from the Reference Library, I-CAD performance significantly increases to A{sub z}=0.914 (p
Hans H Maurer - One of the best experts on this subject based on the ideXlab platform.
-
Towards a universal LC–MS screening procedure – can an LIT LC–MSn screening approach and Reference Library be used on a quadrupole‐LIT hybrid instrument?
Journal of Mass Spectrometry, 2020Co-Authors: Dirk K Wissenbach, Markus R Meyer, Armin A Weber, Daniela Remane, Andreas H Ewald, Frank T Peters, Hans H MaurerAbstract:In contrast to libraries with highly reproducible gas chromatography electron ionization mass spectra, current liquid chromatography (LC–MS) libraries are limited to specific instrument types. Therefore, the aim of the study was to prove whether a recently developed linear ion trap (LIT) LC–MSn screening approach and Reference Library can be transferred to an LC–MS/MS system with a quadrupole-LIT hybrid mass analyzer using SmileMS, a sophisticated search algorithm. The LIT Reference Library was built with MS² and MS³ wideband spectra recorded on a ThermoFisher LXQ LIT with electrospray ionization in positive mode and full-scan data-dependent acquisition (DDA). Collision parameter optimizations, including different scan types and energies, were performed on an Applied Biosystems QTRAP 4000 system using electrospray ionization in positive mode and full-scan DDA. Modified Library sets were generated to improve the detection of a compound by the used search algorithm. Additionally, 100 authentic human urine samples were screened by both systems for proof of applicability. In the applicability study, 533 compounds were detected by the LXQ and 477 by the QTRAP system using enhanced product ion scan and a modified database. The presented data showed that the LIT screening approach and Reference Library could be used successfully on a QTRAP instrument with some limitations. These should be overcome by further optimizations regarding DDA settings for better sensitivity and further Library modifications to reduce spectra mismatches. Copyright © 2012 John Wiley & Sons, Ltd.
-
towards a universal lc ms screening procedure can an lit lc msn screening approach and Reference Library be used on a quadrupole lit hybrid instrument
Journal of Mass Spectrometry, 2012Co-Authors: Dirk K Wissenbach, Markus R Meyer, Armin A Weber, Daniela Remane, Andreas H Ewald, Frank T Peters, Hans H MaurerAbstract:In contrast to libraries with highly reproducible gas chromatography electron ionization mass spectra, current liquid chromatography (LC–MS) libraries are limited to specific instrument types. Therefore, the aim of the study was to prove whether a recently developed linear ion trap (LIT) LC–MSn screening approach and Reference Library can be transferred to an LC–MS/MS system with a quadrupole-LIT hybrid mass analyzer using SmileMS, a sophisticated search algorithm. The LIT Reference Library was built with MS² and MS³ wideband spectra recorded on a ThermoFisher LXQ LIT with electrospray ionization in positive mode and full-scan data-dependent acquisition (DDA). Collision parameter optimizations, including different scan types and energies, were performed on an Applied Biosystems QTRAP 4000 system using electrospray ionization in positive mode and full-scan DDA. Modified Library sets were generated to improve the detection of a compound by the used search algorithm. Additionally, 100 authentic human urine samples were screened by both systems for proof of applicability. In the applicability study, 533 compounds were detected by the LXQ and 477 by the QTRAP system using enhanced product ion scan and a modified database. The presented data showed that the LIT screening approach and Reference Library could be used successfully on a QTRAP instrument with some limitations. These should be overcome by further optimizations regarding DDA settings for better sensitivity and further Library modifications to reduce spectra mismatches. Copyright © 2012 John Wiley & Sons, Ltd.
Nicolas Hubert - One of the best experts on this subject based on the ideXlab platform.
-
assessing species diversity of coral triangle artisanal fisheries a dna barcode Reference Library for the shore fishes retailed at ambon harbor indonesia
Ecology and Evolution, 2020Co-Authors: Gino V Limmon, Erwan Delrieutrottin, Jesaya Patikawa, Frederik Rijoly, Hadi Dahruddin, Frederic Busson, Dirk Steinke, Nicolas HubertAbstract:The Coral Triangle (CT), a region spanning across Indonesia and Philippines, is home to about 4,350 marine fish species and is among the world's most emblematic regions in terms of conservation. Threatened by overfishing and oceans warming, the CT fisheries have faced drastic declines over the last decades. Usually monitored through a biomass-based approach, fisheries trends have rarely been characterized at the species level due to the high number of taxa involved and the difficulty to accurately and routinely identify individuals to the species level. Biomass, however, is a poor proxy of species richness, and automated methods of species identification are required to move beyond biomass-based approaches. Recent meta-analyses have demonstrated that species richness peaks at intermediary levels of biomass. Consequently, preserving biomass is not equal to preserving biodiversity. We present the results of a survey to estimate the shore fish diversity retailed at the harbor of Ambon Island, an island located at the center of the CT that display exceptionally high biomass despite high levels of threat, while building a DNA barcode Reference Library of CT shore fishes targeted by artisanal fisheries. We sampled 1,187 specimens and successfully barcoded 696 of the 760 selected specimens that represent 202 species. Our results show that DNA barcodes were effective in capturing species boundaries for 96% of the species examined, which opens new perspectives for the routine monitoring of the CT fisheries.
-
A DNA barcode Reference Library of French Polynesian shore fishes
Scientific Data, 2019Co-Authors: Erwan Delrieu-trottin, Jeffrey T. Williams, Diane Pitassy, Amy C. Driskell, Nicolas Hubert, Jeremie Viviani, Thomas H. Cribb, Benoit Espiau, R. Galzin, Michel KulbickiAbstract:The emergence of DNA barcoding and metabarcoding opened new ways to study biological diversity, however, the completion of DNA barcode libraries is fundamental for such approaches to succeed. This dataset is a DNA barcode Reference Library (fragment of Cytochrome Oxydase I gene) for 2,190 specimens representing at least 540 species of shore fishes collected over 10 years at 154 sites across the four volcanic archipelagos of French Polynesia; the Austral, Gambier, Marquesas and Society Islands, a 5,000,000 km(2) area. At present, 65% of the known shore fish species of these archipelagoes possess a DNA barcode associated with preserved, photographed, tissue sampled and cataloged specimens, and extensive collection locality data. This dataset represents one of the most comprehensive DNA barcoding efforts for a vertebrate fauna to date. Considering the challenges associated with the conservation of coral reef fishes and the difficulties of accurately identifying species using morphological characters, this publicly available Library is expected to be helpful for both authorities and academics in various fields.
-
A DNA barcode Reference Library of the French Polynesian shore fishes
bioRxiv, 2019Co-Authors: Erwan Delrieu-trottin, Jeffrey T. Williams, Diane Pitassy, Amy C. Driskell, Nicolas Hubert, Jeremie Viviani, Thomas H. Cribb, Benoit Espiau, R. Galzin, Michel KulbickiAbstract:The emergence of DNA barcoding and metabarcoding opened new ways to study biological diversity, however, the completion of DNA barcode libraries is fundamental for such approaches to succeed. This dataset is a DNA barcode Reference Library (fragment of Cytochrome Oxydase I gene) for 2,190 specimens representing at least 540 species of shore fishes collected over 10 years at 154 sites across the four volcanic archipelagos of French Polynesia; the Austral, Gambier, Marquesas and Society Islands, a 5,000,000 km 2 area. At present, 65% of the known shore fish species of these archipelagoes possess a DNA barcode associated with preserved, photographed, tissue sampled and cataloged specimens, and extensive collection locality data. This dataset represents one of the most comprehensive DNA barcoding efforts for a vertebrate fauna to date. Considering the challenges associated with the conservation of coral reef fishes and the difficulties of accurately identifying species using morphological characters, this publicly available Library is expected to be helpful for both authorities and academics in various fields.