检索结果-内蒙古大学图书馆

Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists

引用

ANNALS OF ONCOLOGY 2018年第8期29卷 1836-1842页

作者： Haenssle, H. A. Fink, C. Schneiderbauer, R. Toberer, F. Buhl, T. Blum, A. Kalloo, A. Hassens, A. Ben Hadj Thomas, L. Enk, A. Uhlmann, L. Heidelberg Univ Dept Dermatol Neuenheimer Feld 440 D-69120 Heidelberg Germany Univ Gottingen Dept Dermatol Gottingen Germany Off Based Clin Dermatol Constance Germany Mem Sloan Kettering Canc Ctr Dept Med Dermatol Serv New York NY 10021 USA Univ Passau Fac Comp Sci & Math Passau Germany Lyon 1 Univ Dept Dermatol Lyons Canc Res Ctr Lyon France Heidelberg Univ Inst Med Biometry & Informat Heidelberg Germany

Background: Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking. Methods: Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only;level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge. Results: In level-I dermatologists achieved a mean (6standard deviation) sensitivity and specificity for lesion classification of 86.6% (69.3%) and 71.3% (611.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (69.6%, P = 0.19) and specificity to 75.7% (611.7%, P<0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P<0.01) and level-II (75.7%, P<0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P<0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge. Conclusions: For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatolog

关键词： melanoma melanocytic nevi dermoscopy deep learning convolutional neural network computer algorithm automated melanoma detection

来源：评论

学校读者我要写书评

暂无评论

An interactive algorithm for the assessment of cumulative cortisol suppression during inhaled corticosteroid therapy

引用

AAPS PHARMSCI 2000年第3期2卷 art.no.-22页

作者： Krishnaswami, S Hochhaus, G Derendorf, H Univ Florida Coll Pharm Dept Pharmaceut Gainesville FL 32610 USA

The objective of the study was to develop an algorithm based on a pharmacokinetic-pharmacodynamic (PK/PD) modeling approach to quantify and predict cumulative cortisol suppression (CCS) as a surrogate marker for the systemic activity of inhaled corticosteroid therapy. Two Excel spreadsheets, one for single dose and another for steady-state multiple doses of inhaled steroids, were developed for predicting CCS. Four of the commonly used inhaled steroids were chosen for the purposes of simulation: fluticasone propionate (FP), budesonide (BUD), flunisolide (FLU), and triamcinolone acetonide (TAA). Drug-specific PK and PD parameters were obtained from previous single- and multiple-dose studies. In cases in which multiple-dose data were not available, the single-dose data were extrapolated. The algorithm was designed to calculate CCS based on 5 input parameters: name of drug, dose, dosing interval, time(s) of dosing, and type of inhaler device. In addition, a generalized algorithm was set up to calculate CCS based on clearance, volume of distribution, absorption rate, protein binding, pulmonary deposition, oral bioavailability, and unbound EC50 Of the corticosteroid of interest. The spreadsheet allowed predictions of CCS for single doses as well as steady-state conditions. A simple method has been developed that facilitates comparisons between various drugs and dosing regimens and has the potential to significantly reduce the number of comparative clinical trials to be performed for evaluating the short-term systemic activity of inhaled corticosteroids.

关键词： computer algorithm PK/PD inhaled corticosteroids Excel cortisol safety

来源：评论

学校读者我要写书评

暂无评论

Design and Application of an Improved Genetic algorithm to a Class Scheduling System

INTERNATIONAL JOURNAL OF EMERGING TECHNOLOGIES IN LEARNING

引用

INTERNATIONAL JOURNAL OF EMERGING TECHNOLOGIES IN LEARNING 2021年第1期16卷 44-59页

作者： Chen, Xiangliu Yue, Xiao-Guang Li, Rita Yi Man Zhumadillayeva, Ainur Liu, Ruru Guilin Univ Elect Technol Guilin Peoples R China European Univ Cyprus Nicosia Cyprus Hong Kong Shue Yan Univ Hong Kong Peoples R China LN Gumilyov Eurasian Natl Univ Fac Informatio Technol Nur Sultan Kazakhstan Chizhou Univ Sch Mech & Elect Engn Chizhou Peoples R China

The current expansion of national colleges and universities or the increase in the number of enrolments requires teaching management to ensure the quality of teaching. The problem of scheduling is a very complicated problem in teaching management, and there are many restrictions. If the number of courses scheduled is large, it will be necessary to repeat the experiment and make adjustments. This kind of work is difficult to accomplish accurately by manpower. Moreover, for a comprehensive university, there are many subjects, many professional settings, limited classroom resources, limited multimedia classroom resources, and other factors that limit and constrain the results of class scheduling. Such a large data volume and complicated workforce are difficult to complete accurately. Therefore, manpower scheduling cannot meet the needs of the educational administration of colleges and universities. Today, computer technology is highly developed. It is very economical to use software technology to design a course scheduling system and let the computer complete this demanding and rigorous work. Common course scheduling systems mainly include hill climbing algorithms, tabu search algorithms, ant colony algorithms, and simulated annealing algorithms. These algorithms have certain shortcomings. In this research, we investigated the mutation genetic algorithm and applied the algorithm to the student's scheduling system. Finally, we tested the running speed and accuracy of the system. We found that the algorithm worked well in the course scheduling system and provided strong support for solving the tedious scheduling work of the educational administration staff.

关键词： Course scheduling system Accuracy Running speed computer algorithm

来源：评论

学校读者我要写书评

暂无评论

Structural analysis, identification, and design of calcium-binding sites in proteins

引用

PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS 2002年第3期47卷 344-356页

作者： Yang, W Lee, HW Hellinga, H Yang, JJ Georgia State Univ Dept Chem Ctr Drug Design Atlanta GA 30303 USA Georgia State Univ Dept Biol Drug Design Atlanta GA 30303 USA Duke Univ Med Ctr Dept Biochem Durham NC 27710 USA

Assigning proteins with functions based on the 3-D structure requires high-speed techniques to make a systematic survey of protein structures. Calcium regulates many biological systems by binding numerous proteins in different biological environments. Despite the great diversity in the composition of ligand residues and bond angles and lengths of calcium-binding sites, our structural analysis of 11 calcium-binding sites in different classes of proteins has shown that common local structural parameters can be used to identify and design calcium-binding proteins. Natural calcium-binding sites in both EF-hand proteins and non-EF-hand proteins can be described with the smallest deviation from the geometry of an ideal pentagonal bi-pyramid. Further, two different magnesium-binding sites in parvalbumin and calbindin(D9K) can also be identified using an octahedral geometry. Using the established method, we have designed de novo calcium-binding sites into the scaffold of non-calcium-binding proteins CD2 and Rop. Our results suggest that it is possible to identify calcium- and magnesium-binding sites in proteins and design de novo metal-binding sites. (C) 2002 Wiley-Liss, Inc.

关键词： EF-hand motif calcium-binding proteins magnesium binding de novo design computer algorithm

来源：评论

学校读者我要写书评

暂无评论

computerized analysis of the 12-lead electrocardiogram to identify epicardial ventricular tachycardia exit sites

引用

HEART RHYTHM 2014年第11期11卷 1966-1973页

作者： Yokokawa, Miki Jung, Dae Yon Joseph, Kim K. Hero, Alfred O., III Morady, Fred Bogun, Frank Univ Michigan Div Cardiovasc Med Ann Arbor MI 48109 USA Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA

BACKGROUND Twelve-lead electrocardiogram (ECG) criteria for epicardial ventricular tachycardia (VT) origins have been described. In patients with structural heart disease, the ability to predict an epicardial origin based on QRS morphology is Limited and has been investigated only for limited regions in the heart. OBJECTIVE The purpose of this study was to determine whether a computerized algorithm is able to accurately differentiate epicardial vs endocardial origins of ventricular arrhythmias. METHODS Endocardial and epicardiaL pace-mapping were performed in 43 patients at 3277 sites. The 12-Lead ECGs were digitized and analyzed using a mixture of gaussian model (MoG) to assess whether the algorithm was able to identify an epicardial vs endocardial origin of the paced rhythm. The MoG computerized algorithm was compared to algorithms published in prior reports. RESULTS The computerized algorithm correctly differentiated epicardial vs endocardial pacing sites for 800/0 of the sites compared to an accuracy of 42% to 66% of other described criteria. The accuracy was higher in patients without structural heart disease than in those with structural heart disease (94 /a vs 80%, P =.0004) and for right bundle branch block (82%) compared to left bundle branch block morphologies (79%, P = .001). Validation studies showed the accuracy for VT exit sites to be 84%. CONCLUSION A computerized algorithm was able to accurately differentiate the majority of epicardial vs endocardial pacemapping sites. The algorithm is not region specific and performed best in patients without structural heart disease and with VTs having a right bundle branch block morphology.

关键词： Ventricular tachycardia Epicardial Endocardial computer algorithm ORS morphology

来源：评论

学校读者我要写书评

暂无评论

Can individualized weight monitoring using the HeartPhone algorithm improve sensitivity for clinical deterioration of heart failure?

引用

EUROPEAN JOURNAL OF HEART FAILURE 2013年第4期15卷 447-455页

作者： Ledwidge, Mark T. O'Hanlon, Rory Lalor, Lorraine Travers, Bronagh Edwards, Nuala Kelly, Deirdre Voon, Victor McDonald, Kenneth M. St Vincents Univ Hosp Heart Failure Unit Dublin 4 Ireland Univ Coll Dublin Sch Med & Med Sci Dublin 2 Ireland

Previous studies have demonstrated poor sensitivity of guideline weight monitoring in predicting clinical deterioration of heart failure (HF). This study aimed to evaluate patterns of remotely transmitted daily weights in a high-risk HF population and also to compare guideline weight monitoring and an individualized weight monitoring algorithm. Consenting, consecutive, high-risk patients were provided with a mobile phone-based remote weight telemonitoring device. We aimed to evaluate population vs. individual weight variability, weight patterns pre- and post-events of clinical deterioration of HF, and to compare guideline weight thresholds with the HeartPhone algorithm in terms of sensitivity and specificity for such events. Of 87 patients recruited and followed for an average of 23.9 12 weeks, 19 patients experienced 28 evaluable episodes of clinical deterioration of HF. Following a post-discharge decline, the population average weight remained stable for the follow-up period, yet the 7-day moving average of individual patients exceeded 2 kg in three-quarters of patients. Significant increases in weight were observed up to 4 days before HF events. The HeartPhone algorithm was significantly more sensitive (82) in predicting HF events than guideline weight thresholds of 2 kg over 23 days (21) and a rule of thumb threshold of 1.36 kg over 1 day (46). An individualized approach to weight monitoring in HF with the HeartPhone algorithm improved prediction of HF deterioration. Further evaluation of HeartPhone with and without other biomarkers of HF deterioration is warranted.

关键词： Telemonitoring Weight monitoring in heart failure Fluid retention Prevention of clinical deterioration computer algorithm Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Phylogenetic profiles: A graphical method for detecting genetic recombinations in homologous sequences

引用

MOLECULAR BIOLOGY AND EVOLUTION 1998年第3期15卷 326-335页

作者： Weiller, GF Australian Natl Univ Res Sch Biol Sci Bioinformat Lab Canberra ACT 0200 Australia

Phylogenetic profiles constitute a novel way of graphically displaying the coherence of the sequence relationships over the entire length of a set of aligned homologous sequences. Using a sliding-window technique, this method determines the pairwise distances of all sequences in the windows and evaluates, for each sequence, the degree to which the patterns of distances in these regions agree. This method is suited for exploring data consistency as well as detecting recombinant sequences. A computer program implementing the algorithm has been developed, and examples with simulated and natural sequences are given to demonstrate the sensitivity and accuracy of the method for identifying recombinant sequences and their recombination junctions as well as detecting hot spots of recombinational activity.

关键词： genetic recombination computer algorithm Salmonella enterica molecular phylogeny evolution

来源：评论

学校读者我要写书评

暂无评论

Hierarchical structure of donor splice site sequence multitude

引用

GENE 2003年第1-2期320卷 89-96页

作者： Denisov, DA Denisova, GF Tel Aviv Univ Dept Cell Res & Immunol George S Wise Fac Life Sci IL-69978 Tel Aviv Israel

An analysis of donor splice site sequence (dsss) multitude was carried out. A special method was developed to study the multitude properties. The multitude of dsss was arranged as a hierarchical tree where the "root" consists of a small group of "ancestors", VAGgtVAG (gt stands in the beginning of intron, V = C,A,G). Every ancestor has its own clan of "descendants" which represent point mutants of it. The latter are split into "progenies". The first progeny looks like point mutants of the ancestors, the second as one-point mutants of sequences of the first progeny, and so forth. This picture looks like a hierarchical phylogenetic tree. The most striking property of the multitude is the successive monotonic decrease in occurrences of the sequences from one progeny to another. It is shown that such results may be modeled by a virtual mutational process. (C) 2003 Elsevier B.V. All rights reserved.

关键词： DNA evolution splicing computer algorithm

来源：评论

学校读者我要写书评

暂无评论

Assessment of Tissue Edema in Patients With Acute Myocardial Infarction by computer-Assisted Quantification of Triple Inversion Recovery Prepared MRI of the Myocardium

引用

MAGNETIC RESONANCE IN MEDICINE 2011年第2期66卷 564-573页

作者： Johnstone, R. I. Greenwood, J. P. Biglands, J. D. Plein, S. Ridgway, J. P. Radjenovic, A. Univ Leeds Sch Med NIHR LMBRU Chapel Allerton Hosp Leeds LS7 4SA W Yorkshire England Leeds Teaching Hosp Trust Dept Med Phys & Engn Leeds W Yorkshire England Univ Leeds Sch Med Leeds LS7 4SA W Yorkshire England

The aim of this study was to design a computer algorithm to assess the extent of cardiac edema from triple inversion recovery MR images of the human left ventricular myocardium. Twenty-one patients presenting with acute myocardial infarction were scanned within 48 h of the onset of symptoms. Eight patients were scanned a second time, 4 weeks after the initial event. Myocardial edema was detected in 27 of 29 studies using visual contour-based manual segmentation. A reference standard, created from the segmentations of three raters by voxel-wise majority voting, was compared to the edema mass estimates obtained using a newly developed computer algorithm. At baseline (n = 20), the reference standard yielded an edema mass of 16.4 +/- 15.0 g (mean +/- SD) and the computer algorithm edema mass was 16.4 +/- 12.6 g. At follow-up (n = 7), the reference standard edema mass was 7.1 +/- 4.4 g compared to 16.3 +/- 7.7 g at baseline. computer algorithm estimates showed the same pattern of change with 5.7 +/- 5.7 g at follow-up compared to 20.8 +/- 13.8 g at baseline. Although there was a significant degree of discrepancy between reference standard and computer algorithm estimates of edema mass in individual patients, their overall agreement was good, with intraclass correlation coefficient ICC(3, 1) = 0.753. Magn Reson Med 66:564-573, 2011. (C) 2011 Wiley-Liss, Inc.

关键词： myocardial edema myocardial infarction magnetic resonance imaging image processing computer algorithm

来源：评论

学校读者我要写书评

暂无评论

MEASURING NOMINAL SCALE AGREEMENT BETWEEN A JUDGE AND A KNOWN STANDARD

引用

PSYCHOMETRIKA 1978年第2期43卷 213-223页

作者： WACKERLY, DD MCCLAVE, JT RAO, PV Department of Statistics Nuclear Sciences Center University of Florida 32611 Gainesville Florida

Two designs for comparing a judge's ratings with a known standard are presented and compared. Design A pertains to the situation where the judge is asked to categorize each ofN subjects into one ofr (known) classes with no knowledge of the actual number in each class. Design B is employed when the judge is given the actual number in each class and is asked to categorize the individuals subject to these constraints. The probability distribution of the total number of correct choices is developed in each case. A power comparison of the two procedures is undertaken.

关键词： categorical data nominal data Fisher's tea-tasting experiment Fleiss' Kappa multinomial distribution power comparisons computer algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：