A propagation-DNN: Deep combination learning of multi-level features for MR prostate segmentation.

Abstract:

BACKGROUND AND OBJECTIVE:Prostate segmentation on Magnetic Resonance (MR) imaging is problematic because disease changes the shape and boundaries of the gland and it can be difficult to separate the prostate from surrounding tissues. We propose an automated model that extracts and combines multi-level features in a deep neural network to segment prostate on MR images. METHODS:Our proposed model, the Propagation Deep Neural Network (P-DNN), incorporates the optimal combination of multi-level feature extraction as a single model. High level features from the convolved data using DNN are extracted for prostate localization and shape recognition, while labeling propagation, by low level cues, is embedded into a deep layer to delineate the prostate boundary. RESULTS:A well-recognized benchmarking dataset (50 training data and 30 testing data from patients) was used to evaluate the P-DNN. When compared it to existing DNN methods, the P-DNN statistically outperformed the baseline DNN models with an average improvement in the DSC of 3.19%. When compared to the state-of-the-art non-DNN prostate segmentation methods, P-DNN was competitive by achieving 89.9 ± 2.8% DSC and 6.84 ± 2.5 mm HD on training sets and 84.13 ± 5.18% DSC and 9.74 ± 4.21 mm HD on testing sets. CONCLUSION:Our results show that P-DNN maximizes multi-level feature extraction for prostate segmentation of MR images.

authors

Yan K,Wang X,Kim J,Khadra M,Fulham M,Feng D

doi

10.1016/j.cmpb.2018.12.031

subject

Has Abstract

pub_date

2019-03-01 00:00:00

pages

11-21

eissn

0169-2607

issn

1872-7565

pii

S0169-2607(18)31099-X

journal_volume

170

pub_type

杂志文章
  • A method for measuring and reporting manual data extraction reliability.

    abstract::As health care costs have risen dramatically, the use of clinical data to analyze the quality of health care provided has increased. Central to this analysis is the means by which the clinical data itself is obtained. The reliability and validity of the data must be established in order to insure credible use of the d...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(93)90063-q

    authors: Rozewski CM

    更新日期:1993-09-01 00:00:00

  • Graphical simulation environments for modelling and simulation of integrative physiology.

    abstract::Guyton's original integrative physiology model was a milestone in integrative physiology, combining significant physiological knowledge with an engineering perspective to develop a computational diagrammatic model. It is still used in research and teaching, with a small number of variants on the model also in circulat...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2010.05.001

    authors: Mangourova V,Ringwood J,Van Vliet B

    更新日期:2011-06-01 00:00:00

  • An optoelectronic based approach for handwriting capture.

    abstract::Clinical practice for the evaluation of motor and cognitive capabilities often relies upon writing and drawing tests. A non-invasive method to capture handwriting and analyze data is therefore needed. In this work a method to capture motion of a pen through a mo-cap optoelectronic system was developed, which could sol...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2013.05.002

    authors: Ancillao A,Galli M,Vimercati SL,Albertini G

    更新日期:2013-08-01 00:00:00

  • Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features.

    abstract::The aim of the present study was to design, implement and evaluate a software system for discriminating between metastatic and primary brain tumors (gliomas and meningiomas) on MRI, employing textural features from routinely taken T1 post-contrast images. The proposed classifier is a modified probabilistic neural netw...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2007.10.007

    authors: Georgiadis P,Cavouras D,Kalatzis I,Daskalakis A,Kagadis GC,Sifaki K,Malamas M,Nikiforidis G,Solomou E

    更新日期:2008-01-01 00:00:00

  • Automated quantitative analysis of angiogenesis in the rat aorta model using Image-Pro Plus 4.1.

    abstract::This paper explains the automated image-processing steps for the quantification of microvascular growth formation in the rat thoracic aortic ring model, an ex vivo model using excised rings of rat aorta embedded in a collagen matrix which produce outgrowths of microvessels. This model of angiogenesis is useful to stud...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2003.11.001

    authors: Blatt RJ,Clark AN,Courtney J,Tully C,Tucker AL

    更新日期:2004-07-01 00:00:00

  • A software for the description of workplaces in the PRS system.

    abstract::Workplace description is an operation indispensable for the identification of professional risks and, in fulfillment of that objective, can best be accomplished by listing the constituent tasks associated with each job. This article presents a software in Visual-Basic to be run on a portable micro-computer, which faci...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/s0169-2607(97)01777-x

    authors: Martin JM,Dartois E,Bontoux-Frank G,Ricour B,Pariset L,Robaux P,Giampietro V

    更新日期:1997-01-01 00:00:00

  • SAE: an R package for early stopping rules in clinical trials.

    abstract::In the case of an unexpected high frequency of serious adverse events (SAE), statistical methods are needed to help in the decision making process as to continuation of accrual to the trial. This paper describes an R package, named SAE that implements a method recently developed by defining stopping rules after each o...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2011.05.005

    authors: Bascoul-Mollevi C,Laplanche A,Le Deley MC,Kramar A

    更新日期:2011-11-01 00:00:00

  • Fetal health status prediction based on maternal clinical history using machine learning techniques.

    abstract:BACKGROUND AND OBJECTIVE:Congenital anomalies are seen at 1-3% of the population, probabilities of which are tried to be found out primarily through double, triple and quad tests during pregnancy. Also, ultrasonographical evaluations of fetuses enhance detecting and defining these abnormalities. About 60-70% of the ano...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2018.06.010

    authors: Akbulut A,Ertugrul E,Topcu V

    更新日期:2018-09-01 00:00:00

  • Corrigendum to "Transportation of magnetized micropolar hybrid nanomaterial fluid flow over a Riga curface surface" [Comput Meth Prog Bio 185 (2020) 105,136].

    abstract::This corrigendum corrects the dimensions of partial differential equations in the paper [1], where these mistakes are occurred during typing processes. But the results in [1] does not affect the scientific and mathematical validity of the paper. ...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 信件

    doi:10.1016/j.cmpb.2019.105251

    authors: Abbas N,Malik MY,Nadeem S

    更新日期:2020-04-01 00:00:00

  • Intelligent classification of electrocardiogram (ECG) signal using extended Kalman Filter (EKF) based neuro fuzzy system.

    abstract::This study presents the development of a hybrid system consisting of an ensemble of Extended Kalman Filter (EKF) based Multi Layer Perceptron Network (MLPN) and a one-pass learning Fuzzy Inference System using Look-up Table Scheme for the recognition of electrocardiogram (ECG) signals. This system can distinguish vari...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2006.03.003

    authors: Meau YP,Ibrahim F,Narainasamy SA,Omar R

    更新日期:2006-05-01 00:00:00

  • Shape prior model via dual subspace segment projection learning.

    abstract:BACKGROUND AND OBJECTIVE:Shape prior models play a vital role for segmentation in medical image analysis. These models are most effective when shape variations can be captured by a parametric distribution, and sufficient training data is available. However, in the absence of these conditions, results are invariably muc...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2020.105760

    authors: Belous G,Busch A,Gao Y

    更新日期:2020-09-24 00:00:00

  • A method for the recovery of noisy missing data in movement analysis.

    abstract::A new method is proposed for the accurate recovery of missing marker data obtained from movement tracking systems. The method has the form of a least-squares cubic polynomial approximation which is realized by the recursive expansion of orthogonal polynomials. ...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(91)90082-5

    authors: Stokes VP

    更新日期:1991-01-01 00:00:00

  • Making heterogeneous medical databases interoperable.

    abstract::The increasing use of computer systems for storing patient information in different hospitals, in different departments within the same hospital, in clinics and even in doctors' surgeries, is creating a problem in terms of the fragmentation of the patient record. The lack of any coordination or standardization in the ...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(94)90080-9

    authors: Williams MH,Hu J

    更新日期:1994-06-01 00:00:00

  • Fulfilling programmatic needs at the University of Maryland at Baltimore: the reality.

    abstract::This article will focus on the actual needs enumerated in the University of Maryland at Baltimore's Health Sciences Library/Information Services program entitled, Health Sciences Library: A New Building for Information Services Including the Health Sciences Library. These needs fall into one of 3 categories: collectio...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(94)90120-1

    authors: Tooey MJ

    更新日期:1994-09-01 00:00:00

  • DISTING: A web application for fast algorithmic computation of alternative indistinguishable linear compartmental models.

    abstract:BACKGROUND AND OBJECTIVES:We describe and illustrate use of DISTING, a novel web application for computing alternative structurally identifiable linear compartmental models that are input-output indistinguishable from a postulated linear compartmental model. Several computer packages are available for analysing the str...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2017.02.025

    authors: Davidson NR,Godfrey KR,Alquaddoomi F,Nola D,DiStefano JJ 3rd

    更新日期:2017-05-01 00:00:00

  • Cross-sectional photoacoustic tomography image reconstruction with a multi-curve integration model.

    abstract:BACKGROUND AND OBJECTIVE:In acoustic inversion of photoacoustic tomography (PAT), an imaging model that precisely describes both the ultrasonic wave propagation and the detector properties is of crucial importance. Inspired by the multi-stripe integration model in clinical X-ray computed tomography systems, in this wor...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2020.105731

    authors: Qi L,Huang S,Li X,Zhang S,Lu L,Feng Q,Chen W

    更新日期:2020-12-01 00:00:00

  • frailtypack: a computer program for the analysis of correlated failure time data using penalized likelihood estimation.

    abstract::Correlated survival outcomes occur quite frequently in the biomedical research. Available software is limited, particularly if we wish to obtain smoothed estimate of the baseline hazard function in the context of random effects model for correlated data. The main objective of this paper is to describe an R package cal...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2005.06.010

    authors: Rondeau V,Gonzalez JR

    更新日期:2005-11-01 00:00:00

  • Computer algorithm compared with routine clinical practice in screening for deep venous thrombosis in the leg in an emergency department.

    abstract:OBJECTIVE:To audit routine clinical practice in screening patients admitted to an accident and emergency department for deep venous thrombosis in the leg (DVT) and compare it with a computer algorithm. DESIGN:Retrospective study of case notes with data subsequently entered into a computer algorithm followed by a compa...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2019.105046

    authors: Steer P,Nader A,Ostler A,Malik O,Prior R,Scurr J

    更新日期:2019-12-01 00:00:00

  • Classification of THz pulse signals using two-dimensional cross-correlation feature extraction and non-linear classifiers.

    abstract::This work provides a performance comparison of four different machine learning classifiers: multinomial logistic regression with ridge estimators (MLR) classifier, k-nearest neighbours (KNN), support vector machine (SVM) and naïve Bayes (NB) as applied to terahertz (THz) transient time domain sequences associated with...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2016.01.017

    authors: Siuly,Yin X,Hadjiloucas S,Zhang Y

    更新日期:2016-04-01 00:00:00

  • Benchmarking of a T-wave alternans detection method based on empirical mode decomposition.

    abstract:BACKGROUND AND OBJECTIVE:T-wave alternans (TWA) is a fluctuation of the ST-T complex occurring on an every-other-beat basis of the surface electrocardiogram (ECG). It has been shown to be an informative risk stratifier for sudden cardiac death, though the lack of gold standard to benchmark detection methods has promote...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2017.04.005

    authors: Blanco-Velasco M,Goya-Esteban R,Cruz-Roldán F,García-Alberola A,Rojo-Álvarez JL

    更新日期:2017-07-01 00:00:00

  • Using the job-exposure matrix for elaborating job histories.

    abstract::A first software (JHS) for the elaboration of job histories oriented toward risks was designed and results published In an article "A software for the elaboration of Job Histories". This article presents a second software (JES), based on the use of a job-exposure matrix designed for one company. The matrix is essentia...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(92)90056-d

    authors: Martin JM,Mouaddib AI,Bouzid M,Robaux P

    更新日期:1992-09-01 00:00:00

  • Control system design of a 3-DOF upper limbs rehabilitation robot.

    abstract::This paper presents the control system design of a rehabilitation and training robot for the upper limbs. Based on a hierarchical structure, this control system allows the execution of sequence of switching control laws (position, force, impedance and force/impedance) corresponding to the required training configurati...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2007.07.006

    authors: Denève A,Moughamir S,Afilal L,Zaytoon J

    更新日期:2008-02-01 00:00:00

  • Computer-assisted centrifugal elutriation. II. Multiparametric statistical analysis.

    abstract::A combination of non-interactive statistical methods is discussed to analyze multiparametric light-scatter data obtained by means of computer-assisted centrifugal elutriation. ...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(88)90101-0

    authors: Sloot PM,Van der Donk EH,Figdor CG

    更新日期:1988-07-01 00:00:00

  • A simple computer programme for biokinetic study of 99Tcm-radiopharmaceuticals.

    abstract::A simple programme has been written in GW BASIC to calculate the percentage activity of 99Tcm-radiopharmaceuticals in different tissues after biodistribution. The programme is efficient, easy to handle and produces a permanent record in terms of a final report. ...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(94)90139-2

    authors: Imran MB,Khurshid SJ,Anwar K

    更新日期:1994-02-01 00:00:00

  • Micro-Analyzer: automatic preprocessing of Affymetrix microarray data.

    abstract::A current trend in genomics is the investigation of the cell mechanism using different technologies, in order to explain the relationship among genes, molecular processes and diseases. For instance, the combined use of gene-expression arrays and genomic arrays has been demonstrated as an effective instrument in clinic...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2013.04.006

    authors: Guzzi PH,Cannataro M

    更新日期:2013-08-01 00:00:00

  • Development of an auxiliary system for the execution of vascular catheter interventions with a reduced radiological risk; system description and first experimental results.

    abstract::Vascular catheterization is a common procedure in clinical medicine. It is normally performed by a specialist using an X-ray fluoroscopic guide and contrast-media. In the present paper, an image-guided navigation system which indicates a path providing guidance to the desired target inside the vascular tree is describ...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2007.07.009

    authors: Placidi G,Franchi D,Marsili L,Gallo P

    更新日期:2007-11-01 00:00:00

  • Measurement systems calibration: microcomputer implementation.

    abstract::Measurement systems used in the collection and processing of laboratory data must be calibrated periodically to obtain accurate results. Because calibration factors can change over time or may be reset to optimize measurements for specific tests, care must be taken to assure that calibration factors and data are align...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(91)90014-k

    authors: Reinking RM,Laouris Y,Stuart DG

    更新日期:1991-09-01 00:00:00

  • Computerized diagnosis of gastrointestinal helminths of humans.

    abstract::An interactive computer program written in BASIC with the objective of assisting the identification of species of common gastrointestinal parasites of humans is presented. The computer program acquires observational information needed for the identification of a parasite from the user. The user selects a description f...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/0169-2607(88)90037-5

    authors: Theodoropoulos G

    更新日期:1988-03-01 00:00:00

  • Facilitating pharmacometric workflow with the metrumrg package for R.

    abstract::metrumrg is an R package that facilitates workflow for the discipline of pharmacometrics. Support is provided for data preparation, modeling, simulation, diagnostics, and reporting. Existing tools and techniques are emphasized where available; original solutions are provided for otherwise unmet needs. In particular, m...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 杂志文章

    doi:10.1016/j.cmpb.2012.08.009

    authors: Bergsma TT,Knebel W,Fisher J,Gillespie WR,Riggs MM,Gibiansky L,Gastonguay MR

    更新日期:2013-01-01 00:00:00

  • Controlled multicenter study on the effect of computer assistance in intensive insulin therapy of type 1 diabetics.

    abstract::This paper describes the results of a controlled multicenter study on the effect of the computer assistance in the intensive insulin therapy. The patient collective consisted of 50 diabetics, randomly divided in two groups with 25 patients per group. The Multiple Subcutaneous Injection (MSI) group was treated with the...

    journal_title:Computer methods and programs in biomedicine

    pub_type: 临床试验,杂志文章,多中心研究,随机对照试验

    doi:10.1016/s0169-2607(02)00034-2

    authors: Schrezenmeir J,Dirting K,Papazov P

    更新日期:2002-08-01 00:00:00