Computers in Biology and Medicine (COMPUT BIOL MED)

Publications in this journal

• Article: A semi-automated computer tool for the analysis of retinal vessel diameter dynamics

  Guillaume Euvrard, Olivier Genevois, Isabelle Rivals, Pascale Massin, Amélie Collet, José-Alain Sahel, Michel Paques
  [show abstract] [hide abstract]
  ABSTRACT: Retinal vessels are directly accessible to clinical observation. This has numerous potential interests for medical investigations. Using the Retinal Vessel Analyzer, a dedicated eye fundus camera enabling dynamic, video-rate recording of micrometric changes of the diameter of retinal vessels, we developed a semi-automated computer tool that extracts the heart beat rate and pulse amplitude values from the records. The extracted data enabled us to show that there is a decreasing relationship between heart beat rate and pulse amplitude of arteries and veins. Such an approach will facilitate the modeling of hemodynamic interactions in small vessels.
  Computers in Biology and Medicine 06/2013; 43:513-523.
• Article: Standalone functional CAD system for multi-object case analysis in hepatic disorders

  Luminita Morarua, Corresponding author contact information, E-mail the corresponding author, Dorin Bibicua, Anjan Biswasc
  [show abstract] [hide abstract]
  ABSTRACT: A new algorithm able to automatically diagnose the presence of the hemangioma areas in the hepatic ultrasonographic image is proposed. The algorithm uses a new multi-object approach which decomposes the image into three biological regions: a normal hepatic area, a hemangioma area and other areas. The de-noising process is efficiently accomplished for both Gaussian and Rayleigh noise distributions. Furthermore, a segmentation technique, based on gray level intensity analysis and the Moore-Neighbor contour tracing algorithm for a robust differentiation of the hemangioma area are employed. This new proposed technique is almost fully automatic, fast, and simple and its results are satisfactory.
  Computers in Biology and Medicine 05/2013;
• Article: An Insight into the Molecular Basis for Convergent Evolution in Fish Antifreeze Proteins

  Abhigyan Nath, Radha Chaube, S.Karthikeyan
  [show abstract] [hide abstract]
  ABSTRACT: Antifreeze proteins (AFPs) prevent the growth of ice-crystals in order to enable certain organisms to survive under sub-zero temperature surroundings. These AFPs have evolved from different types of proteins without having any significant structural and sequence similarities among them. However all the AFPs perform the same function of anti-freeze activity and are a classical example of convergent evolution. We have analyzed fish AFPs at the sequence level, the residue level and the physicochemical property group composition to discover molecular basis for this convergent evolution. Our study on amino acid distribution does not reveal any distinctive feature among AFPs, but comparative study of AFPs with their close non-AFP homologs based on the physicochemical property group residues revealed some useful information. In particular (a) there is a similar pattern of avoidance and preference of amino acids in Fish AFP subtypes II, III and IV - Aromatic residues are avoided whereas small residues are preferred, (b) Like other psychrophilic proteins, AFPs have a similar pattern of preference/avoidance for most of the residues except for Ile, Leu and Arg, and (c) Most of the computed amino acids in preferred list are the key functional residues as obtained in previous predicted model of Doxey et al. For the first time this study revealed common patterns of avoidance/preference in fish AFP subtypes II, III and IV. These avoidance/preference lists can further facilitate the identification of key functional residues and can shed more light into the mechanism of antifreeze function.
  Computers in Biology and Medicine 04/2013;
• Article: Keratin protein property based classification of mammals and non-mammals using machine learning techniques

  Amit Kumar Banerjee, Vadlamani Ravi, U.S.N. Murty, Anirudh P. Shanbhag, Lakshmi Prasanna V
  [show abstract] [hide abstract]
  ABSTRACT: Keratin protein is ubiquitous in most vertebrates and invertebrates, and has several important cellular and extracellular functions that are related to survival and protection. Keratin function has played a significant role in the natural selection of an organism. Hence, it acts as a marker of evolution. Much information about an organism and its evolution can therefore be obtained by investigating this important protein. In the present study, keratin sequences were extracted from public data repositories and various important sequential, structural and physicochemical properties were computed and used for preparing the dataset. The dataset containing two classes, namely mammals (Class-1) and non mammals (Class-0), was prepared, and rigorous classification analysis was performed. To reduce the complexity of the dataset containing 56 parameters and to achieve improved accuracy, feature selection was done using the t-statistic. The 20 best features (parameters) were selected for further classification analysis using computational algorithms which included SVM, KNN, Neural Network, Logistic regression, Meta Modeling, Tree Induction, Rule Induction, Discriminant analysis and Bayesian Modeling. Statistical methods were used to evaluate the output. Logistic regression was found to be the most effective algorithm for classification, with greater than 96% accuracy using a 10-fold cross validation analysis. KNN, SVM and Rule Induction algorithms also were found to be efficacious for classification.
  Computers in Biology and Medicine 04/2013;
• Article: Structural modeling and simulation studies of human cyclooxygenase (COX) isozymes with selected terpenes: Implications in drug designing and development.

  Swati Singh, Veda P. Pandey, Huma Naaz, Priyanka Singh, Upendra N. Dwivedi
  Computers in Biology and Medicine 02/2013; 43:744–750.
• Article: HeMoLab – Hemodynamics Modelling Laboratory: An application for modelling the human cardiovascular system.

  Larrabide I, Blanco PJ, Urquiza SA, Dari EA, Vénere MJ, Souza e Silva NA, Feijóo RA
  [show abstract] [hide abstract]
  ABSTRACT: In this work we present HeMoLab (Hemodynamics Modeling Laboratory), a computational environment for modeling the Human Cardiovascular System. Its integrates novel computational tools, running from medical image processing to numerical simulation and visualization. As a simulation tool, it allows to accommodate complex physiological and/or pathophysiological (virtual) scenarios aimed to retrieve detailed information from the numerical computations. Such application makes possible to speed up research in the study and analysis of the cardiovascular system and, to provide a virtual laboratory for medical training and education, and specialized Human Resources development. In order to demonstrate the modeling and simulation capabilities of HeMoLab some cases of use are presented.
  Computers in Biology and Medicine 10/2012; 42(10):993–1004.
• Article: On the relevance of automatically selected single-voxel MRS and multimodal MRI and MRSI features for brain tumour differentiation

  Geert J. Postma, Jan Luts, Albert J. Idema, Ángel Moreno-Torres, Witek Gajewicz, Johan A. K. Suykens, Arend Heerschap, Sabine Van Huffel, Lutgarde M. C. Buydens
  [show abstract] [hide abstract]
  ABSTRACT: In order to evaluate the relevance of magnetic resonance (MR) features selected by automatic feature selection techniques to build classifiers for differential diagnosis and tissue segmentation two data sets containing MR spectroscopy data from patients with brain tumours were investigated. The automatically selected features were evaluated using literature and clinical experience. It was observed that a significant part of the automatically selected features correspond to what is known from the literature and clinical experience. We conclude that automatic feature selection is a useful tool to obtain relevant and possibly interesting features, but evaluation of the obtained features remains necessary.
  Computers in Biology and Medicine 02/2011; 41(2):87-97.
• Article: Measurement of Phase Synchrony of Coupled Segmentation Clocks

  MD. JAHOOR ALAM, BHAYANA L, DEVI G R, SINGH H D, BROJEN R K, SHARMA B I
  Computers in Biology and Medicine 01/2011; 41:916–921.
• Source

  Available from: swin.edu.au

  Article: Dissociating the effects of nitrous oxide on brain electrical activity using fixed order time series modeling.

  David T J Liley, Kate Leslie, Nicholas C Sinclair, Martin Feckie
  [show abstract] [hide abstract]
  ABSTRACT: A number of commonly used anesthetics, including nitrous oxide (N2O), are poorly detected by current electroencephalography (EEG)-based measures of anesthetic depth such as the bispectral index. Based on a previously elaborated theory of electrocortical rhythmogenesis we developed a physiologically inspired method of EEG analysis that was hypothesized to be more sensitive in detecting and characterizing N2O effect than the bispectral index, through its combined EEG estimates of cortical input and cortical state. By evaluating sevoflurane-induced loss of consciousness in the presence of low brain concentrations of N2O in 38 elective surgical patients, N2O was associated with a statistically significant reduction in the input the frontal cortex received from other cortical and subcortical areas. In contrast the bispectral index responded only to low, but not to high, concentrations of N2O.
  Computers in Biology and Medicine 11/2008; 38(10):1121-30.
• Article: Robust feature-based registration using a Gaussian-weighted distance map and brain feature points for brain PET/CT images.

  Ho Lee, Jeongjin Lee, Namkug Kim, Sang Joon Kim, Yeong Gil Shin
  [show abstract] [hide abstract]
  ABSTRACT: Feature-based registration is an effective technique for clinical use, because it can greatly reduce computational costs. However, this technique, which estimates the transformation by using feature points extracted from two images may cause misalignments, particularly in brain PET and CT images that have low correspondence rates between features due to differences in image characteristics. To cope with this limitation, we propose a robust feature-based registration technique using a Gaussian-weighted distance map (GWDM) that finds the best alignment of feature points even when features of two images are mismatched. A GWDM is generated by propagating the value of the Gaussian-weighted mask from feature points of CT images and leads the feature points of PET images to be aligned on an optimal location even though there is a localization error between feature points extracted from PET and CT images. Feature points are extracted from two images by our automatic brain segmentation method. In our experiments, simulated and clinical data sets were used to compare our method with conventional methods such as normalized mutual information (NMI)-based registration and chamfer matching in accuracy, robustness, and computational time. Experimental results showed that our method aligned the images robustly even in cases where conventional methods failed to find optimal locations. In addition, the accuracy of our method was comparable to that of the NMI-based registration method.
  Computers in Biology and Medicine 10/2008; 38(9):945-61.
• Article: Screening of knee-joint vibroarthrographic signals using the strict 2-surface proximal classifier and genetic algorithm.

  Tingting Mu, Asoke K Nandi, Rangaraj M Rangayyan
  [show abstract] [hide abstract]
  ABSTRACT: We propose the strict 2-surface proximal (S2SP) classifier, by seeking two cross proximal planes to fit the distribution of the given samples in a corresponding feature space. The method is applied to screen knee-joint vibration or vibroarthrographic (VAG) signals based on statistical parameters derived from signals and selected by the genetic algorithm. A database of 89 VAG signals was studied. With the leave-one-out procedure, the linear S2SP classifier provided an efficiency of 0.82 in terms of the area under the receiver operating characteristics curve (A(z)); the nonlinear S2SP classifier provided 0.95 in A(z) value using the Gaussian kernel, and possessed good robustness around the selected kernel parameter.
  Computers in Biology and Medicine 10/2008; 38(10):1103-11.
• Article: A quantitative method for representing balance strategies of goal-directed human motions.

  Woojin Park, Devender P Singh, Ronald L Huston, Seongho Song
  [show abstract] [hide abstract]
  ABSTRACT: A movement index termed balance strategy vector (BSV) was developed as a research tool for studying human balance strategies during goal-directed motions. For a given motion (motion capture data), the BSV index quantitatively represents its balance strategy by computing how available body joint DoFs' angular motions affect the formation of the wholebody center-of-mass trajectory. The index facilitates easy and intuitive understanding of balance strategies of various human motions and can assist scientific investigations on human balance strategies. As an example demonstrating the utility of the index, the index was used to explore balance strategies of free-style, sagittal-plane load lifting motions.
  Computers in Biology and Medicine 10/2008; 38(10):1094-102.
• Article: A simulation environment for estimation of the performance of RSA cages.

  M Gammuto, S Martelli, C Trozzi, L Bragonzoni, A Russo
  [show abstract] [hide abstract]
  ABSTRACT: Roentgen stereophotogrammetric analysis (RSA) is an important technique for in vivo evaluation of joint kinematics and surgical outcome. However, its accuracy is highly affected by the experimental set-up. In this paper we present a new software environment for assessing the impact of calibration cage design on the accuracy of the reconstruction of 3D points, which can be easily used for preliminary evaluations also by non-expert users. The paper presents methods of the simulator and preliminary results in a clinical standard and custom environment. The software was realized using MATLAB and developed for the PC/Windows operating system. It is freeware under request to authors.
  Computers in Biology and Medicine 10/2008; 38(9):1000-6.
• Article: EZ-Entry: a clinical data management system.

  Qing-Bin Gao, Yu Kong, Zheng Fu, Jian Lu, Cheng Wu, Zhi-Chao Jin, Jia He
  [show abstract] [hide abstract]
  ABSTRACT: In this paper, a new data management system named EZ-Entry is introduced. Five major functions are enclosed in this system: (1) user authentication; (2) database construction; (3) double data entry with instant alignment; (4) revision tracking; (5) query management. The practical application performed on two clinical trials indicates that EZ-Entry meets the requirements of clinical data management with high efficiency and security. This software is freely available on request from the authors for academic purposes.
  Computers in Biology and Medicine 10/2008; 38(9):1042-4.
• Article: A stochastic model of tumor angiogenesis.

  Babak Mohammadi, Vahid Haghpanah, Bagher Larijani
  [show abstract] [hide abstract]
  ABSTRACT: Angiogenesis is a prerequisite for the growth, invasion and metastasis of solid tumors. The aim of this study was to investigate the changes of microvessel densities in tumor with a method of probability. We showed that the stages of tumor angiogenesis may follow a probabilistic pattern compatible with Markov chain and this could be of prognostic importance. The system was simulated with 10,000 patients in order to show the applicability of this method. This approach may improve classification schemes and perhaps make diagnosis and treatment more individualized to patients.
  Computers in Biology and Medicine 10/2008; 38(9):1007-11.
• Article: Sequential local least squares imputation estimating missing value of microarray data.

  Xiaobai Zhang, Xiaofeng Song, Huinan Wang, Huanping Zhang
  [show abstract] [hide abstract]
  ABSTRACT: Missing values in microarray data can significantly affect subsequent analysis, thus it is important to estimate these missing values accurately. In this paper, a sequential local least squares imputation (SLLSimpute) method is proposed to solve this problem. It estimates missing values sequentially from the gene containing the fewest missing values and partially utilizes these estimated values. In addition, an automatic parameter selection algorithm, which can generate an appropriate number of neighboring genes for each target gene, is presented for parameter estimation. Experimental results confirmed that SLLSimpute method exhibited better estimation ability compared with other currently used imputation methods.
  Computers in Biology and Medicine 10/2008; 38(10):1112-20.