Muhammad Attique Khan¹, Abdul Majid¹, Tallha Akram², Nazar Hussain¹, Yunyoung Nam^3,*, Seifedine Kadry⁴, Shui-Hua Wang⁵, Majed Alhaisoni⁶

CMC-Computers, Materials & Continua, Vol.68, No.1, pp. 1003-1019, 2021, DOI:10.32604/cmc.2021.015541

Abstract Here, we use multi-type feature fusion and selection to predict COVID-19 infections on chest computed tomography (CT) scans. The scheme operates in four steps. Initially, we prepared a database containing COVID-19 pneumonia and normal CT scans. These images were retrieved from the Radiopaedia COVID-19 website. The images were divided into training and test sets in a ratio of 70:30. Then, multiple features were extracted from the training data. We used canonical correlation analysis to fuse the features into single vectors; this enhanced the predictive capacity. We next implemented a genetic algorithm (GA) in which an Extreme Learning Machine (ELM) served… More >

Muhammad Attique Khan¹, Nazar Hussain¹, Abdul Majid¹, Majed Alhaisoni², Syed Ahmad Chan Bukhari³, Seifedine Kadry⁴, Yunyoung Nam^5,*, Yu-Dong Zhang⁶

CMC-Computers, Materials & Continua, Vol.66, No.3, pp. 2923-2938, 2021, DOI:10.32604/cmc.2021.013191

Abstract In medical imaging, computer vision researchers are faced with a variety of features for verifying the authenticity of classifiers for an accurate diagnosis. In response to the coronavirus 2019 (COVID-19) pandemic, new testing procedures, medical treatments, and vaccines are being developed rapidly. One potential diagnostic tool is a reverse-transcription polymerase chain reaction (RT-PCR). RT-PCR, typically a time-consuming process, was less sensitive to COVID-19 recognition in the disease’s early stages. Here we introduce an optimized deep learning (DL) scheme to distinguish COVID-19-infected patients from normal patients according to computed tomography (CT) scans. In the proposed method, contrast enhancement is used to… More >

Minliang Liu¹, Liang Liang², Xiaoying Lou³, Glen Iannucci³, Edward Chen³, Bradley Leshnower³, Wei Sun^1,*

Molecular & Cellular Biomechanics, Vol.16, Suppl.2, pp. 53-53, 2019, DOI:10.32604/mcb.2019.07387

Abstract It is well known that mechanical properties of the aortic wall exhibit patient-specific variations. Recent experimental findings also suggest the aortic wall properties are highly region-specific [1-2]. Thus, in vivo heterogeneous (non-uniform) nonlinear mechanical properties of the aortic wall of individual patients needs to be noninvasively identified for accurate prediction of clinical events (e.g. aortic rupture).
In this study, we developed an inverse approach for identification of patient-specific non-uniform material properties of the aortic wall from gated 3D CT scans. This inverse approach leverages the fact that the in vivo transmural mean stress (tension) of the aortic wall is… More >

FU Zhiliang¹, GUO Hua², GAO Yanfa³

The International Conference on Computational & Experimental Engineering and Sciences, Vol.5, No.3, pp. 145-156, 2008, DOI:10.3970/icces.2008.005.145

Abstract This paper is focused on the micro-damage evolution properties of gray green mudstone under impacting disturbance load conditions for the first time by using the real time CT testing technique. CT images and CT values for rock cross-sections under different impacting disturbance loading levels were obtained. The paper is also to describe process of rock creep damage under disturbance loads and to explore the mechanism of micro-damage. The results have shown that rock failure is easy to happen suddenly rock is in or close to limit strength neighborhood during the process of disturbance. This will further lay the theory basis… More >

Y. Gür^*

Molecular & Cellular Biomechanics, Vol.11, No.4, pp. 249-258, 2014, DOI:10.3970/mcb.2014.011.249

Abstract The purpose of the study presented here was to investigate the manufacturability of human anatomical models from Computed Tomography (CT) scan data via a 3D desktop printer which uses fused deposition modelling (FDM) technology. First, Digital Imaging and Communications in Medicine (DICOM) CT scan data were converted to 3D Standard Triangle Language (STL) format by using InVaselius digital imaging program. Once this STL file is obtained, a 3D physical version of the anatomical model can be fabricated by a desktop 3D FDM printer. As a case study, a patient’s skull CT scan data was considered, and a tangible version of… More >