Shaik Mahaboob Basha^1,*, Victor Hugo C. de Albuquerque², Samia Allaoua Chelloug^3,*, Mohamed Abd Elaziz^4,5,6,7, Shaik Hashmitha Mohisin⁸, Suhail Parvaze Pathan⁹

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.2, pp. 1981-2004, 2024, DOI:10.32604/cmes.2023.031425 - 17 November 2023

Abstract Manual investigation of chest radiography (CXR) images by physicians is crucial for effective decision-making in COVID-19 diagnosis. However, the high demand during the pandemic necessitates auxiliary help through image analysis and machine learning techniques. This study presents a multi-threshold-based segmentation technique to probe high pixel intensity regions in CXR images of various pathologies, including normal cases. Texture information is extracted using gray co-occurrence matrix (GLCM)-based features, while vessel-like features are obtained using Frangi, Sato, and Meijering filters. Machine learning models employing Decision Tree (DT) and Random Forest (RF) approaches are designed to categorize CXR images… More > Graphic Abstract

A. S. Al-Waisy¹, Mazin Abed Mohammed¹, Shumoos Al-Fahdawi¹, M. S. Maashi², Begonya Garcia-Zapirain³, Karrar Hameed Abdulkareem⁴, S. A. Mostafa⁵, Nallapaneni Manoj Kumar⁶, Dac-Nhuong Le^7,8,*

CMC-Computers, Materials & Continua, Vol.67, No.2, pp. 2409-2429, 2021, DOI:10.32604/cmc.2021.012955 - 05 February 2021

Abstract Coronavirus (COVID-19) epidemic outbreak has devastating effects on daily lives and healthcare systems worldwide. This newly recognized virus is highly transmissible, and no clinically approved vaccine or antiviral medicine is currently available. Early diagnosis of infected patients through effective screening is needed to control the rapid spread of this virus. Chest radiography imaging is an effective diagnosis tool for COVID-19 virus and follow-up. Here, a novel hybrid multimodal deep learning system for identifying COVID-19 virus in chest X-ray (CX-R) images is developed and termed as the COVID-DeepNet system to aid expert radiologists in rapid and… More >

Mohamed Ben Gharsallah^a, Issam Ben Mhammed^b, Ezzedine Ben Braiek^a

Intelligent Automation & Soft Computing, Vol.24, No.2, pp. 231-240, 2018, DOI:10.1080/10798587.2016.1262457

Abstract In radiography imaging, contrast, sharpness and noise there are three fundamental factors that determine the image quality. Removing noise while preserving and sharpening image contours is a complicated task particularly for images with low contrast like radiography. This paper proposes a new anisotropic diffusion method for radiography image enhancement. The proposed method is based on the integration of geometric parameters derived from the local pixel intensity distribution in a nonlinear diffusion formulation that can concurrently perform the smoothing and the sharpening operations. The main novelty of the proposed anisotropic diffusion model is the ability to More >

Daniel C. Moura¹, Jorge G. Barbosa¹, Ana M. Reis², João Manuel R. S. Tavares³

CMES-Computer Modeling in Engineering & Sciences, Vol.60, No.2, pp. 115-138, 2010, DOI:10.3970/cmes.2010.060.115

Abstract This paper presents a new method for the calibration of biplanar radiography that makes possible performing 3D reconstructions of the spine using conventional radiological systems. A novel approach is proposed in which a measuring device is used for determining focal distance and have a rough estimation of translation parameters. Using these data, 3D reconstructions of the spine with correct scale were successfully obtained without the need of calibration objects, something that was not previously achieved. For superior results, two optional steps may be executed that involve an optimisation of the geometrical parameters, followed by a… More >

G. Papaioannou¹, C. Mitrogiannis¹, G. Nianios¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.8, No.2, pp. 41-46, 2008, DOI:10.3970/icces.2008.008.041

Abstract Previous attempts to track skeletal kinematics from sequences of images acquired using biplane dynamic radiography report challenges in automating the tracking technique due to image resolution issues, occlusion from segments appearing synchronously in the field of view and computational load. This translates into many hours of manual work to export the kinematics. The proposed new tracking method tackles the above problems and reduces the time to export kinematics from several hours to less than 3 minutes. More >

G. Papaioannou¹, G. Nianios¹, C. Mitroyiannis¹, S.Tashman², K.H. Yang²

The International Conference on Computational & Experimental Engineering and Sciences, Vol.8, No.1, pp. 7-12, 2008, DOI:10.3970/icces.2008.008.007

Abstract Little is known about in vivo menisci loads and displacements in the knee during strenuous activities. We have developed a method that combines biplane high-speed dynamic radiography (DRSA) and a subject-specific finite element model for studying in vivo meniscal behavior. In a very controlled uniaxial compression loading condition, removing of the pressure sensor from the model can result in relatively large errors in contact and cartilage stress that are not reflected in the change of meniscal displacement. More >