Deep Embedding Convolutional Neural Network for Synthesizing CT Image from T1-Weighted MR Image
Computed tomography (CT) and structural magnetic resonance (MR) images are both important and widely applied in the treatment planning of radiotherapy (Balter et al., 1998; Chen et al., 2004; Khoo et al., 1997; Schad et al., 1987). Recently, it has become desirable to synthesize CT image from the corresponding MR scan. For example, quantitative positron emission tomography (PET) requires CT image for attenuation correction (Carney et al., 2006; Kinahan et al., 1998; Pan et al., 2005). The approach for CT-based attenuation correction is to transform the CT image, which is expressed in Hounsfield units, into an estim...
Source: Medical Image Analysis - March 29, 2018 Category: Radiology Authors: Lei Xiang, Qian Wang, Dong Nie, Lichi Zhang, Xiyao Jin, Yu Qiao, Dinggang Shen Source Type: research
Joint solution for PET image segmentation, denoising, and partial volume correction
Positron emission tomography (PET) has been extensively used in oncology applications. It provides diagnostic and therapeutic interpretations by measuring tracer activity, which could be related to various physiological and pathological functionalities. It has been used for other diseases, including neurological disorders, infection, and inflammation. In radiation oncology applications, for instance, PET helps localization and staging of the tumors. PET images have high contrast, but low spatial resolution compared to magnetic resonance imaging (MRI) and computed tomography (CT). (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 28, 2018 Category: Radiology Authors: Ziyue Xu, Mingchen Gao, Georgios Z. Papadakis, Brian Luna, Sanjay Jain, Daniel J. Mollura, Ulas Bagci Source Type: research
SiSSR: Simultaneous subdivision surface registration for the quantification of cardiac function from computed tomography in canines
Regional cardiac dysfunction commonly precedes changes in global metrics such as ejection fraction (EF), and is useful in the characterization of subtle impairment and monitoring of treatment response (Tee et al., 2013). Techniques developed for cardiac magnetic resonance imaging (CMR), including harmonic phase (HARP) imaging (Osman et al., 1999), strain encoded (SENC) imaging (Osman et al., 2001), and displacement encoding with stimulated echos (DENSE) imaging (Aletras et al., 1999), have en abled the measurement of biomarkers for regional cardiac function, including strain, strain rate, and torsion. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 28, 2018 Category: Radiology Authors: Davis M. Vigneault, Amir Pourmorteza, Marvin L. Thomas, David A. Bluemke, J. Alison Noble Source Type: research
Joint Solution for PET Image Segmentation, Denoising, and Partial Volume Correction
Positron emission tomography (PET) has been extensively used in oncology applications. It provides diagnostic and therapeutic interpretations by measuring tracer activity, which could be related to various physiological and pathological functionalities. It has been used for other diseases, including neurological disorders, infection, and inflammation. In radiation oncology applications, for instance, PET helps localization and staging of the tumors. PET images have high contrast, but low spatial resolution compared to magnetic resonance imaging (MRI) and computed tomography (CT). (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 28, 2018 Category: Radiology Authors: Ziyue Xu, Mingchen Gao, Georgios Z. Papadakis, Brian Luna, Sanjay Jain, Daniel J. Mollura, Ulas Bagci Source Type: research
SiSSR: Simultaneous Subdivision Surface Registration for the Quantification of Cardiac Function from Computed Tomography in Canines
Regional cardiac dysfunction commonly precedes changes in global metrics such as ejection fraction (EF), and is useful in the characterization of subtle impairment and monitoring of treatment response (Tee et al., 2013). Techniques developed for cardiac magnetic resonance imaging (CMR), including harmonic phase (HARP) imaging (Osman et al., 1999), strain encoded (SENC) imaging (Osman et al., 2001), and displacement encoding with stimulated echos (DENSE) imaging (Aletras et al., 1999), have enabled t he measurement of biomarkers for regional cardiac function, including strain, strain rate, and torsion. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 28, 2018 Category: Radiology Authors: Davis M. Vigneault, Amir Pourmorteza, Marvin L. Thomas, David A. Bluemke, J. Alison Noble Source Type: research
Deep learning in mammography and breast histology, an overview and future trends
In this study, the relationship between mammography and histopathology phenotypes is described, which takes biological aspects into account. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 26, 2018 Category: Radiology Authors: Azam Hamidinekoo, Erika Denton, Andrik Rampun, Kate Honnor, Reyer Zwiggelaar Source Type: research
Probabilistic guidance for catheter tip motion in cardiac ablation procedures
Heart rhythm disorders are serious conditions affecting the cardiac contraction and output, which can lead to stroke and sudden death. Worldwide, 33.5 million people suffer from atrial fibrillation, with additional patients presenting with atrial and ventricular tachycardias, atrial flutter and other arrhythmias (Chugh et al., 2014). Rhythm disorders are poorly tolerated in particular by patients with congenital heart disease (CHD), such as Tetralogy of Fallot or univentricular hearts treated by Fontan procedure. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 26, 2018 Category: Radiology Authors: Mihaela AM Constantinescu, Su-Lin Lee, Sabine Ernst, Apit Hemakom, Danilo Mandic, Guang-Zhong Yang Source Type: research
Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks
An Abdominal Aortic Aneurysm (AAA) is a focal dilation of the aorta that exceeds its normal diameter by more than 50%. If not treated, it tends to grow and may rupture, with a high mortality rate (Pearce et al., 2008). In the last decade, the treatment of aortic aneurysm has shifted from open surgery to a minimally invasive alternative, known as Endovascular Aneurysm Repair (EVAR) (Moll et al., 2011). This technique consists of the transfemoral insertion and deployment of a stent graft using a catheter. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 26, 2018 Category: Radiology Authors: Karen L ópez-Linares, Nerea Aranjuelo, Luis Kabongo, Gregory Maclair, Nerea Lete, Mario Ceresa, Ainhoa García-Familiar, Iván Macía, Miguel A. González Ballester Source Type: research
Deep Learning in Mammography and Breast Histology, an Overview and Future Trends
In this study, the relationship between mammography and histopathology phenotypes is described, which takes biological aspects into account. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 26, 2018 Category: Radiology Authors: Azam Hamidinekoo, Erika Denton, Andrik Rampun, Kate Honnor, Reyer Zwiggelaar Source Type: research
Probabilistic Guidance for Catheter Tip Motion in Cardiac Ablation Procedures
Heart rhythm disorders are serious conditions affecting the cardiac contraction and output, which can lead to stroke and sudden death. Worldwide, 33.5 million people suffer from atrial fibrillation, with additional patients presenting with atrial and ventricular tachycardias, atrial flutter and other arrhythmias (Chugh et al., 2014). Rhythm disorders are poorly tolerated in particular by patients with congenital heart disease (CHD), such as Tetralogy of Fallot or univentricular hearts treated by Fontan procedure. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 26, 2018 Category: Radiology Authors: Mihaela AM Constantinescu, Su-Lin Lee, Sabine Ernst, Apit Hemakom, Danilo Mandic, Guang-Zhong Yang Source Type: research
Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using deep convolutional neural networks
An Abdominal Aortic Aneurysm (AAA) is a focal dilation of the aorta that exceeds its normal diameter by more than 50%. If not treated, it tends to grow and may rupture, with a high mortality rate (Pearce et al., 2008). In the last decade, the treatment of aortic aneurysm has shifted from open surgery to a minimally invasive alternative, known as Endovascular Aneurysm Repair (EVAR) (Moll et al., 2011). This technique consists of the transfemoral insertion and deployment of a stent graft using a cathe ter. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 26, 2018 Category: Radiology Authors: Karen L ópez-Linares, Nerea Aranjuelo, Luis Kabongo, Gregory Maclair, Nerea Lete, Mario Ceresa, Ainhoa García-Familiar, Iván Macía, Miguel A. González Ballester Source Type: research
Heterogeneous Multifrequency Direct Inversion (HMDI) for magnetic resonance elastography with application to a clinical brain exam
Magnetic resonance elastography (MRE) (Hirsch et al., 2016) encodes induced shear wave displacements using phase-contrast MRI imaging, enabling estimation of in vivo tissue viscoelastic properties by wave inversion. These mechanical properties, including mechanical “stiffness” and viscosity, are of strong medical interest (Mariappan et al., 2010; Sack et al., 2013), and elastography-related research is widespread. One of the strengths of MRE is that full-field displacements of tissue are acquired; however magnetic resonance elastography is challenged by complicated tissue structures and the ill-posed nature of wa...
Source: Medical Image Analysis - March 17, 2018 Category: Radiology Authors: Eric Barnhill, Penny J. Davies, Cemre Ariyurek, Andreas Fehlner, J ürgen Braun, Ingolf Sack Source Type: research
Heterogeneous Multifrequency Direct Inversion (HMDI) for Magnetic Resonance Elastography with Application to a Clinical Brain Exam
Magnetic resonance elastography (Hirsch et al., 2016) encodes induced shear wave displacements using phase-contrast MRI imaging, enabling estimation of in vivo tissue viscoelastic properties by wave inversion. These mechanical properties, including mechanical “stiffness” and viscosity, are of strong medical interest (Mariappan et al., 2010; Sack et al., 2013), and elastography-related research is widespread. One of the strengths of MRE is that full-field displacements of tissue are acquired; however magnetic resonance elastography is challenged by complicated tissue structures and the ill-posed nature of wave inver...
Source: Medical Image Analysis - March 17, 2018 Category: Radiology Authors: Eric Barnhill, Penny J. Davies, Cemre Ariyurek, Andreas Fehlner, J ürgen Braun, Ingolf Sack Source Type: research
Riemannian metric optimization on surfaces (RMOS) for intrinsic brain mapping in the Laplace –Beltrami embedding space
Surface mapping methods play an important role in various scientific discoveries from tracking the maturation of adolescent brains (Gogtay et al., 2004), mapping gray matter atrophy patterns in Alzheimer’s disease (AD) (Thompson et al., 2004), to studying early prenatal and postnatal brain development (Li et al., 2013; Nie et al., 2010). The backbone of surface mapping methods is the computational technique that establishes de tailed one-to-one correspondences across different brain surfaces. In this work, we propose a novel computational framework for establishing surface correspondences in the Laplace–Beltrami...
Source: Medical Image Analysis - March 16, 2018 Category: Radiology Authors: Jin Kyu Gahm, Yonggang Shi, for the Alzheimer ’s Disease Neuroimaging Initiative Source Type: research
