Frequency-splitting Dynamic MRI Reconstruction using Multi-scale 3D Convolutional Sparse Coding and Automatic Parameter Selection
Dynamic magnetic resonance imaging (MRI), including dynamic contrast-enhanced (DCE) MRI and cardiac MRI, has been widely used to analyze changes in tissue characteristics or the movement of organs over time. Since dynamic MRI ’s diagnostic performance is highly correlated with its temporal resolution (El Khouli et al., 2009), speeding up the acquisition time has been actively studied in the recent decades. More recently, compressed sensing theory (Donoho, 2006) has been applied to the MRI reconstruction problem (Lu stig et al., 2008) to reduce the acquisition time. (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 7, 2019 Category: Radiology Authors: Thanh Nguyen-Duc, Tran Minh Quan, Won-Ki Jeong Source Type: research
Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images
Automated medical image analysis has been extensively studied in the medical imaging community due to the fact that manual labelling of large amounts of medical images is a tedious and error-prone task. Accurate and reliable solutions are required to increase clinical work flow efficiency and support decision making through fast and automatic extraction of quantitative measurements. (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 5, 2019 Category: Radiology Authors: Jo Schlemper, Ozan Oktay, Michiel Schaap, Mattias Heinrich, Bernhard Kainz, Ben Glocker, Daniel Rueckert Source Type: research
Automatic needle detection and real-time Bi-planar needle visualization during 3D ultrasound scanning of the liver
Generally, minimally invasive techniques are used for diagnosis and treatment. Compared to open surgery, these procedures are aimed to reduce the risk of surrounding tissues injury and lead to less trauma and shorter recovery time (Slakey  et al. 2013). Percutaneous biopsy in the liver is a minimally invasive procedure where a needle is used to remove tissue samples for histology-based diagnosis. Needle insertion is also performed in therapeutic procedures such as in prostate brachytherapy and in liver tumor thermal ablation (radi ofrequency, microwave or cryo ablation). (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 2, 2019 Category: Radiology Authors: Muhammad Arif, Adriaan Moelker, Theo van Walsum Source Type: research
Automatic Needle Detection and Real-time Bi-planer Needle Visualization during 3D Ultrasound Scanning of the Liver
Generally, minimally invasive techniques are used for diagnosis and treatment. Compared to open surgery, these procedures are aimed to reduce the risk of surrounding tissues injury and lead to less trauma and shorter recovery time (Slakey, Simms et al. 2013). Percutaneous biopsy in the liver is a minimally invasive procedure where a needle is used to remove tissue samples for histology-based diagnosis. Needle insertion is also performed in therapeutic procedures such as in prostate brachytherapy and in liver tumor thermal ablation (radiofrequency, microwave or cryo ablation). (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 2, 2019 Category: Radiology Authors: Muhammad Arif, Adriaan Moelker, Theo van Walsum Source Type: research
Adversarial training with cycle consistency for unsupervised super-resolution in endomicroscopy
According to a recent report by the World Health Organization, cancer is the second leading cause of death after cardiovascular disease and was responsible for 8.8 million deaths in 2015. Early detection, such as the ability to detect precancerous lesions, plays an important role in reducing cancer incidence and related mortality  (Torre et al., 2016). Optical endomicroscopy, based for example on confocal microscopy, optical coherence tomography or spectroscopy, has the ability to perform optical biopsies and identify early pathology in tissues or organs including the colon, oesophagus, pancreas, brain, liver and cervixÂ...
Source: Medical Image Analysis - February 2, 2019 Category: Radiology Authors: Daniele Rav ì, Agnieszka Barbara Szczotka, Stephen P Pereira, Tom Vercauteren Source Type: research
f-AnoGAN: Fast Unsupervised Anomaly Detection with Generative Adversarial Networks
The detection and localization of imaging biomarkers correlating with disease status is important for initial diagnosis, assessment of treatment response and follow-up examinations. Spiculation patterns of lung nodules in lung CT scans (Zwirewich et  al., 1991), microcalcification in X-ray mammography images for breast screening (Wang et al., 2014), or macular fluid in OCT scans of the retina (Schmidt-Erfurth et al., 2018) are examples of imaging biomarkers used in clinical routine. Training of highly accurate deep learning methods for the i dentification of imaging biomarkers has shown promising results reaching clinic...
Source: Medical Image Analysis - January 31, 2019 Category: Radiology Authors: Thomas Schlegl, Philipp Seeb öck, Sebastian M. Waldstein, Georg Langs, Ursula Schmidt-Erfurth Source Type: research
Novel and facile criterion to assess the accuracy of WSS estimation by 4D flow MRI
Cardiovascular disease (CVD) is known to have the highest mortality rate according to a recent report (Kochanek et al., 2016). In order to understand CVD, the hemodynamics of a cardiovascular flow needs to be investigated because a fluid flow plays a dominant role in a cardiovascular system. The phase-contrast magnetic resonance imaging (MRI) technique is an effective clinical modality that can obtain the vast quantities of information of both cardiovascular flow and anatomy simultaneously. The three-dimensional (3D) cine (time-resolved) phase-contrast cardiovascular magnetic resonance (CMR) with three-directional velocity...
Source: Medical Image Analysis - January 30, 2019 Category: Radiology Authors: Seungbin Ko, Byungkuen Yang, Jee-Hyun Cho, Jeesoo Lee, Simon Song Source Type: research
AAR-RT - A system for auto-contouring organs at risk on CT images for radiation therapy planning: Principles, design, and large-scale evaluation on head-and-neck and thoracic cancer cases
Cancer is a major public health problem worldwide and is the 2nd most common cause of death in the US, with ∼1.7 million new cancer cases expected to be diagnosed in the US in 2018, and with an estimated 609,640 American deaths to occur in 2018 (Siegal et al., 2018). Among several therapeutic options, nearly two thirds of cancer patients will have treatment that will involve radiation therapy (RT) (ASTR O website, 2018). Contouring of critical organs, called Organs at Risk (OARs), and target tumor in medical images taken for the purpose of RT planning (referred to as planning images) is required for accurate RT planning ...
Source: Medical Image Analysis - January 29, 2019 Category: Radiology Authors: Xingyu Wu, Jayaram K. Udupa, Yubing Tong, Dewey Odhner, Gargi V. Pednekar, Charles B. Simone, David McLaughlin, Chavanon Apinorasethkul, Ontida Apinorasethkul, John Lukens, Dimitris Mihailidis, Geraldine Shammo, Paul James, Akhil Tiwari, Lisa Wojtowicz, J Source Type: research
Multi-task Exclusive Relationship Learning for Alzheimer ’s Disease Progression Prediction with Longitudinal Data
Alzheimer ’s disease (AD), characterized by progressive impairment of memory and cognitive functions, is the most common type of dementia in elderly people. As life expectancy increases, the number of AD patients will also increase correspondingly, resulting in a heavy socio-economic burden (Fan et al., 2 008). It was reported that there are 26.6 million AD cases in the world in 2006, and about 56% of the cases are at the early stage (called mild cognitive impairment, MCI). In 2050, the AD population will increase to over 100 million (Brookmeyer et al., 2007). (Source: Medical Image Analysis)
Source: Medical Image Analysis - January 29, 2019 Category: Radiology Authors: Mingliang Wang, Daoqiang Zhang, Dinggang Shen, Mingxia Liu Source Type: research
Noise Reduction in Diffusion MRI Using Non-Local Self-Similar Information in Joint x −q Space
Diffusion MRI (DMRI) relies on its sensitivity to the displacement of water molecules to probe tissue microstructure. To be able to characterize fine microstructural details, the diffusion weighting (i.e., b-value) needs to be sufficiently high, allowing for example more accurate separation of fiber bundles crossing at small angles and greater sensitivity to the restricted diffusion of water molecules trapped inside axons. However, due to the significant attenuation of the MR signal at high diffusion weightings, the low signal-to-noise ratio (SNR) poses significant challenges to subsequent analysis. (Source: Medical Image Analysis)
Source: Medical Image Analysis - January 21, 2019 Category: Radiology Authors: Geng Chen, Yafeng Wu, Dinggang Shen, Pew-Thian Yap Source Type: research
Recurrent Inference Machines for Reconstructing Heterogeneous MRI Data
Magnetic Resonance Imaging (MRI) is used in a wide variety of research and clinical applications measuring soft tissue in the human body. Systems at multiple field strengths deploy several measuring sequences to produce the specific contrast for the intended purpose, including T1-, T2-, and -weighted images. The scanner measures data in the space of proton net-precession frequencies, known in MRI as k-space. Once enough samples in k-space are acquired to meet the Nyquist-criterion, the MR-image of tissue density can be computed through the inverse Fourier transform. (Source: Medical Image Analysis)
Source: Medical Image Analysis - January 18, 2019 Category: Radiology Authors: Kai L ønning, Patrick Putzky, Jan-Jakob Sonke, Liesbeth Reneman, Matthan W.A. Caan, Max Welling Source Type: research
Generalised coherent point drift for group-wise multi-dimensional analysis of diffusion brain MRI data
This study proposes a probabilistic approach for group-wise registration of generalised point sets comprising positions, associated axial orientations and scalar-valued measures. This is achieved through formulation of a hybrid mixture model (HdMM), combining suitable probability distributions to model disparate data features within a cohesive framework. (Source: Medical Image Analysis)
Source: Medical Image Analysis - January 17, 2019 Category: Radiology Authors: Nishant Ravikumar, Ali Gooya, Leandro Beltrachini, Alejandro F. Frangi, Zeike A. Taylor Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - January 16, 2019 Category: Radiology Source Type: research
Nonrigid reconstruction of 3D breast surfaces with a low-cost RGBD camera for surgical planning and aesthetic evaluation
Breast cancer is the most frequently diagnosed cancer site among women worldwide (Jemal et  al., 2011; Fitzmaurice et al., 2015). Despite increased incidence, mortality from breast cancer is declining with 10-year survival rates reaching 82% in Europe (De Angelis et al., 2014). A longer life expectancy after developing breast carcinoma in turn emphasizes the importance of aesthetic tr eatment outcome and late effects. Beside the oncological result, several studies have linked cosmetic and functional outcome to patients’ quality of life, mental health and self-image (Hau et al., 2013; Stanton et al., 2001). (Source:...
Source: Medical Image Analysis - January 11, 2019 Category: Radiology Authors: R.M. Lacher, F. Vasconcelos, N.R. Williams, G. Rindermann, J. Hipwell, D. Hawkes, D. Stoyanov Source Type: research
Training recurrent neural networks robust to incomplete data: application to Alzheimer ’s disease progression modeling
Alzheimer ’s disease (AD) is a chronic neurodegenerative disorder that begins with memory loss and develops over time, causing issues in conversation, orientation, and control of bodily functions (McKhann et al., 1984). Early diagnosis of the disease is challenging and is usually made once cognitive impair ment has already compromised daily living. Hence, developing robust, data-driven methods for disease progression modeling (DPM) utilizing longitudinal data is necessary to yield a complete perspective on the disease for better diagnosis, monitoring, and prognosis (Oxtoby and Alexander, 2017). (Source: Medical Image Analysis)
Source: Medical Image Analysis - January 11, 2019 Category: Radiology Authors: Mostafa Mehdipour Ghazi, Mads Nielsen, Akshay Pai, M. Jorge Cardoso, Marc Modat, S ébastien Ourselin, Lauge Sørensen Source Type: research
