Spatial Aggregation of Holistically-Nested Convolutional Neural Networks for Automated Pancreas Localization and Segmentation
Pancreas segmentation in computed tomography (CT) challenges current computer-aided diagnosis (CAD) systems. While automatic segmentation of numerous other organs in CT scans, such as the liver, heart or kidneys, achieves good performance with Dice similarity coefficients (DSCs) of > 90% (Wang et al., 2014c; Chu et al., 2013; Wolz et al., 2013), the pancreas’ variable shape, size, and location in the abdomen limits segmentation accuracy to (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 4, 2018 Category: Radiology Authors: Holger R. Roth, Le Lu, Nathan Lay, Adam P. Harrison, Amal Farag, Andrew Sohn, Ronald M. Summers Source Type: research
A novel multi-atlas strategy with dense deformation field reconstruction for abdominal and thoracic multi-organ segmentation from computed tomography
Non-invasive clinical assessment of the inner body is usually performed through medical imaging. Imaging modalities, such as magnetic resonance imaging (MRI) or computed tomography (CT), are used to evaluate multiple organs through a full or partial body acquisition. However, because of the huge amount of data acquired, a correct 3D assessment of the target structures is difficult and time-consuming to obtain. Thus, a multitude of (semi-)automatic segmentation techniques were presented and validated in research (Heimann and Meinzer, 2009; Iglesias and Sabuncu, 2015; Jimenez-Del-Toro et al., 2016). (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 2, 2018 Category: Radiology Authors: Bruno Oliveira, Sandro Queir ós, Pedro Morais, Helena R. Torres, João Gomes-Fonseca, Jaime C. Fonseca, João L. Vilaça Source Type: research
Conversion and Time-to-Conversion Predictions of Mild Cognitive Impairment using Low-Rank Affinity Pursuit Denoising and Matrix Completion
Alzheimer ’s disease (AD) (Association et al., 2016; 2017) is the most prevalent dementia and is commonly associated with progressive memory loss and cognitive decline. It is incurable and requires attentive care, thus imposing significant socio-economic burden on many nations. It is thus vital to detect A D in its earliest stage before its onset for possible therapeutic treatment. The prodromal stage of AD, called mild cognitive impairment (MCI), is characterized by mild but measurable decline of memory and cognition. (Source: Medical Image Analysis)
Source: Medical Image Analysis - January 23, 2018 Category: Radiology Authors: Kim-Han Thung, Pew-Thian Yap, Ehsan Adeli, Seong-Whan Lee, Dinggang Shen, Alzheimer ’s Disease Neuroimaging Initiative Source Type: research
How does the femoral cortex depend on bone shape? A methodology for the joint analysis of surface texture and shape
Hip fractures are the most common cause of acute orthopaedic hospital admission in older people (Parker and Johansen, 2006), with their annual incidence projected to rise worldwide from 1.7 million in 1990 to 6.3 million in 2050 (Sambrook and Cooper, 2006). Bone mineral density is currently the imaging biomarker of choice for assessing an individual ’s fracture risk, but although it is specific (Johnell et al., 2005; Kanis et al., 2008) it lacks sensitivity (Kanis et al., 2008; Kaptoge et al., 2008; Sanders et al., 2006), missing the majority who go on to fracture. (Source: Medical Image Analysis)
Source: Medical Image Analysis - January 19, 2018 Category: Radiology Authors: A.H. Gee, G.M. Treece, K.E.S. Poole Source Type: research
3D Multi-scale FCN with Random Modality Voxel Dropout Learning for Intervertebral Disc Localization and Segmentation from Multi-modality MR Images
Intervertebral discs (IVDs) are spine components that lie between each pair of adjacent vertebrae. They serve as shock absorbers in the spine and are crucial for vertebral movement. Disc degeneration (An et al., 2004; Urban and Roberts, 2003) is a common cause of back pain and stiffness for adults, and is a major public health problem in modern societies. Traditionally, studies on disc degeneration were done mainly by means of manual segmentation of the discs. Such a manual approach is, however, rath er tedious and time-consuming, and is often subject to inter- and intra-observer variabilities (Violas et al., 2007; Niem...
Source: Medical Image Analysis - January 17, 2018 Category: Radiology Authors: Xiaomeng Li, Qi Dou, Hao Chen, Chi-Wing Fu, Xiaojuan Qi, Daniel L. Belav ý, Gabriele Armbrecht, Dieter Felsenberg, Guoyan Zheng, Pheng-Ann Heng Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - January 13, 2018 Category: Radiology Source Type: research
Reviewers -- An acknowledgement
(Source: Medical Image Analysis)
Source: Medical Image Analysis - January 13, 2018 Category: Radiology Source Type: research
Low-dimensional representation of cardiac motion using Barycentric Subspaces: A new group-wise paradigm for estimation, analysis, and reconstruction
Many pathologies of the heart affect its motion during the cardiac cycle and therefore it is crucial for clinicians to have methods to understand and analyze the different patterns of motions seen in a population (Konstam et al., 2011). Efficient classification and quantification of the cardiac motion of a patient can help clinicians to have additional insights in order to help in diagnosis, therapy planning, and to determine the prognosis for a given patient (Bijnens et al., 2007). For example it can be used to extract relevant clinical indices such as the ejection fraction or strain values at different locations of ...
Source: Medical Image Analysis - December 22, 2017 Category: Radiology Authors: Marc-Michel Roh é, Maxime Sermesant, Xavier Pennec Source Type: research
Low-Dimensional Representation of Cardiac Motion Using Baryncetric Subspaces: a New Group-Wise Paradigm for Estimation, Analysis, and Reconstruction
Many pathologies of the heart affect its motion during the cardiac cycle and therefore it is crucial for clinicians to have methods to understand and analyze the different patterns of motions seen in a population Konstam et al. (2011). Efficient classification and quantification of the cardiac motion of a patient can help clinicians to have additional insights in order to help in diagnosis, therapy planning, and to determine the prognosis for a given patient Bijnens et al. (2007). For example it can be used to extra ct relevant clinical indices such as the ejection fraction or strain values at different locations of the...
Source: Medical Image Analysis - December 22, 2017 Category: Radiology Authors: Marc-Michel Roh é, Maxime Sermesant, Xavier Pennec Source Type: research
Long Term Safety Area Tracking (LT-SAT) with Online Failure Detection and Recovery for Robotic Minimally Invasive Surgery
The introduction of Robotics in Minimally Invasive Surgery (RMIS) allows overcoming many of the obstacles introduced by traditional laparoscopic techniques, by improving the surgeon ’s dexterity and the ergonomics during the surgical procedure, and restoring the surgeon’s hand-eye coordination (Bravo et al., 2016; Forgione, 2009; Lanfranco et al., 2004). Despite these benefits, the outcome of the surgical procedure can still be compromised by adverse events occurring dur ing the surgery. In robotic abdominal surgery, for example, one of the major complications is intra-operative bleeding due to injuries to vessels ...
Source: Medical Image Analysis - December 21, 2017 Category: Radiology Authors: Veronica Penza, Xiaofei Du, Danail Stoyanov, Antonello Forgione, Leonardo S. Mattos, Elena De Momi Source Type: research
Fast Elastic Registration of Soft Tissues under Large Deformations
A vast amount of research has been dedicated to deformable registration due to its potential clinical impact. Many methods have been proposed to address this complex task, and the solutions usually depend on the actual scenario and the type of data to be registered (Sotiras et al., 2013). Image registration has been widely addressed in the context of radiation therapy, intervention planning, intra-operative navigation and others. (Source: Medical Image Analysis)
Source: Medical Image Analysis - December 20, 2017 Category: Radiology Authors: Igor Peterl ík, Hadrien Courtecuisse, Robert Rohling, Purang Abolmaesumi, Christopher Nguan, Stéphane Cotin, Septimiu Salcudean Source Type: research
Enhancing interpretability of automatically extracted machine learning features: application to a RBM-Random Forest system on brain lesion segmentation
Machine learning approaches can be broadly divided into two categories: those using hand-crafted features, and those relying on Representation Learning techniques. Representation Learning refers to a set of general machine learning methods for automatic learning and extraction of features directly from data. By contrast, hand-crafted features require expert knowledge on the problem, hence making them more problem-dependent (LeCun et al., 2015). Notwithstanding, there is usually a data representation mapping stage that takes the input data and transforms it into a more discriminative representation. (Source: Medical Image Analysis)
Source: Medical Image Analysis - December 19, 2017 Category: Radiology Authors: S érgio Pereira, Raphael Meier, Richard McKinley, Roland Wiest, Victor Alves, Carlos A. Silva, Mauricio Reyes Source Type: research
The first MICCAI challenge on PET tumor segmentation
Positron Emission Tomography (PET) / Computed Tomography (CT) is established today as an important tool for patients management in oncology, cardiology and neurology. In oncology especially, fluorodeoxyglucose (FDG) PET is routinely used for diagnosis, staging, radiotherapy planning, and therapy monitoring and follow-up (Bai et al., 2013). After data acquisition and image reconstruction, an important step for exploiting the quantitative content of PET/CT images is the region of interest (ROI) determination that allows extracting semi-quantitative metrics such as mean or maximum standardized uptake values (SUV). (Source: Me...
Source: Medical Image Analysis - December 9, 2017 Category: Radiology Authors: Mathieu Hatt, Baptiste Laurent, Anouar Ouahabi, Hadi Fayad, Shan Tan, Laquan Li, Wei Lu, Vincent Jaouen, Clovis Tauber, Jakub Czakon, Filip Drapejkowski, Witold Dyrka, Sorina Camarasu-Pop, Fr édéric Cervenansky, Pascal Girard, Tristan Glatard, Michael K Source Type: research
Autocalibration Method for Non-stationary CT Bias Correction
Computed tomographic imaging has become almost universally available in clinical and research settings. Since its introduction, it has grown to be part of routine clinical practice, and it is estimated that over 80 million CT scans are performed each year in the United States (Hess et al., 2014). While it continues to provide new insight into the characterization and prognostication of disease, this high utilization has also raised concerns about the implications of radiation exposure to clinical populations (Brenner and Hall, 2007). (Source: Medical Image Analysis)
Source: Medical Image Analysis - December 8, 2017 Category: Radiology Authors: Gonzalo Vegas-S ánchez-Ferrero, Maria J. Ledesma-Carbayo, George R. Washko, Raúl San José Estépar Source Type: research
Robust MR elastography stiffness quantification using a localized divergence free finite element reconstruction
Tissue stiffness is considered a valuable clinical marker as abnormalities - such as tumors, inflamation, or fibrosis - can fundamentally alter tissue structure, leading to significant variations in material properties. In the case of tumors, factors such as angiogenesis, increase in cell stiffness, and compaction of surrounding tissue alter homeostatic conditions (Krouskop et al., 1998; Paszek et al., 2005). In liver fibrosis, scarring occurs in the liver, yielding an increased collagen density in the extracellular matrix (Bataller and Brenner, 2005; Yeh et al., 2002). (Source: Medical Image Analysis)
Source: Medical Image Analysis - December 8, 2017 Category: Radiology Authors: Daniel Fovargue, Sebastian Kozerke, Ralph Sinkus, David Nordsletten Source Type: research
