Population shrinkage of covariance (PoSCE) for better individual brain functional-connectivity estimation
Functional magnetic resonance imaging (fMRI) reflects neural activity in the brain through the blood-oxygen-level-dependent (BOLD) signal. Task-free or resting-state experiments (r-fMRI) are used to estimate brain functional connectivity between brain structures or regions. These pairwise interactions capture patterns that can be linked to the cognitive, psychiatric, or neurological status of individuals. With the advent of large cohort studies, functional connectivity has been used in neuroimaging population analyses to study cognitive differences between individuals (Smith et al., 2015; Finn et al., 2015). (Source: Me...
Source: Medical Image Analysis - March 14, 2019 Category: Radiology Authors: Mehdi Rahim, Bertrand Thirion, Ga ël Varoquaux Source Type: research
Exploiting Structural Redundancy in q-space for Improved EAP Reconstruction from Highly Undersampled (k, q)-space in dMRI
Diffusion-weighted MRI (dMRI) is an imaging technique that allows for the inference of axonal fiber connectivity in biological tissues non-invasively by sensitizing the MR signal to water diffusion. The water diffusion process is fully characterized by the ensemble average propagator (EAP), defined in the displacement r-space at each location x. It is related to the dMR measurements in (k, q)-space through the 6D Fourier transform under the narrow pulse assumption (Callaghan, 1991):. (Source: Medical Image Analysis)
Source: Medical Image Analysis - March 12, 2019 Category: Radiology Authors: Jiaqi Sun, Alireza Entezari, Baba C. Vemuri Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - February 28, 2019 Category: Radiology Source Type: research
Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge
Tumor proliferation is an important biomarker indicative of the prognosis of breast cancer patients. Patients with high tumor proliferation have worse outcomes compared to patients with low tumor proliferation (van Diest et al., 2004). The assessment of tumor proliferation influences the clinical management of the patient – patients with aggressive tumors are treated with more aggressive therapies and patients with indolent tumor are given more conservative treatments that are preferred because of fewer side-effects (Fitzgibbons et al., 2000). (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 27, 2019 Category: Radiology Authors: Mitko Veta, Yujing J. Heng, Nikolas Stathonikos, Babak Ehteshami Bejnordi, Francisco Beca, Thomas Wollmann, Karl Rohr, Manan A. Shah, Dayong Wang, Mikael Rousson, Martin Hedlund, David Tellez, Francesco Ciompi, Erwan Zerhouni, David Lanyi, Matheus Viana, Source Type: research
Breast MRI and X-ray mammography registration using gradient values.
Breast cancer is the most common cancer in women worldwide. Current statistics have shown that 1 in 8 women will develop invasive breast cancer over the course of her lifetime (BreastCancer.org, 2017). Early detection through imaging increases the likelihood of overcoming the disease, motivating the implementation of screening programs. While X-ray mammography is considered the gold standard image modality for screening and diagnosis of breast diseases, magnetic resonance imaging (MRI) can be used to obtain complementary information, especially for women with an increased risk. (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 26, 2019 Category: Radiology Authors: Eloy Garc ía, Yago Diez, Oliver Diaz, Xavier Lladó, Albert Gubern-Mérida, Robert Martí, Joan Martí, Arnau Oliver Source Type: research
Deep-Learning based Multiclass Retinal Fluid Segmentation and Detection in Optical Coherence Tomography Images using a Fully Convolutional Neural Network
Optical coherence tomography (OCT) is an established imaging modality in ophthalmology providing micrometer-resolution 3D images of sub-surface biological tissue. It can be used to monitor disease progression, such as in diabetic macular edema (DME) or age-related macular degeneration (AMD) (Hee et al., 1995). High quality visualizations of the retinal structures provided by OCT images can improve the understanding of the onset and development of these retinal diseases, which are major causes of visual impairment (Joussen et al., 2010). (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 22, 2019 Category: Radiology Authors: Donghuan Lu, Morgan Heisler, Sieun Lee, Gavin Weiguang Ding, Eduardo Navajas, Marinko V. Sarunic, Mirza Faisal Beg Source Type: research
Medical Image Classification Using Synergic Deep Learning
The significance of digital medical imaging in the modern healthcare has led to the indispensable role of medical image analysis in the clinical therapy (Ghosh et al., 2011; de Bruijne, 2016; Kalpathy-Cramer et al., 2015). Medical image classification, a fundamental step in medical image analysis, aims to distinguish medical images according to a certain criterion, such as clinical pathologies or imaging modalities. A reliable medical image classification system is able to assist doctors in the fast and accurate interpretation of medical images. (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 18, 2019 Category: Radiology Authors: Jianpeng Zhang, Yutong Xie, Qi Wu, Yong Xia Source Type: research
Evaluating Reinforcement Learning Agents for Anatomical Landmark Detection
Accurate detection of anatomical landmarks from medical images is an essential step for many image analysis and interpretation methods. For instance, the localization of the anterior commissure (AC) and posterior commissure (PC) points in brain images is required to obtain the optimal view of the mid-sagittal plane. This can be used as an initial step for image registration (Ardekani et al., 1997) or for the identification of pathological anatomy (Stegmann et al., 2005). Another example is the automated localization of standard views such as 2- and 4-chamber views in cardiac MRI examinations. (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 14, 2019 Category: Radiology Authors: Amir Alansary, Ozan Oktay, Yuanwei Li, Loic Le Folgoc, Benjamin Hou, Ghislain Vaillant, Konstantinos Kamnitsas, Athanasios Vlontzos, Ben Glocker, Bernhard Kainz, Daniel Rueckert Source Type: research
Weakly Supervised Mitosis Detection in Breast Histopathology Images using Concentric Loss
The most widely used invasive breast cancer grading system is the Nottingham Grading System (Elston and Ellis, 1991), which consists of three components: nuclear pleomorphism, tubule formation and mitotic count. Among them, mitotic count is the most important one since the propagation of cancer is mainly governed by cell division. Generally, the mitosis figures are marked manually by pathologists on the Hematoxylin and Eosin (H&E) stained slides. Counting mitosis manually is very time-consuming and subjective, thus it is extremely useful to develop an automatic detection method, which is capable of making this process more...
Source: Medical Image Analysis - February 14, 2019 Category: Radiology Authors: Chao Li, Xinggang Wang, Wenyu Liu, Longin Jan Latecki, Bo Wang, Junzhou Huang Source Type: research
Iterative fully convolutional neural networks for automatic vertebra segmentation and identification
Segmentation and identification of the vertebrae is often a prerequisite for automatic analysis of the spine, such as detection of vertebral fractures (Yao et al., 2012), assessment of spinal deformities (Forsberg et al., 2013), or computer-assisted surgical interventions (Knez et al., 2016). Automatic spine analysis can be performed with a large variety of tomographic scans, including dedicated spine scans but also scans of the neck, chest or abdomen that incidentally cover part of the spine. A generic vertebra segmentation algorithm therefore needs to be robust with respect to different image resolutions and differen...
Source: Medical Image Analysis - February 12, 2019 Category: Radiology Authors: Nikolas Lessmann, Bram van Ginneken, Pim A. de Jong, Ivana I šgum Source Type: research
An Image Interpolation Approach for Acquisition Time Reduction in Navigator-Based 4D MRI
Involuntary motion of anatomical structures due to factors such as breathing, peristalsis and heart beat is an important concern in image-guided therapy applications, such as planning and guiding radiotherapy (Bert and Durante, 2011) and high intensity focused ultrasound therapy (Arnold et al., 2011). For instance, if such motion is not taken into account in radiotherapy, it may lead to dose distribution degradation (Lambert et al., 2005), reducing the efficacy of the treatment and irradiating healthy tissue. (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 12, 2019 Category: Radiology Authors: Neerav Karani, Lin Zhang, Christine Tanner, Ender Konukoglu Source Type: research
OBELISK-Net: Fewer Layers to Solve 3D Multi-Organ Segmentation with Sparse Deformable Convolutions
A series of recent research papers have demonstrated that convolutional encoder-decoder networks excel at object delineation tasks. This is very important for medical image understanding and analysis, since segmenting different organs, anatomies and pathologies lies at the core of computer-assistance for diagnosis and interventions (Litjens et al., 2017). While the performance of automated algorithms has rapidly and steadily increased since the advent of deep learning, there is limited knowledge of why certain architectural choices lead to empirically observed improvements. (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 12, 2019 Category: Radiology Authors: Mattias P. Heinrich, Ozan Oktay, Nassim Bouteldja Source Type: research
Constrained-CNN Losses for Weakly Supervised Segmentation
In the recent years, deep convolutional neural networks (CNNs) have been dominating semantic segmentation problems, both in computer vision and medical imaging, achieving ground-breaking performances when full-supervision is available (Long et al., 2015; Dolz et al., 2018; Litjens et al., 2017). In semantic segmentation, full supervision requires laborious pixel/voxel annotations, which may not be available in a breadth of applications, more so when dealing with volumetric data. Furthermore, pixel/voxel level annotations become a seri ous impediment for scaling deep segmentation networks to new object categories or tar...
Source: Medical Image Analysis - February 12, 2019 Category: Radiology Authors: Hoel Kervadec, Jose Dolz, Meng Tang, Eric Granger, Yuri Boykov, Ismail Ben Ayed Source Type: research
Optimal Surface Segmentation with Convex Priors in Irregularly Sampled Space
Optimal surface segmentation method for 3-D surfaces representing object boundaries is widely used in image understanding, object recognition and quantitative analysis of volumetric medical images (Li et al., 2006; Abràmoff et al., 2010; Withey and Koles, 2008). The optimal surface segmentation technique (Li et al., 2006) has been extensively employed for segmentation of complex objects and surfaces, such as knee bone and cartilage (Yin et al., 2010; Kashyap et al., 2013), heart (Wu et al., 2011; Zhang et al., 2013), airways and vessels tress (Liu et al., 2013; Bauer et al., 2014), lungs (Sun et al., 2013), liv...
Source: Medical Image Analysis - February 7, 2019 Category: Radiology Authors: Abhay Shah, Michael D. Abr ámoff, Xiaodong Wu Source Type: research
Multiple-correlation similarity for block-matching based fast CT to ultrasound registration in liver interventions
Computed tomography (CT) is a popular diagnostic imaging technique with high image resolution and, due to fast imaging speed, few motion artifacts. Vessels are not always clearly visible in CT. To image blood vessels, scans are performed after the administration of contrast material. With matrix array probes ultrasound (US) provides real-time 3D imaging. 2D US imaging is used as an intraoperative imaging modality, e.g. in thermal ablation tumor therapy. However, tumors are not always clearly visible in US. (Source: Medical Image Analysis)
Source: Medical Image Analysis - February 7, 2019 Category: Radiology Authors: Jyotirmoy Banerjee, Yuanyuan Sun, Camiel Klink, Renske Gahrmann, Wiro J. Niessen, Adriaan Moelker, Theo van Walsum Source Type: research
