Tissue Microstructure Estimation Using a Deep Network Inspired by a Dictionary-based Framework
Neurite morphology provides important information for the understanding of brain development (Conel, 1939), aging (Jacobs et al., 1997), and disorders (Evangelou et al., 2000; Paula-Barbosa et al., 1980; Fiala et al., 2002). By capturing the anisotropic pattern of water displacement in the neuronal tissue, diffusion magnetic resonance imaging (dMRI) allows noninvasive assessment of the complex tissue microstructure and is thus a valuable tool for in vivo investigation of neurite morphology (Johansen-Berg and Behrens, 2013). (Source: Medical Image Analysis)
Source: Medical Image Analysis - September 6, 2017 Category: Radiology Authors: Chuyang Ye Source Type: research
Discriminative Confidence Estimation for Probabilistic Multi-atlas Label Fusion
Brain segmentation from magnetic resonance imaging (MRI) is an important preprocessing step for many neuroimaging studies, e.g., volumetry, cortical thickness, etc. For this task, automatic methods are desirable over manual segmentation since the latter is very time-consuming and subject to inter- and intra-rater variability. Although good outcomes can be achieved for the segmenation of the main tissues based only on image intensities (Leemput et al., 1999; Ashburner and Friston, 2005; Shattuck et al., 2001), segmentation of anatomical structures (e.g., defined by their functional properties) renders intensity informat...
Source: Medical Image Analysis - September 1, 2017 Category: Radiology Authors: Oualid M. Benkarim, Gemma Piella, Miguel Angel Gonz ález Ballester, Gerard Sanroma, for the Alzheimer’s Disease Neuroimaging Initiative Source Type: research
Multivariate Brain Network Graph Identification in Functional MRI
Human brain is a complex network of different but functionally coupled brain regions (van den Heuvel and Pol, 2010). This functional coupling of regions in literature is known as functional integration (Razi and Friston, 2016). A number of neuroimaging modalities such as Electroencephalogram (EEG), Magnetoencephalography (MEG), and Positron emission tomography (PET) are being used to r eveal brain’s complex functional network model (Cabral et al., 2014). Functional magnetic resonance imaging (fMRI) is one of the powerful non-invasive neuroimaging modalities that studies human brain functional network model. (Source: M...
Source: Medical Image Analysis - August 29, 2017 Category: Radiology Authors: Priya Aggarwal, Anubha Gupta, Ajay Garg Source Type: research
CorteXpert: A Model-based Method for Automatic Renal Cortex Segmentation
Kidney cancer is a life-threatening disease with a high mortality rate and poor prognosis all over the world, with 338,000 new cases diagnosed in 2012 (Ferlay et al., 2013). Renal cell carcinoma, which arises from the renal cortex, is the most common type of kidney cancer in adults, responsible for approximately 80% of cases (Garcia et al., 2009). There is a lot of evidence to show that partial nephrectomy has become the first treatment of selective renal tumors, with equivalent oncological cure and better preservation of renal function compared to radical nephrectomy (Russo and Huang, 2008; Clark et al., 2011; Shao et...
Source: Medical Image Analysis - August 23, 2017 Category: Radiology Authors: Dehui Xiang, Ulas Bagci, Chao Jin, Fei Shi, Weifang Zhu, Jianhua Yao, Milan Sonka, Xinjian Chen Source Type: research
Co-Trained Convolutional Neural Networks for Automated Detection of Prostate Cancer in Multi-parametric MRI
Prostate cancer (PCa) is one of the most lethal cancers with a high incidence rate. It has been reported that there are 180,890 newly diagnosed patients and 26,120 deaths caused by PCa in 2016 (Siegel et al., 2016). The number of PCa diagnoses is expected to increase to 1,700,000 globally by 2030, and could result in up to 500,000 related deaths annually (Maddams et al., 2012). Early detection and risk assessment of PCa with a proper treatment can effectively prevent it from progressing to advanc ed metastatic disease, greatly increasing the survival rate of patients and maintaining the quality of patients’ life. (Sou...
Source: Medical Image Analysis - August 22, 2017 Category: Radiology Authors: Xin Yang, Chaoyue Liu, Zhiwei Wang, Jun Yang, Hung Le Min, Liang Wang, Kwang-Ting (Tim) Cheng Source Type: research
Constructing Fine-granularity Functional Brain Network Atlases via Deep Convolutional Autoencoder
Understanding the organizational architecture of human brain function has been of intense interest since the inception of human neuroscience. After decades of active research using in-vivo functional neuroimaging techniques such as fMRI (Heeger and Ress, 2002), there has been mounting evidence (Dosenbach et al., 2006; Duncan, 2010; Fedorenko et al., 2013; Fox et al., 2005; Pessoa et al., 2012) that the human brain function emerges from and is realized by the interaction of multiple concurrent neural processes or networks, each of wh ich is spatially distributed across specific structural substrate of neuroanatomical...
Source: Medical Image Analysis - August 17, 2017 Category: Radiology Authors: Yu Zhao, Qinglin Dong, Hanbo Chen, Armin Iraji, Yujie Li, Milad Makkie, Zhifeng Kou, Tianming Liu Source Type: research
Learning and combining image neighborhoods using random forests for neonatal brain disease classification
During early childhood, the brain undergoes complex structural changes, which makes it challenging to characterize and quantify normal and abnormal brain development. Depending on the condition occurring during the pregnancy, brain structure could have overt lesions or more subtle and general structural changes that could make it difficult to quantify these changes. The diagnostic and subsequent therapy, however, often relies only on one dimensional measurements, such as the width of the ventricles in a specific plane manually determined by the experts. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 9, 2017 Category: Radiology Authors: Veronika A. Zimmer, Ben Glocker, Nadine Hahner, Elisenda Eixarch, Gerard Sanroma, Eduard Gratac ós, Daniel Rueckert, Miguel Ángel González Ballester, Gemma Piella Source Type: research
3D/2D Registration with Superabundant Vessel Reconstruction for Cardiac Resynchronization Therapy
Patients with advanced drug-refractory heart failure can be safely treated with Cardiac Resynchronization Therapy (CRT). However, 3040 % of patients do not respond to therapy (Claridge et al., 2015). In this procedure, a CRT device is implanted using fluoroscopic image guidance. The device has 3 leads which are placed in the right atrium, right ventricle and through the coronary sinus (CS) on the surface of the left ventricle (LV). Suboptimal placement of the lead on the LV has be en identified as a leading cause of non-response. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 5, 2017 Category: Radiology Authors: Daniel Toth, Maria Panayiotou, Alexander Brost, Jonathan M. Behar, Christopher A. Rinaldi, Kawal S. Rhode, Peter Mountney Source Type: research
MR-based respiratory and cardiac motion correction for PET imaging
The hybrid Positron-Emission Tomography (PET) and Magnetic Resonance (MR) technology offers the possibility to combine the high resolution of MR imaging (MRI) with the high molecular sensitivity of PET. This enables simultaneous whole-body data acquisition and fusion of the non-invasive multifunctional MRI with the molecular information of PET. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 3, 2017 Category: Radiology Authors: Thomas K üstner, Martin Schwartz, Petros Martirosian, Sergios Gatidis, Ferdinand Seith, Christopher Gilliam, Thierry Blu, Hadi Fayad, Dimitris Visvikis, F. Schick, B. Yang, H. Schmidt, N.F. Schwenzer Source Type: research
Registration and Fusion Quantification of Augmented Reality based Nasal Endoscopic Surgery
Minimizing surgical invasion of resecting tumors in skull base has drawn continuous attention because of the recent advancements in endoscopic imaging. The image-guided approach, which improves the visibility in lesion areas, is subject to severe constraints of composite influential factors. The geometrical complexity of skull anatomic structure and delicate coupling with adjacent cranial nerves and internal carotid artery are intrinsic factors that much likely extend surgery duration and risk (Nicolau et al., 2011; Sugimoto, 2010). (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 3, 2017 Category: Radiology Authors: Yakui CHU, Jian YANG, Danni AI, Wenjie Li, Hong SONG, Liang LI, Shaodong MA, Duanduan CHEN, Lei CHEN, Yongtian WANG Source Type: research
Ensemble of Expert Deep Neural Networks for Spatio-Temporal Denoising of Contrast-Enhanced MRI Sequences
Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) of the brain is a noninvasive, in vivo tool to detect and quantify pathologies based on contrast agent (CA) accumulation (Tofts, 2005). The acquisition technique involves repeated T1 weighted imaging of tissues before, during and after the injection of a CA. The CA changes the tissue ’s T1 relaxation time (Tofts and Kermode, 1991), which manifests as signal enhancement (see Fig. 1). The frequency of MRI acquisitions (temporal sampling rate) in DCE-MRI should be sufficiently high to fully capture the dynamics of the CA. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 2, 2017 Category: Radiology Authors: A. Benou, R. Veksler, A. Friedman, T. Riklin Raviv Source Type: research
Supervised Graph Hashing for Histopathology Image Retrieval and Classification
Histopathology plays an important role in the early diagnosis of different cancers, such as lung and breast cancers. However, manual examination of histopathological images is labor intensive, time consuming and error-prone due to high-resolution and subjective assessment of doctors. To reduce the workload of pathologists and provide more reliable and consistent analysis of histopathological images, image process techniques and modern machine learning algorithms have been widely used for medical diagnosis, disease detection and decision support (Petushi et al., 2006; Yang et al., 2007; Caicedo et al., 2009; Basavanh...
Source: Medical Image Analysis - August 1, 2017 Category: Radiology Authors: Xiaoshuang Shi, Fuyong Xing, Kadi Xu, Yuanpu Xie, Hai Su, Lin Yang Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - July 30, 2017 Category: Radiology Source Type: research
New methods for the geometrical analysis of tubular organs
Tubular organ analysis is essential for the physiological understanding of this kind of organs and for the characterization of related diseases. Many major diseases involve tubular organs. For instance, in the case of airway-trees, chronic obstructive pulmonary disease (COPD) has been reported to be one of the major causes of death (Murray and Lopez, 1996). Another example is coronary heart disease, which is linked to obstructed vessels, and is the first cause of death in the US (Members et al., 2008). (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 28, 2017 Category: Radiology Authors: Florent Gr élard, Fabien Baldacci, Anne Vialard, Jean-Philippe Domenger Source Type: research
A competitive strategy for atrial and aortic tract segmentation based on deformable models
Multiple strategies have previously been described for atrial region (i.e. atrial bodies and aortic tract) segmentation. Although these techniques have proven their accuracy, inadequate results in the mid atrial walls are common, restricting their application for specific cardiac interventions. In this work, we introduce a novel competitive strategy to perform atrial region segmentation with correct delineation of the thin mid walls, and integrated it into the B-spline Explicit Active Surfaces framework. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 28, 2017 Category: Radiology Authors: Pedro Morais, Jo ão L. Vilaça, Sandro Queirós, Felix Bourier, Isabel Deisenhofer, João Manuel R.S. Tavares, Jan D'hooge Source Type: research
