Measuring rib cortical bone thickness and cross section from CT
The ribs play a key structural role in the thorax by protecting vital organs from injury during loading from falls, motor vehicle crashes (MVCs), and other blunt impact trauma. Rib fractures occur in over 10% of injured patients and, particularly in the elderly, are a significant clinical concern (Ziegler and Agarwal, 1994). Their presence is associated with increased morbidity, increased mortality, and poorer patient outcomes including longer hospital stays and higher rates of pneumonia (Bergeron et al., 2003; Lee et al., 2006; Brasel et al., 2006). (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 10, 2018 Category: Radiology Authors: Sven A. Holcombe, Eunjoo Hwang, Brian A. Derstine, Stewart C. Wang Source Type: research
Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration
Multimodal image registration aims to spatially align medical images produced from different imaging modalities. Among many other medical imaging applications, this is useful in minimally- or none-invasive image-guided procedures, in which a common strategy is to fuse the detailed diagnostic information from quality pre-procedural images with intra-procedural imaging that is typically restricted by the interventional requirements, such as portability, accessibility, temporal resolution, limited field of view and controlled dosage for contrast agent or radiation. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 4, 2018 Category: Radiology Authors: Yipeng Hu, Marc Modat, Eli Gibson, Wenqi Li, Nooshin Ghavami, Ester Bonmati, Guotai Wang, Steven Bandula, Caroline M. Moore, Mark Emberton, S ébastien Ourselin, J. Alison Noble, Dean C. Barratt, Tom Vercauteren Source Type: research
Synthesizing Retinal and Neuronal Images with Generative Adversarial Nets
A broad range of biomedical images contain thin and long tubular-like foreground objects. They include tubular structured images of various modalities such as magnetic resonance angiography, x-ray angiography, retinal fundus images, as well as cellular neuronal images. Taking retinal fundus images as an example, topological and geometrical properties (Martinez-Perez et al., 2000) of the vessel structures provide valuable clinical information in diagnosing diseases such as proliferative diabetic retinopathy, glaucoma, and hypertensive retinopathy (Abramoff et al., 2010). (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 4, 2018 Category: Radiology Authors: He Zhao, Huiqi Li, Sebastian Maurer-Stroh, Li Cheng Source Type: research
A Cortical Shape-Adaptive Approach to Local Gyrification Index
Cortical gyrification is a dynamic process involving cortical expansion, sharpening of gyri and deepening of sulci in early brain development, followed by flattening and opening of sulci and narrowing of gyral crowns with aging (Zilles et al., 1988; 1989; Armstrong et al., 1995). The process of gyrification is often studied from a maturational perspective by tracing global or local developmental trajectories over time. Additionally, it has been shown that local cortical gyrification is related to brain development (Zilles et al., 1988; Armstrong et al., 1995; Luders et al., 2004; Lui et al., 2011; Li et al., 2014b;...
Source: Medical Image Analysis - July 2, 2018 Category: Radiology Authors: Ilwoo Lyu, Sun Hyung Kim, Jessica B. Girault, John H. Gilmore, Martin A. Styner Source Type: research
Slice-level diffusion encoding for motion and distortion correction
Diffusion MRI (dMRI) offers a unique observation window into tissue microstructure in-vivo Le Bihan et al. (1986). Increasingly advanced biophysical modelling techniques for dMRI allow insight into microscopic tissue properties, such as axon diameter Assaf et al. (2008); Alexander et al. (2010), neurite morphology Zhang et al. (2012), global connectivity patterns Tournier et al. (2012); Wedeen et al. (2008); Steven et al. (2014) and cell size and density Panagiotaki et al. (2015). These techniques demand a rich dMRI acquisition for accurate parameter estimation, namely a high number of samples varying in direction...
Source: Medical Image Analysis - June 25, 2018 Category: Radiology Authors: Jana Hutter, Daan Christiaens, Torben Schneider, Lucilio Cordero-Grande, Paddy J Slator, Maria Deprez, Anthony N Price, Donald Tournier, Mary Rutherford, Joseph V Hajnal Source Type: research
Towards Intelligent Robust Detection of Anatomical Structures in Incomplete Volumetric Data
In routine clinical practice, the radiologist is required to read and interpret a large variety of medical image scans and produce a corresponding report (Lang et al., 2013). 3D Computed Tomography (CT) is typically used to support diagnosis of brain hemorrhages, brain tumors and aneurysms, detection of complex bone fractures, advanced cancer screening, radiation therapy, and so on (Hess et al., 2014). The process of reading 3D-CT scans is parti cularly tedious, considering the large size of the scans, quantitative reporting requirements or image quality limitations due to reconstruction artifacts (Barrett and Keat, ...
Source: Medical Image Analysis - June 23, 2018 Category: Radiology Authors: Florin C. Ghesu, Bogdan Georgescu, Sasa Grbic, Andreas Maier, Joachim Hornegger, Dorin Comaniciu Source Type: research
Deep Learning and Conditional Random Fields-based Depth Estimation and Topographical Reconstruction from Conventional Endoscopy
Colorectal cancer (CRC) is the third most commonly diagnosed cancer in the United States (Siegel et al., 2017). Colonoscopy screening can significantly reduce colorectal cancer mortality by detecting and removing premalignant lesions. However, this approach has well-known limitations (Baxter et al., 2009; Ransohoff, 2009) and recent studies have suggested that gastroenterologists can easily mis s more than 20% of clinically relevant polyps (Kim et al., 2007; Leufkens et al., 2012; Pabby et al., 2005; Van Rijn et al., 2006). (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 13, 2018 Category: Radiology Authors: Faisal Mahmood, Nicholas J. Durr Source Type: research
Dual-modality endoscopic probe for tissue surface shape reconstruction and hyperspectral imaging enabled by deep neural networks
In the past several decades, the development of technology has boosted the emergence of new surgical approaches. Minimal access surgery (MAS), for example, has limited trauma to the patient by using smaller incisions resulting in reduced blood loss, less pain, fewer infections, quicker recovery and improved quality of life (Velanovich, 2000; Darzi and Mackay, 2002). However, MAS also brings challenges to surgeons, such as the lack of tactile feedback, reduced depth perception, limited dexterity of surgical instruments and difficult hand-eye coordination, all of which contribute to a steeper learning curve. (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 11, 2018 Category: Radiology Authors: Jianyu Lin, Neil T. Clancy, Ji Qi, Yang Hu, Taran Tatla, Danail Stoyanov, Lena Maier Hein, Daniel S. Elson Source Type: research
Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features
Brain structure segmentation in Magnetic Resonance Images (MRI) is one of the major interests in medical practice due to its various applications, including pre-operative evaluation and surgical planning, radiotherapy treatment planning, longitudinal monitoring for disease progression or remission (Kikinis et al., 1996; Phillips et al., 2015; Pitiot et al., 2004), etc. The sub-cortical structures (i.e. thalamus, caudate, putamen, pallidum, hippocampus, amygdala, and accumbens) have attracted the interest of the research community for a long time, since their morphological changes are frequently assoc iated with psychia...
Source: Medical Image Analysis - June 11, 2018 Category: Radiology Authors: Kaisar Kushibar, Sergi Valverde, Sandra Gonz ález-Villá, Jose Bernal, Mariano Cabezas, Arnau Oliver, Xavier Lladó Source Type: research
3D Freehand Ultrasound Without External Tracking Using Deep Learning
Ultrasound imaging (US) combines a number of advantages as a medical modality: it is affordable, safe for both the patient and the clinician, and is convenient to set up and use. This unique combination of properties makes it one of the most popular imaging modalities for both diagnostic and interventional applications. For a long time though, the range of its applications was limited due to its inability to produce three-dimensional data, which is required for many clinical scenarios, for instance to reliably measure the extent of structures of interest, or to perform registration with pre-operative data. (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 8, 2018 Category: Radiology Authors: Raphael Prevost, Mehrdad Salehi, Simon Jagoda, Navneet Kumar, Julian Sprung, Alexander Ladikos, Robert Bauer, Oliver Zettinig, Wolfgang Wein Source Type: research
Temporal and Volumetric Denoising via Quantile Sparse Image Prior
The reliable reduction of image noise poses a constantly recurring problem in todays imaging systems. In healthcare, noise may limit the reliability of medical image data for subsequent clinical workflows. For instance, in radiology using computed tomography (CT) or related morphological imaging modalities, noise affects the analysis of anatomical structures and thus impedes diagnostic applications. In optical coherence tomography (OCT) for retinal imaging as another example use case, noise limits the measurement of structural features in the human eye, e. g. (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 6, 2018 Category: Radiology Authors: Franziska Schirrmacher, Thomas K öhler, Jürgen Endres, Tobias Lindenberger, Lennart Husvogt, James G. Fujimoto, Joachim Hornegger, Arnd Dörfler, Philip Hoelter, Andreas K. Maier Source Type: research
Tracing Cell Lineages in Videos of Lens-free Microscopy
Cell growth and migration play key roles in cancer progression: abnormal cell growth can lead to formation of tumors and cancer cells can spread to other parts of the body, a process known as metastasis. In order to understand these mechanisms, in vitro experiments are essential. Such experiments allow, for example, to compare the behaviour of modified and wildtype cell lines or measure the influence of certain chemicals on the cells culture, and can therefore be designed to gain insights into biological processes. (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 4, 2018 Category: Radiology Authors: Markus Rempfler, Valentin Stierle, Konstantin Ditzel, Sanjeev Kumar, Philipp Paulitschke, Bjoern Andres, Bjoern H. Menze Source Type: research
Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer ’s Disease
Large scale collaborative initiatives and consortiums, like the Alzheimer ’s Disease Neuroimaging Initiative (ADNI), the Enhancing NeuroImaging Genetics through Meta-Analysis (ENIGMA) consortium (Thompson et al., 2014) and the International Neuroimaging Data-sharing Initiative (INDI)4, acquire and share hundreds of terabytes of imaging, genetic, phenotypic and behavio ural data in an effort to facilitate the discovery of novel biomarkers and better understand disease mechanisms. This ever-increasing volume of imaging and non-imaging information that is collected and shared among researchers stresses the need for comput...
Source: Medical Image Analysis - June 2, 2018 Category: Radiology Authors: Sarah Parisot, Sofia Ira Ktena, Enzo Ferrante, Matthew Lee, Ricardo Guerrero, Ben Glocker, Daniel Rueckert Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - June 1, 2018 Category: Radiology Source Type: research
A Deep Learning Approach for Real Time Prostate Segmentation in Freehand Ultrasound Guided Biopsy
Prostate cancer is the second most common cancer in men; each year there are approximately 1.6 million new cases diagnosed worldwide Fitzmaurice et al. (2017). The established, widely available, standard diagnostic tool for prostate cancer is transrectal ultrasound (TRUS)-guided biopsy Verma et al. (2017), which involves obtaining around 12 prostate tissue samples using a systematic, yet, non-targeted approach. This scheme i s blind to individual patient intraprostatic pathology, and has a high rate of false negatives. (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 1, 2018 Category: Radiology Authors: Emran Mohammad Abu Anas, Parvin Mousavi, Purang Abolmaesumi Source Type: research
