Segmentation and classification in MRI and US fetal imaging: Recent trends and future prospects
Prenatal imaging technology for fetal diagnosis has rapidly evolved (Yan (2017)). Two-dimensional ultrasound (2D US) is the primary screening modality for pregnancy evaluation because of its relative low cost, real-time imaging, lack of harmful effects to both fetus and mother, and high resolution. Three- and four -dimensional ultrasound (3D / 4D US) with additional sonography modalities such as color / power Doppler are increasingly available and have been successfully employed to detect fetal structural abnormalities (Roy-Lacroix et al. (Source: Medical Image Analysis)
Source: Medical Image Analysis - October 19, 2018 Category: Radiology Authors: Jordina Torrents-Barrena, Gemma Piella, Narc ís Masoller, Eduard Gratacós, Elisenda Eixarch, Mario Ceresa, Miguel Ángel González Ballester Source Type: research
Fully Convolutional Multi-scale Residual DenseNets for Cardiac Segmentation and Automated Cardiac Diagnosis using Ensemble of Classifiers
Cardiac cine Magnetic Resonance (MR) Imaging is primarily used for assessment of cardiac function and diagnosis of Cardiovascular diseases (CVDs). Cardiac MRI is considered the most accurate method for the estimation of clinical parameters such as ejection fraction, ventricular volumes, stroke volume and myocardial mass. Delineating important organs and structures from volumetric medical images, such as MR and computed tomography (CT) images, is usually considered the primary step for estimating clinical parameters, disease diagnosis, prediction of prognosis and surgical planning. (Source: Medical Image Analysis)
Source: Medical Image Analysis - October 19, 2018 Category: Radiology Authors: Mahendra Khened, Varghese Alex, Ganapathy Krishnamurthi Source Type: research
Improvement of fully automated airway segmentation on volumetric computed tomographic images using a 2.5 dimensional convolutional neural net
Multi-detector computerized tomography (MDCT) offers volumetric images of the airway tree geometry at the sublobal level with submillimeter resolution. Quantifying the peripheral geometry from MDCT images is important for diagnosis and treatment planning of pulmonary diseases involving airway pathology, such as chronic obstructive pulmonary disease (COPD), cystic fibrosis, and interstitial lung diseases (Barnes and Hansel, 2004; Pu et al., 2012). Airway tree segmentation plays an especially important role in pulmonary disease analysis because it quantifies the anatomical features, including the airway wall thickening, wall...
Source: Medical Image Analysis - October 19, 2018 Category: Radiology Authors: Jihye Yun, Jinkon Park, Donghoon Yu, Jaeyoun Yi, Minho Lee, Hee Jun Park, June-Goo Lee, Joon Beom Seo, Namkug Kim Source Type: research
Recovery of 3D rib motion from dynamic chest radiography and CT data using local contrast normalization and articular motion model
The rib cage, lungs, and thoracic muscles cooperatively contribute to the pulmonary function. Since the rib cage mobility is a key factor in the respiratory motion partly in relation with spine deformity, analysis of the rib cage motion has received considerable attention and its importance was pointed out especially on the patients with chronic obstructive pulmonary disease (COPD) (Gilmartin and Gibson, 1986), kyphosis (Culham et al., 1994), scoliosis (Tanaka et al., 2015), and so on. Clinically available systems for accurate rib cage motion analysis are required for diagnosis of these patients. (Source: Medical Image Analysis)
Source: Medical Image Analysis - October 18, 2018 Category: Radiology Authors: Yuta Hiasa, Yoshito Otake, Rie Tanaka, Shigeru Sanada, Yoshinobu Sato Source Type: research
Mind the gap: quantification of incomplete ablation patterns after pulmonary vein isolation using minimum path search
Around 33.5 million people suffer from atrial fibrillation (AF) worldwide (Chugh et al., 2014), the most frequent class of arrhythmia. The origin of AF is the appearance of rapid abnormal electrical signals activating the atrium in a disorganized way. Most of these abnormal electrical currents originate inside the pulmonary veins (Haissaguerre et al., 1998). Pulmonary vein isola tion (PVI), which aims to electrically isolate the PVs from the main atrial body, is a common treatment, especially for patients not responding to medication. (Source: Medical Image Analysis)
Source: Medical Image Analysis - October 10, 2018 Category: Radiology Authors: Marta Nu ñez-Garcia, Oscar Camara, Mark D. O’Neill, Reza Razavi, Henry Chubb, Constantine Butakoff Source Type: research
A hybrid camera- and ultrasound-based approach for needle localization and tracking using a 3D motorized curvilinear ultrasound probe
Several diagnostic and therapeutic clinical procedures, such as biopsy, therapeutic injection, nerve block, and anesthesia, involve needle interventions. These procedures require accurate needle localization and tracking to improve the success rate of the intervention and reduce the incidence of undesired complications. Ultrasound imaging, which provides a low-cost, real-time, and noninvasive imaging modality, is widely used to guide needle insertion interventions (Holm and Skjoldbye, 1996; Wisniewski et al., 2010). (Source: Medical Image Analysis)
Source: Medical Image Analysis - October 3, 2018 Category: Radiology Authors: Mohammad I. Daoud, Abdel-Latif Alshalalfah, Otmane Ait Mohamed, Rami Alazrai Source Type: research
Automatic Grading of Prostate Cancer in Digitized Histopathology Images: Learning from Multiple Experts
With an estimated number of 161,360 new cases and 26,730 deaths in 2017, prostate cancer (PCa) is the second most commonly diagnosed cancer, and third most common cause of cancer death among American men Siegel et al. (2017). PCa is a heterogeneous disease and is manifested in a diverse range of histologic patterns. The Gleason score Gleason (1966) is currently the most common grading system of prostate adenocarcinoma, and proven to be a clinically relevant prognostic marker. The grade is determined by path ologists based on the glandular architectural features observed in haematoxylin and eosin (H&E) stained samples. (S...
Source: Medical Image Analysis - September 24, 2018 Category: Radiology Authors: Guy Nir, Soheil Hor, Davood Karimi, Ladan Fazli, Brian F. Skinnider, Peyman Tavassoli, Dmitry Turbin, Carlos F. Villamil, Gang Wang, R. Storey Wilson, Kenneth A. Iczkowski, M. Scott Lucia, Peter C. Black, Purang Abolmaesumi, S. Larry Goldenberg, Septimiu Source Type: research
Local spatio-temporal encoding of raw perfusion MRI for the prediction of final lesion in stroke
Cerebrovascular diseases represent a leading cause of disability and mortality worldwide (Towfighi and Saver, 2011; Feigin et al., 2014; Murray et al., 2015). Ischemic stroke ( 85% of all stroke cases) results from an acute occlusion of a cerebral artery. Early restoration of blood flow within the ischemic tissue (reperfusion), using intravenous thrombolysis and/or mechanical thrombectomy, is the most effective therapy to reduce infarct growth and promote clinical recovery (Goyal et al., 2016). The clinical benefit of reperfusion is highly dependent on the extent of the ischemic, but still viable, cerebral tissue (i....
Source: Medical Image Analysis - September 23, 2018 Category: Radiology Authors: Mathilde Giacalone, Pejman Rasti, Noelie Debs, Carole Frindel, Tae-Hee Cho, Emmanuel Grenier, David Rousseau Source Type: research
Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections
Histology is the study of tissue microanatomy. Histological analysis involves cutting a wax-embedded or frozen block of tissue into very thin sections (in the order of 10 microns), which are subsequently stained, mounted on glass slides, and examined under the microscope. Using different types of stains, different microscopic structures can be enhanced and studied. Moreover, mounted sections can be digitised at high resolution – in the order of a micron. Digital histological sections not only enable digital pathology in a clinical setting, but also open the door to an array of image analysis applications. (Source: Medical Image Analysis)
Source: Medical Image Analysis - September 22, 2018 Category: Radiology Authors: Juan Eugenio Iglesias, Marc Modat, Lo ïc Peter, Allison Stevens, Roberto Annunziata, Tom Vercauteren, Ed Lein, Bruce Fischl, Sebastien Ourselin, for the Alzheimer’s Disease Neuroimaging Initiative Source Type: research
A pilot study using kernelled support tensor machine for distant failure prediction in lung SBRT
Non-small cell lung cancer (NSCLC) is the most common type of lung cancer worldwide (World Health Organization, 2017). Approximately of NSCLC patients present with early-stage, localized disease that can be controlled upon receiving treatment with curative-intent (Howlader N, 2016), although this number may rise with the recent implementation of CT-based screening programs (Team, 2013). In general, surgery has been the standard treatment for early stage NSCLC with long-term local control rates of (Miller et al., 2016), but systemic failure rates range from 15-20% (Ginsberg et al., 1995; Martini et al., 1995). (Source: Medical Image Analysis)
Source: Medical Image Analysis - September 15, 2018 Category: Radiology Authors: Shulong Li, Bin Li, Zhiguo Zhou, Ning Yang, Hongxia Hao, Michael R. Folkert, Puneeth Iyengar, Kenneth Westover, Hak Choy, Robert Timmerman, Steve Jiang, Jing Wang Source Type: research
Quantitative 3D Analysis of Coronary Wall Morphology in Heart Transplant Patients: OCT-Assessed Cardiac Allograft Vasculopathy Progression
Cardiac allograft vasculopathy (CAV) represents the leading cause of late morbidity and mortality in heart transplant (HTx) recipients (Chih et al., 2016; Wever-Pinzon et al., 2014). Overall, CAV accounts for about 30% of all HTx patient deaths. For patients at high risk for CAV complications after HTx, therapy must be initiated early to be effective. Once CAV causes allograft dysfunction, the only long-term therapeutic solution is a re- transplantation. Therefore, development of a methodology for quantitative detection of early CAV progression, sufficiently sensitive to initially small changes of the intimal and medial...
Source: Medical Image Analysis - September 14, 2018 Category: Radiology Authors: Zhi Chen, Michal Pazdernik, Honghai Zhang, Andreas Wahle, Zhihui Guo, Helena Bedanova, Josef Kautzner, Vojtech Melenovsky, Tomas Kovarnik, Milan Sonka Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - September 8, 2018 Category: Radiology Source Type: research
Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture
Direct delineation of myocardial infarction (MI) area without contrast agents highly impacts early patient management and therapy planning. In routine clinical practice, delayed enhancement (DE) - cardiac magnetic resonance (CMR) imaging can be considered as the current standard for the detection of infarction area because it uses gadolinium contrast agent to provide highly accurate delineation of MI area during the imaging process. (J örg Barkhausen et al., 2002; Ingkanisorn et al., 2004). However, this imaging process may be dangerous because the administration of gadolinium contrast agent is fatal to the patients wi...
Source: Medical Image Analysis - September 6, 2018 Category: Radiology Authors: Chenchu Xu, Lei Xu, Zhifan Gao, Shen Zhao, Heye Zhang, Yanping Zhang, Xiuquan Du, Shu Zhao, Dhanjoo Ghista, Huafeng Liu, Shuo Li Source Type: research
Iterative multi-path tracking for video and volume segmentation with sparse point supervision
At its core, semantic segmentation is tasked with associating pixels, or voxels, of an image with a label that corresponds to a meaningful category. As a fundamental problem in medical image computing, an impressive amount of research on the topic has been conducted in recent years, spanning methods that segment tumors in MRI volumes (Zikic et al., 2014; Menze, 2014), airways from chest CT scans (Miyawaki et al., 2017), vessels in retinal scans (Pilch et al., 2012) or mitochondria in electron microscopes (Seyedhosseini et al., 2013) to name a few. (Source: Medical Image Analysis)
Source: Medical Image Analysis - August 29, 2018 Category: Radiology Authors: Laurent Lejeune, Jan Grossrieder, Raphael Sznitman Source Type: research
Automatic segmentation variability estimation with segmentation priors
Segmentation of anatomical structures and pathologies in medical images is a fundamental technical problem in medical image processing. Segmentation is the state-of-practice in a variety of medical products and is gaining prominence in clinical practice, as more clinicians rely on it for a wide variety of clinical tasks, including diagnosis, treatment planning, treatment delivery, and treatment evaluation. Indeed, segmentation is state-of-practice and is a key component in an increasing number of commercial medical products applications such as multi-modal tumor volumetry and tumor tracking, patient-specific custom jig pri...
Source: Medical Image Analysis - August 26, 2018 Category: Radiology Authors: L. Joskowicz, D. Cohen, N. Caplan, J. Sosna Source Type: research
