Efficient and Robust Cell Detection: A Structured Regression Approach
Manual analysis of microscopy images is not only laborious and expensive but is also inclined to suffer from inter-observer variabilities. Recent progress (Gurcan et al., 2009) shows that digitized specimen analysis can significantly improve the objectivity and reproducibility of computer-aided diagnosis (CAD). In the context of microscopy image analysis-based CAD, automatic and robust cell detection are highly desirable and serve as an essential prerequisite for a wide variety of subsequent tasks, such as cell segmentation, tracking and morphological measurements Veta et al. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 26, 2017 Category: Radiology Authors: Yuanpu Xie, Fuyong Xing, Xiaoshuang Shi, Xiangfei Kong, Hai Su, Lin Yang Source Type: research
A Survey on Deep Learning in Medical Image Analysis
As soon as it was possible to scan and load medical images into a computer, researchers have built systems for automated analysis. Initially, from the 1970s to the 1990s, medical image analysis was done with sequential application of low-level pixel processing (edge and line detector filters, region growing) and mathematical modeling (fitting lines, circles and ellipses) to construct compound rule-based systems that solved particular tasks. There is an analogy with expert systems with many if-then-else statements that were popular in artificial intelligence in the same period. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 26, 2017 Category: Radiology Authors: Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen A.W.M. van der Laak, Bram van Ginneken, Clara I. S ánchez Source Type: research
Designing image segmentation studies: statistical power, sample size and reference standard quality
Demonstrating an improvement in segmentation algorithm accuracy typically involves comparison with an accepted reference standard, such as manual expert segmentations or other imaging modalities (e.g. histology). In many medical image segmentation problems, such segmentations are challenging due to the variable appearance of anatomical/pathological features, ambiguous anatomical definitions, clinical constraints, and interobserver variability. The resulting errors in the reference standards introduce errors in the performance measures used to compare segmentation algorithms, and can impact the probability of detecting a si...
Source: Medical Image Analysis - July 22, 2017 Category: Radiology Authors: Eli Gibson, Yipeng Hu, Henkjan J. Huisman, Dean C. Barratt Source Type: research
Editorial Board
(Source: Medical Image Analysis)
Source: Medical Image Analysis - July 21, 2017 Category: Radiology Source Type: research
SpineNet: Automated Classification and Evidence Visualization in Spinal MRIs
Automated detection, grading and localization of abnormalities in medical images is an important task to support clinical decision making across many medical specialties. As the utilization and interpretation of medical images continues to expand beyond the radiology department, as it has in cardiology and neurology, it is becoming increasingly important to supplement the typically qualitative radiological read with objective quantitative methods. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 21, 2017 Category: Radiology Authors: Amir Jamaludin, Timor Kadir, Andrew Zisserman Source Type: research
Accurate Model-based Segmentation of Gynecologic Brachytherapy Catheter Collections in MRI-images
Gynecological malignancies, including those of the cervix, endometrium, ovaries, and external female genitalia, are a leading cause of mortality in women worldwide. In the United States, with an estimated 105,890 new cases and a mortality of 29%, gynecological malignancies continue to present a medical challenge (Society, 2015). Chemoradiation, which consists of concurrent chemotherapy and external-beam radiation, followed by brachytherapy (Fig. 1) remains the standard-of-care for treatment of gynecologic cancers. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 18, 2017 Category: Radiology Authors: Andre Mastmeyer, Guillaume Pernelle, Ruibin Ma, Lauren Barber, Tina Kapur Source Type: research
Gyral Net: A New Representation of Cortical Folding Organization
Modern magnetic resonance imaging (MRI) techniques enable in vivo studies of the cortical folding patterns, which attract growing research interest. It has been shown that an understanding of the cortical folding can benefit cytoarchitectonic areal parcellation (Fischl et al., 2008), normal maturation and neurodegenerative process investigation (Giedd et al., 1999), and abnormal brain development understanding (Schaer et al., 2008). As a convoluted surface, the neocortex is usually represented by a reconstructed mesh surface, upon which quantitative analyse s are performed. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 15, 2017 Category: Radiology Authors: Hanbo Chen, Yujie Li, Fangfei Ge, Gang Li, Dinggang Shen, Tianming Liu Source Type: research
Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge
Lung cancer is the deadliest cancer worldwide, accounting for approximately 27% of cancer-related deaths in the United States (American Cancer Society (2016)). The NLST trial showed that three annual screening rounds of high-risk subjects using low-dose computed tomography (CT) reduced lung cancer mortality after 7 years by 20% in comparison to screening with chest radiography (Aberle et al. (2011)). As a result of this trial and subsequent modeling studies, lung cancer screening programs using low-dose CT are currently being implemented in the U.S. (Source: Medical Image Analysis)
Source: Medical Image Analysis - July 12, 2017 Category: Radiology Authors: Arnaud Arindra Adiyoso Setio, Alberto Traverso, Thomas de Bel, Moira S.N. Berens, Cas van den Bogaard, Piergiorgio Cerello, Hao Chen, Qi Dou, Maria Evelina Fantacci, Bram Geurts, Robbert van der Gugten, Pheng Ann Heng, Bart Jansen, Michael M.J. de Kaste, Source Type: research
Probabilistic Modeling of Anatomical Variability Using a Low Dimensional Parameterization of Diffeomorphisms
The study of anatomical shape variability across populations and its relationship with disease processes plays an important role in medical image analysis. For example, identifying pathological brain shape changes caused by neurodegenerative disorders from brain MRI scans provides new insights into the nature of the disease and supports treatment (Gerig et al., 2001; Nemmi et al., 2015). Research in shape analysis mainly focuses on developing statistical models with well defined shape descriptors such as landmarks (Cootes et al., 1995; Bookstein, 1997), medial axes (Pizer et al., 1999), and deformation-based...
Source: Medical Image Analysis - July 6, 2017 Category: Radiology Authors: Miaomiao Zhang, William M. Wells, Polina Golland Source Type: research
Central Focused Convolutional Neural Networks: Developing a Data-driven Model for Lung Nodule Segmentation
Lung cancer is the leading cause for cancer related deaths and carrying a dismal prognosis with a 5-year survival rate at only 18% (Siegel et al., 2016). Treatment therapy monitoring and lung nodule analysis (Aerts et al., 2014) using computed tomography (CT) images are important strategies for early lung cancer diagnosis and survival time improvement. In these approaches, accurate lung nodule segmentation is necessary tha t can directly affect the subsequent analysis results. Specifically, given the fact of growing volumes of clinical imaging data, developing a data-driven segmentation model is of great clinical impo...
Source: Medical Image Analysis - June 30, 2017 Category: Radiology Authors: Shuo Wang, Mu Zhou, Zaiyi Liu, Zhenyu Liu, Dongsheng Gu, Yali Zang, Di Dong, Olivier Gevaert, Jie Tian Source Type: research
The 19th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2016)
was held in Athens, Greece. It was organized by a collaboration among University College London, Harvard Medical School, The Hebrew University of Jerusalem and Bogazici, Sabanci, and Istanbul Technical Universities. MICCAI 2016 and its satellite events gathered word-leading scientists, engineers, and clinicians, who presented excellent scientific work covering different fields including medical image processing, medical image formation, medical robotics and computer assisted interventions. (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 29, 2017 Category: Radiology Authors: Sebastien Ourselin, Mert R. Sabuncu, William Wells, Leo Joskowicz, Gozde Unal, Andreas Maier Tags: Editorial Source Type: research
Estimation of individual axon bundle properties by a Multi-Resolution Discrete-Search method
Diffusion-weighted (DW) magnetic resonance imaging (MRI) is an imaging modality which is sensitive to the microscopic Brownian motion of water molecules (i.e. diffusion). Water diffusion in living tissues is affected by their cellular organization. In particular, in the brain white matter (WM), the coherent organization in packed bundles of the neuronal tissue introduces a directional dependence to the microscopic random movements (Beaulieu, 2002). Therefore, by measuring water molecular displacements using diffusion MRI, it is possible to infer properties of the local tissue micro-structure and the architecture of the n...
Source: Medical Image Analysis - June 29, 2017 Category: Radiology Authors: Ricardo Coronado-Leija, Alonso Ramirez-Manzanares, Jose Luis Marroquin Source Type: research
Modelling and Extraction of Pulsatile Radial Distension and Compression Motion for Automatic Vessel Segmentation from Video
Identification of blood vessels from medical images is important to many clinical procedures. Common applications of vascular imaging range from routine non-invasive diagnostic procedures to complex surgical interventions. Vascular imaging is routinely used to assess the risk for cardiovascular morbidity by (i) directly imaging and analyzing the coronary arteries with intravascular ultrasound (US), magnetic resonance (MR), or computed tomography (CT) imaging; (ii) quantifying arteriosclerosis from color images of the retina (Pedersen et al., 2000); (iii) segmenting atherosclerotic plaque from US (Bots et al., 1997), ...
Source: Medical Image Analysis - June 29, 2017 Category: Radiology Authors: Alborz Amir-Khalili, Ghassan Hamarneh, Rafeef Abugharbieh Source Type: research
Guest editors of MICCAI 2016 Special Issues of Medical Imaging Analysis: The 19th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2016)
The 19th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2016) was held in Athens, Greece. It was organized by in a collaboration among University College London, Harvard Medical School, The Hebrew University of Jerusalem and Bogazici, Sabanci, and Istanbul Technical Universities. MICCAI 2016 and its satellite events gathered word-leading scientists, engineers, and clinicians, who presented excellent scientific work covering different fields including medical image processing, medical image formation, medical robotics and computer assisted interventions. (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 29, 2017 Category: Radiology Authors: Sebastien Ourselin, Mert R. Sabuncu, William Wells, Leo Joskowicz, Gozde Unal, Andreas Maier Tags: Editorial Source Type: research
A New Algebraic Method for Quantitative Proton Density Mapping using Multi-Channel Coil Data
A difficult problem in quantitative MRI is the accurate determination of basic tissue parameters such as the longitudinal relaxation constant T1 (Stikov et al., 2015) and the proton density ρ (Volz et al., 2012a), which are sensitive quantities in measuring brain tissue organization in a number of debilitating conditions such as multiple sclerosis (MS). Using Inversion Recovery (IR) sequences, T1 can be estimated accurately (Stikov et al., 2015). The proton density, however, is more c hallenging to compute than T1 because the transmit and receiver coil sensitivities need to be known as well. (Source: Medical Image Analysis)
Source: Medical Image Analysis - June 22, 2017 Category: Radiology Authors: Dietmar Cordes, Zhengshi Yang, Xiaowei Zhuang, Karthik Sreenivasan, Virendra Mishra, Le H. Hua Source Type: research
