Search

Super resolution problems are widely discussed in medical imaging. Spatial resolution of medical images are not sufficient due to the constraints such as image acquisition time, low irradiation dose or hardware limits. To address these problems, different super resolution methods have been proposed, such as optimization or learning-based approaches. Recently, deep learning methods become a thriving technology and are developing at an exponential speed. We think it is necessary to write a review to present the current situation of deep learning in medical imaging super resolution. In this paper, we first briefly introduce deep learning methods, then present a number of important deep learning approaches to solve super resolution problems, different architectures as well as up-sampling operations will be introduced. Afterwards, we focus on the applications of deep learning methods in medical imaging super resolution problems, the challenges to overcome will be presented as well. [ABSTRACT FROM AUTHOR]

Context: Spectral Computed Tomography (SPCT) acquires energy-resolved projections that can be used to evaluate the concentrations of the different materials of an object. This can be achieved by decomposing the projection images in a material basis, in a first step, followed by a standard tomographic reconstruction step. However, material decomposition is a challenging non-linear ill-posed inverse problem, which is very sensitive to the photonic noise corrupting the data. Methods: In this paper, material decomposition is solved in a variational framework. We investigate two fidelity terms: a weighted least squares (WLS) term adapted to Gaussian noise and the Kullback–Leibler (KL) distance adapted to Poisson Noise. The decomposition problem is then solved iteratively by a regularized Gauss–Newton algorithm. Results: Simulations are performed in a numerical mouse phantom and the decompositions show that KL outperforms WLS for low numbers of photons, i.e., for high photonic noise. Conclusion: In this work, a new method for material decomposition in SPCT is presented. It is based on the KL distance to take into account the noise statistics. This new method could be of particular interest when low-dose acquisitions are performed. [ABSTRACT FROM AUTHOR]

Cone-beam computed tomography (CBCT) data are, in principle, metrically exact. However, clinicians need to consider the precision of measurements of dental morphology as well as other hard tissue structures. CBCT spatial resolution, and thus image reconstruction quality, is restricted by the acquisition voxel size. The aim of this study was to assess geometric discrepancies among 3-dimensional CBCT reconstructions relative to the micro-CT reference. Methods A total of 37 permanent teeth from 9 mandibles were scanned with CBCT 9500 and 9000 3D and micro-CT. After semiautomatic segmentation, reconstructions were obtained from CBCT acquisitions (voxel sizes 76, 200, and 300 µm) and from micro-CT (voxel size 41 µm). All reconstructions were positioned in the same plane by image registration. The topography of the geometric discrepancies was displayed by using a color map allowing the maximum differences to be located. Results The maximum differences were mainly found at the cervical margins and on the cusp tips or incisal edges. Geometric reconstruction discrepancies were significant at 300-µm resolution (P = .01, Wilcoxon test). Conclusions To study hard tissue morphology, CBCT acquisitions require voxel sizes smaller than 300 µm. This experimental study will have to be complemented by studies in vivo that consider the conditions of clinical practice. [ABSTRACT FROM AUTHOR]

Abstract: In early breast cancer (eBC), established clinicopathological factors are not sufficient for clinical decision making particularly regarding adjuvant chemotherapy since substantial over- or undertreatment may occur. Thus, novel protein- and molecular markers have been put forward as decision aids. Since these potential prognosis and/or predictive tests differ substantially regarding their methodology, analytical and clinical validation, this review attempts to summarize the essential facts for clinicians. This review focuses on those markers which are the most advanced so far in their development towards routine clinical application, i.e. two protein markers (i.e. uPA/PAI-1 and IHC4) and six molecular multigene tests (i.e. Mammaprint®, Oncotype DX®, PAM50, Endopredict®, the 97-gene genomic grade, and 76 gene Rotterdam signatures). Next to methodological aspects, we summarized the clinical evidences, in particular the main prospective clinical trials which have already been fully recruited (i.e. MINDACT, TAILORx, WSG PLAN B) or are still ongoing (i.e. RxPONDER/SWOG S1007, WSG-ADAPT). Last but not least, this review points out the key elements for clinicians to select one test among the wide panel of proposed assays, for a specific population of patients in term of level of evidence, analytical and clinical validity as well as cost effectiveness. [Copyright &y& Elsevier]

Objective: The goal of this study was to determine the efficacy of the intraosseous (IO) injections of anesthetic as a primary technique in children and adolescents. Study design: A cohort of 181 children and adolescents underwent a total of 225 sessions of IO injections of 4% articaine with 1:200,000 epinephrine using the Quick Sleeper 2 system. Results: Evaluations could be performed in 215 sessions (171 patients, 247 teeth), yielding success rates of 91.2% (sessions) and 91.9% (teeth). The success rate was 95% (133 of 140) for temporary teeth (endodontics 96.6%, restorations 100%, extractions 88%) and 87.9% (94 of 107) for permanent teeth (endodontics 92.3%, restorations 89.9%, extractions 75%). No difference was noted in terms of age (P > .05). No cases of biting of mucosa or postinjection pain were noted. Conclusions: The IO injection of anesthetic using a computer-controlled osseous perforation and delivery system can be considered as a good alternative or supplement to classic infiltration techniques in children and adolescents. [Copyright &y& Elsevier]

Abstract: Assessment of oral hard tissues can be of great help in determining the age of an individual. The development and physiological aging of teeth provide many clues for estimating age, in methods that are mainly based on conventional radiography. Although these conventional techniques reveal information on the anatomical and pathological characteristics, they only show two-dimensional images of a system that originally exists in three dimensions. With the growth and development of three-dimensional imaging, it has become possible to include measurements such as volumetric data, which give a better grasp of the continuous process of tooth mineralization. Up to now, these measurements have been obtained in vitro using micro-computed tomography (micro-CT) but three-dimensional imaging has recently been enriched by a new technique: Cone-Beam Computed Tomography (CBCT), which is devoted to the maxillo-facial sphere. These acquisitions may offer real potential for exploiting and analyzing volumetric measurements of teeth. We hypothesize that, using CBCT acquisitions, multiple regression analysis including quantitative volumetric measurement of various parts of each tooth can be useful to determine significant variables for dental age estimation in living subjects. Currently, CBCT examinations are being performed and contain important information for the quantitative study of dental tissue. Although CBCT examinations are conducted in the first intention of making a clinical diagnosis or prognostic evaluation, they could be used as an initial database for the measurement of dental volumes and their ratios, thus furnishing preliminary evaluations and information. Multiple regression analysis requires the constitution of a larger sample sizes which may demonstrate that CBCT data can be helpful to study other aspects of dental morphology in greater depth, especially dental growth. In this hypothesis, integration with a larger network system would be necessary. CBCT data could be helpful in defining new parameters for the rating of dental development, for a quantitative description of the fractions of crown and root and could offer new research oriented towards various aspects of teeth and jaws, thanks to its broad sampling possibilities. [Copyright &y& Elsevier]

To summarize the evidence available from observational studies on the association between periodontal disease and adverse pregnancy outcomes, we conducted a meta-analytic review of 5 medical databases for human observational studies linking preterm delivery and/or birth of low birthweight infants to maternal periodontal disease. [ABSTRACT FROM AUTHOR]

To summarize the evidence available from observational studies on the association between periodontal disease and adverse pregnancy outcomes, we conducted a meta-analytic review of 5 medical databases for human observational studies linking preterm delivery and/or birth of low birthweight infants to maternal periodontal disease. [ABSTRACT FROM AUTHOR]