Number Of Atlases Research Articles

Cross-Modality Multi-Atlas Segmentation via Deep Registration and Label Fusion.

Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation. Generally, MAS methods register multiple atlases, i.e., medical images with corresponding labels, to a target image; and the transformed atlas labels can be combined to generate target segmentation via label fusion schemes. Many conventional MAS methods employed the atlases from the same modality as the target image. However, the number of atlases with the same modality may be limited or even missing in many clinical applications. Besides, conventional MAS methods suffer from the computational burden of registration or label fusion procedures. In this work, we design a novel cross-modality MAS framework, which uses available atlases from a certain modality to segment a target image from another modality. To boost the computational efficiency of the framework, both the image registration and label fusion are achieved by well-designed deep neural networks. For the atlas-to-target image registration, we propose a bi-directional registration network (BiRegNet), which can efficiently align images from different modalities. For the label fusion, we design a similarity estimation network (SimNet), which estimates the fusion weight of each atlas by measuring its similarity to the target image. SimNet can learn multi-scale information for similarity estimation to improve the performance of label fusion. The proposed framework was evaluated by the left ventricle and liver segmentation tasks on the MM-WHS and CHAOS datasets, respectively. Results have shown that the framework is effective for cross-modality MAS in both registration and label fusion https://github.com/NanYoMy/cmmas.

Multi-atlas based neonatal brain extraction using a two-level patch-based label fusion strategy

Compared to adults, brain extraction from magnetic resonance (MR) images of newborn infants is particularly challenging due to their smaller brain size, which causes lower spatial resolution, lower tissue contrast and ambiguous tissue intensity distribution. In this work, a multi-atlas patch-based label fusion method is presented for automatic brain extraction from neonatal head MR images. In this method, a number of atlases are first selected uniformly among a set of training images. After nonlinear alignment of the selected atlas images to the target image, a probabilistic gray level-coded brain mask is created and used to assign brain/non-brain labels to voxels with different degree of uncertainty using a modified non-local patch-based label fusion method based on the integration of low-level and in-depth search patch selection strategies. Experiments with 40 neonates aged between 37 and 44 weeks showed an average Dice, Jaccard and Conformity coefficients of 0.993, 0.986 and 0.986, respectively. We compared the performance of the proposed method with two multi atlas-based methods, i.e. NLPB and MASS, and two popular non-learning-based methods, i.e. BSE and BET. Compared to these methods, our method achieved higher accuracy with brain masks very close to manually extracted ones and produced lower false negative and false positive rates. Our proposed method allows for accurate and efficient brain extraction, a crucial step in brain MRI applications such as brain tissue segmentation and volume estimation in neonates.

Нормальная расшифровка структуры грудной железы с учетом возможностей нового поколения высокочастотных ультрасонографических датчиков

Over the years of the existence of echography in Japan and the English-speaking countries, a large number of atlases and a manual textbookы where the authors describe the echo anatomy of the mammary glands have been published. The rapid technological growth has led to the fact that the echo anatomy of the mammary glands described on the basis of equipment from the 80s-90s does not correspond to the capabilities of modern ultrasonic devices. There was a need to clarify and detail the echographic image of the mammary glands, taking into account the possibilities of a new generation of 10–12 MHz high-frequency, and also upon the use of the new Doppler techniques. The anatomical structures of the mammary glands are clearly differentiated using modern ultrasound equipment. The breast tissue is normally varied widely and depends on the ratio of fat, connective and glandular tissue. The USM allows visualizing the tomographic section of the image of a fragment of the mammary gland from the skin cover to the chest wall. Key words: breast glande, ultrasonography, dopрlerography, US-sensor.

АНАЛІЗ ПРОГРАМИ З КУРСУ "ЕКОЛОГІЯ" ДЛЯ ШКОЛИ ТА ЗАБЕЗПЕЧЕННЯ ЇЇ КАРТАМИ

Analyzed and studied the structure and content of the curriculum of the course “Ecology” for the school. In the course curriculum is “Ecology” divided by academic level to 11th grade profile and 10-11. Details were discussed program for 11th grade. This course is designed for 17 hours (0.5 hours weekly load of 11 class) and includes 8 related topics. Researched work of many scientists concerned with school mapping, such as: Ostrouh V. I, Radchenko V. V, Datsenko L. M, Shevchenko V. A, Peresalko V.A, Kapustenko S. V. The basic principles of school education cartographic works: their specificity, outlined the main differences from other basic requirements and criteria, including such as the card should not be overloaded, the map is a source of information highlights school course, all data must be current, card must meet sanitation m pronunciation. Cartographic work for the school included lists of typical training-visual aids and educational equipment for schools. There are a number of atlases that can be used for educational purposes in schools, both at regional level and at the state. Considered and studied major environmental atlases Ukraine, including eco-Geografical Atlas (published in “Varta”), Atlas of the Environment (“Ranok”) and certain regions: Environmental Atlas of Lviv, Kharkiv region, Dnipropetrovsk region, Luhansk, Poltava and the basin of the Southern Bug).

A Discrete MRF Framework for Integrated Multi-Atlas Registration and Segmentation

Multi-atlas segmentation has emerged in recent years as a simple yet powerful approach in medical image segmentation. It commonly comprises two steps: (1) a series of pairwise registrations that establish correspondences between a query image and a number of atlases, and (2) the fusion of the available segmentation hypotheses towards labeling objects of interest. In this paper, we introduce a novel approach that solves simultaneously for the underlying segmentation labels and the multi-atlas registration. The proposed approach is formulated as a pairwise Markov Random Field, where registration and segmentation nodes are coupled towards simultaneously recovering all atlas deformations and labeling the query image. The coupling is achieved by promoting the consistency between selected deformed atlas segmentations and the estimated query segmentation. Additional membership fields are estimated, determining the participation of each atlas in labeling each voxel. Inference is performed by using a sequential relaxation scheme. The proposed approach is validated on the IBSR dataset and is compared against standard post-registration label fusion strategies. Promising results demonstrate the potential of our method.

Evaluation of the effect of doubling atlases using midsagittal plane on multi-atlas based segmentation of brain structures.

Normal human brain exhibits approximately bi-fold symmetry with respect to its midsagittal plane (MSP). The objective of this work is to investigate the effect of doubling atlases (i.e., reference images) used in multi-atlas fusion methods by exploiting the inherent bilateral symmetry of human brain. To this end, we perform automated segmentation of 15 subcortical structures using Local Weighted Voting (LWV) fusion method with varying number of atlases. We consider three specific scenarios for atlases while performing fusion: (i) fusion with original OASIS atlases, (ii) with atlases obtained by flipping the original atlases based on their MSP, and (iii) with both original and flipped atlases. Evaluations are performed on the publicly available OASIS dataset of 20 normal human brain MR images. One of the key findings of this study is that when the number of atlases available for fusion is less than 10, fusion by combining both the original and flipped atlases provided more accurate segmentations than using only the original atlases, or only the flipped atlases.

Evaluation and optimization of the parameters used in multiple-atlas-based segmentation of prostate cancers in radiation therapy.

To evaluate and optimize the parameters used in multiple-atlas-based segmentation of prostate cancers in radiation therapy. A retrospective study was conducted, and the accuracy of the multiple-atlas-based segmentation was tested on 30 patients. The effect of library size (LS), number of atlases used for contour averaging and the contour averaging strategy were also studied. The autogenerated contours were compared with the manually drawn contours. Dice similarity coefficient (DSC) and Hausdorff distance were used to evaluate the segmentation agreement. Mixed results were found between simultaneous truth and performance level estimation (STAPLE) and majority vote (MV) strategies. Multiple-atlas approaches were relatively insensitive to LS. A LS of ten was adequate, and further increase in the LS only showed insignificant gain. Multiple atlas performed better than single atlas for most of the time. Using more atlases did not guarantee better performance, with five atlases performing better than ten atlases. With our recommended setting, the median DSC for the bladder, rectum, prostate, seminal vesicle and femurs was 0.90, 0.77, 0.84, 0.56 and 0.95, respectively. Our study shows that multiple-atlas-based strategies have better accuracy than single-atlas approach. STAPLE is preferred, and a LS of ten is adequate for prostate cases. Using five atlases for contour averaging is recommended. The contouring accuracy of seminal vesicle still needs improvement, and manual editing is still required for the other structures. This article provides a better understanding of the influence of the parameters used in multiple-atlas-based segmentation of prostate cancers.

A novel atlas-selection approach for multi-atlas based segmentation using the correlation of inter-atlas similarities

Automated segmentation is a frequently applied task in the course of medical imaging. Furthermore, it is a substantial component of image-guided radiotherapy. Atlas based segmentation is one of the most frequently used approach for automated segmentation. Especially for multi-atlas based segmentation, segmentation quality and speed largely depends on the underlying registration and atlas selection strategy. In this work an atlas selection strategy that is based on the correlation of inter-atlas similarities within a set of atlas images is presented. Segmentation quality is analyzed by calculating dice coefficients and 95% Hausdorff distances for the left and right parotid with respect to different numbers of atlases. Results are compared to other state of the art atlas selection strategies. It can be shown that the developed atlas selection technique performs slightly better than NMI-based selection if a low number of atlases is used.

Improving label fusion in multi-atlas based segmentation by locally combining atlas selection and performance estimation

In multi-atlas based segmentation, a target image is segmented by registering multiple atlas images to this target image and propagating the corresponding atlas segmentations. These propagated segmentations are then combined into a single segmentation in a process called label fusion.Multi-atlas based segmentation is a segmentation method that allows fully automatic segmentation of image populations that exhibit a large variability in shape and image quality. Fusing the results of multiple atlases makes this technique robust and reliable. Previously, we have presented the SIMPLE method for label fusion and have shown that it outperforms existing methods. However, the downside of this method is its computation time and the fact that it requires a large atlas set. This is not always a problem, but in some cases segmentation may be time-critical or large atlas sets are not available.This paper presents a new label fusion method which is a local version of the SIMPLE method that has two advantages: when a large atlas set is available it improves the accuracy of label fusion and when this is not the case it gives the same accuracy as the original SIMPLE method, but with considerably fewer atlases. This is made possible by better utilizing the local information contained in propagated segmentations that would otherwise be discarded. Our method (semi-)automatically divides the propagated segmentations in multiple regions. A label fusion process can then be applied to each of these regions separately and the end result can be reconstructed out of multiple partial results. We demonstrate that the number of atlases needed can be reduced to 20 atlases without compromising segmentation quality. Our method is validated in an application to segmentation of the prostate, using an atlas set of 125 manually segmented images.

WE-E-213CD-02: Gaussian Weighted Multi-Atlas Based Segmentation for Head and Neck Radiotherapy Planning.

To develop a multi-atlas segmentation strategy for IMRT head and neck therapy planning. The method was tested on thirty-one head and neck simulation CTs, without demographic or pathology pre-clustering. We compare Fixed Number (FN) and Thresholding (TH) selection (based on normalized mutual information ranking) of the atlases to be included for current patient segmentation. Next step is a pairwise demons Deformable Registration (DR) onto current patient CT. DR was extended to automatically compensate for patient different field of view. Propagated labels are combined according to a Gaussian Weighted (GW) fusion rule, adapted to poor soft tissues contrast. Agreement with manual segmentation was quantified in terms of Dice Similarity Coefficient (DSC). Selection methods, number of atlases used, as well as GW, average and majority voting fusion were discriminated by means of Friedman Test (a=5%). Experimental tuning of the algorithm parameters was performed on five patients, deriving an optimal configuration for each structure. DSC reduction was not significant when ten or more atlases are selected, whereas DSC for single most similar atlas selection is 10% lower in median. DSC of FN selection rule were significantly higher for most structures. Tubular structures may benefit from computing average contour rather than looking at the singular voxel contribution, whereas the best performing strategy for all other structures was GW. When half database is selected, final median DSC were 0.86, 0.80, 0.51, 0.81, 0.69 and 0.79 for mandible, spine, optical nerves, eyes, parotids and brainstem respectively. We developed an efficient algorithm for multiatlas based segmentation of planning CT volumes, based on DR and GW. FN selection of database atlases is foreseen to increase computational efficiency. The absence of clinical pre-clustering and specific imaging protocol on database subjects makes the results closer to real clinical application. "Progetto Roberto Rocca" funded by the Fondazione Fratelli Agostino and Enrico Rocca, Italy.

The Chatsworth Uranographia Britannica

In November 1997, two colleagues at Manchester Astronomical Society, Mike Oates and Tony Cross, and I identified, with the help of Peter Hingley, an old star atlas that had been in our library for over 50 years as an Atlas Celeste: an original, bound set of charts from John Bevis’s unpublished atlas Uranographia, ca. 1750. It was the 16th copy known (see Ashworth 1981) and started a quest to learn more about this rare atlas (Kilburn 2007). In about 1745, the London doctor and amateur astronomer Dr John Bevis FRS proposed to compile a modern British star atlas, Uranographia Britannica. He enlisted the help of John Neale, an instrument maker or toy maker of Leadenhall Street, who sought to finance the project with advance subscriptions from those wealthy enough. A copy of the 1746 list of subscribers is held at Glasgow University Library (Sp. Coll. f465). Uranographia was based on Flamsteed’s star positions and Halley’s observations of the southern hemisphere, together with additional stars from Bevis’s own transit observations between 1738 and 1739. In 1750, as Bevis’s atlas was in the process of being printed, disaster struck. Neale was declared bankrupt, the copper plates were sequestered by the London Courts of Chancery and the project was abruptly terminated. It was not until 1785, long after the deaths of Neale and Bevis, that Bevis’s library was auctioned by the widow of his executor, James Horsfall FRS. According to the auction catalogue, which survives in the Whipple Museum, Cambridge, three near-complete atlases were sold, together with an unknown number of pre-printed star charts. These surplus star charts were compiled into an unknown number of atlases and sold cheap, in 1786, as Atlas Celeste. A typical Atlas Celeste comprises: an elaborate frontispiece showing the Muse, Urania, offering a star atlas to a seated man, Frederick, Prince of Wales, with Greenwich Observatory in the background; and 51 star charts, Tab I to LI, each carrying a dedication to institutions or individuals who subscribed to the project. A few atlases have a simple index thought to have been printed in 1786, together with an exceedingly rare title sheet advertising it as Atlas Celeste. Manchester’s Atlas Celeste is considered to be the most complete and original. Of the three, near-complete Uranographia, one was bought at the Sotheby & Wilkinson sale, London, on 21 January 1856 by the American Philosophical Society, Philadelphia. It was formerly owned by Sir George Shuckburgh-Evelyn (1751–1804). This is the atlas on which Ashworth based his 1981 seminal description. Another less complete copy, also identified by Ashworth, is at St John’s Library, Cambridge. The third went unidentified, until November 2011.

Mapping avian distributions: the evolution of bird atlases

Capsule An increasing proportion of atlases now map patterns of abundance but they are still a minority even though they require no more input of time or fieldworkers. Aims To examine quantitatively the evolution of bird atlas methods, from their inception to the present day, to document the most frequently used methods and to quantify temporal changes in them, and so identify broad patterns that might be of use in the planning and interpretation of future atlases. Methods A database of over 400 atlases was compiled, and a number of variables extracted from each. Temporal trends within, and relationships between, these variables were analysed. Results Atlases have become significantly reduced in scale over time, covering smaller areas in shorter periods of fieldwork, but at higher spatial resolutions and with increasing numbers of observers per unit area. The number of participating fieldworkers and the size of the region being covered together explain over 70% of variation between atlases in spatial resolution. The number of atlases that have mapped abundance or relative abundance, rather than simply occurrence (presence/absence) or breeding status, has increased significantly over time but remains relatively small. However, such atlases were no more expensive in terms of length of the fieldwork or preparation periods or the number of observers deployed per unit area. There is evidence of a sharp decline in the number of new bird atlases being initiated. Conclusions There have been significant changes in the way atlas surveys are undertaken, but no standardized method has evolved. This leads to flexibility that allows atlas surveys to be undertaken over areas varying by six orders of magnitude using numbers of observers that vary by five orders of magnitude.

The Use of Mean Atmospheric Parameters in the Calculation of Modeled Mean Surface Heat Fluxes over the World's Oceans

There are a number of atlases that display the distribution of ocean-atmosphere sensible and latent heat fluxes over various regions. Many are based on the “classical” method, in which time mean quantities are used in the bulk aerodynamic formulas, rather than the more accurate “sampling” method, which computes the mean of the instantaneous fluxes. Much of the justification for the use of this approximation comes from some studies conducted in the North Pacific and Atlantic oceans. How valid is it when applied globally? In this study we use large datasets, generated by January and July simulations of a general circulation model of the atmosphere, to examine comprehensively the differences between the two methods. We find that the ocean zonal averages of the two fluxes differ by less than 10 W m−2 at most latitudes in both months. However, at high southern latitudes in winter the sensible heat fluxes north of the Antarctic ice pack are up to 17 W m−2 (25%) greater when calculated with the sampling method. We show that the two methods differ due to four temporal covariances of various atmospheric quantities Some of the covariances contribute up to 12 W m−2 to the zonal mean fluxes. The fact that the classical and sampling methods give similar results over most of the globe is due, in large part, to the near cancellation of the covariances. However, this is not always true around the periphery of Antarctica.