Morphometry based on effective and accurate correspondences of localized patterns (MEACOLP)

Local features in volumetric images have been used to identify correspondences of localized anatomical structures for brain morphometry. However, the correspondences are often sparse thus ineffective in reflecting the underlying structures, making it unreliable to evaluate specific morphological differences. This paper presents a morphometry method (MEACOLP) based on correspondences with improved effectiveness and accuracy. A novel two-level scale-invariant feature transform is used to enhance the detection repeatability of local features and to recall the correspondences that might be missed in previous studies. Template patterns whose correspondences could be commonly identified in each group are constructed to serve as the basis for morphometric analysis. A matching algorithm is developed to reduce the identification errors by comparing neighboring local features and rejecting unreliable matches. The two-sample t-test is finally adopted to analyze specific properties of the template patterns. Experiments are performed on the public OASIS database to clinically analyze brain images of Alzheimer's disease (AD) and normal controls (NC). MEACOLP automatically identifies known morphological differences between AD and NC brains, and characterizes the differences well as the scaling and translation of underlying structures. Most of the significant differences are identified in only a single hemisphere, indicating that AD-related structures are characterized by strong anatomical asymmetry. In addition, classification trials to differentiate AD subjects from NC confirm that the morphological differences are reliably related to the groups of interest.     

Determination of astigmatism in TEM images

We have developed a new two-step algorithm to determine the astigmatism of images from transmission electron microscopes (TEMs). Instead of computing the radial average of the power spectrum, we divide the power spectrum of a TEM image 1 to m (typically 32) sectors. We use a technique based on perturbation analysis of the contrast transfer function (CTF) to assimilate sector averages of the power spectrum of an image, which are incoherent in the presence of astigmatism, to a coherent radial average corresponding to a nominal defocus value. This is based on the fact that small defocus change from a nominal value can be considered to be equivalent to a perturbation on the spatial frequency spectra. Thus, instead of measuring the angular defocus variations, we optimise the frequency change required to obtain a coherent radial average. Numerically, this is achieved by minimizing sigma(2)/sigma(1) of a matrix formed from the sector averages, where sigma(i) denotes the ith singular value of the matrix. After the minimisation procedure, the second singular value should be very small compared with the first singular value, indicating that the matrix is nearly rank unity. In the second step, the nominal defocus can be obtained from the coherent radial average using any good defocus estimation program, which assumes zero astigmatism. The defocus value at a sector can be obtained from this nominal defocus value and one of the parameters from the unconstrained optima. Our algorithm is tested on astigmatic images of carbon film, 2D crystals of bacteriorhodopsin and cryo-images of HIV cores.     

应用小波变换检测细胞显微荧光图像中的囊泡

文章提出了一种用小波变换来检测生物荧光图像中囊泡的方法。作者用à trous小波对图像进行小波变换,然后求出每层系数的中值绝对偏差σ,并用t=kσ/0.67作为阈值对每层系数进行门限滤波,然后通过提取小波变换系数来重构图像。通过设计实验与常用的“rolling ball”算法对比,发现小波变换算法在低信噪比的情况下,具有更好的灵敏度;对于形状大小不同的信号,具有更好的稳定性;而且对于信号的细节信息具有更好的保真性。     

Adaptive color basis transformation. An aid in image segmentation

Multispectral images of stained cells enable the use of color differences to segment and/or to discriminate between image components, such as cell types and cellular subcomponents. When the spectral characteristics of the image components do not change over the area of a slide or from slide to slide, one can create a constant weighted linear combination of spectral images to generate one-dimensional or two-dimensional images that have the desired contrast between the image components that must be discriminated. However, when the spectral characteristics are not constant, i.e., when they vary from image to image, a constant weighted linear combination cannot be employed; instead, an appropriate solution must be found for each selected image. This is usually a time-consuming, manual procedure that cannot be employed in a fully automated process of discriminating and segmenting stained cells. This paper describes an algorithm that uses principal components decomposition basis vectors to generate a nonstatic weighted linear combination of color images that can be used by an automated system. This algorithm relies on a semiconstant relationship between the areas (sizes) of the image components that are to be discriminated and/or segmented. The technique has been successfully applied as an aid in the segmentation of images of stained cervical smears; the images were acquired with a three-chip CCD camera that generates three broad-band color images.     

Displacements of fiducial markers in patients with prostate cancer treated with image guided radiotherapy: A single-institution descriptive study

Aim

To describe daily displacements when using fiducial markers as surrogates for the target volume in patients with prostate cancer treated with IGRT.

Background

The higher grade of conformity achieved with the use of modern radiation technologies in prostate cancer can increase the risk of geographical miss; therefore, an associated protocol of IGRT is recommended.

Materials and methods

A single-institution, retrospective, consecutive study was designed. 128 prostate cancer patients treated with daily on-line IGRT based on 2D kV orthogonal images were included. Daily displacement of the fiducial markers was considered as the difference between the position of the patient when using skin tattoos and the position after being relocated using fiducial markers. Measures of central tendency and dispersion were used to describe fiducial displacements.

Results

The implant itself took a mean time of 15 min. We did not detect any complications derived from the implant. 4296 sets of orthogonal images were identified, 128 sets of images corresponding to treatment initiation were excluded; 91 (2.1%) sets of images were excluded from the analysis after having identified that these images contained extreme outlier values. If IGRT had not been performed 25%, 10% or 5% of the treatments would have had displacements superior to 4, 7 or 9 mm respectively in any axis.

Conclusions

Image guidance is required when using highly conformal techniques; otherwise, at least 10% of daily treatments could have significant displacements. IGRT based on fiducial markers, with 2D kV orthogonal images is a convenient and fast method for performing image guidance.     

A Fast Image Alignment Approach for 2D Classification of Cryo-EM Images Using Spectral Clustering

Three-dimensional (3D) reconstruction in single-particle cryo-electron microscopy (cryo-EM) is a significant technique for recovering the 3D structure of proteins or other biological macromolecules from their two-dimensional (2D) noisy projection images taken from unknown random directions. Class averaging in single-particle cryo-EM is an important procedure for producing high-quality initial 3D structures, where image alignment is a fundamental step. In this paper, an efficient image alignment algorithm using 2D interpolation in the frequency domain of images is proposed to improve the estimation accuracy of alignment parameters of rotation angles and translational shifts between the two projection images, which can obtain subpixel and subangle accuracy. The proposed algorithm firstly uses the Fourier transform of two projection images to calculate a discrete cross-correlation matrix and then performs the 2D interpolation around the maximum value in the cross-correlation matrix. The alignment parameters are directly determined according to the position of the maximum value in the cross-correlation matrix after interpolation. Furthermore, the proposed image alignment algorithm and a spectral clustering algorithm are used to compute class averages for single-particle 3D reconstruction. The proposed image alignment algorithm is firstly tested on a Lena image and two cryo-EM datasets. Results show that the proposed image alignment algorithm can estimate the alignment parameters accurately and efficiently. The proposed method is also used to reconstruct preliminary 3D structures from a simulated cryo-EM dataset and a real cryo-EM dataset and to compare them with RELION. Experimental results show that the proposed method can obtain more high-quality class averages than RELION and can obtain higher reconstruction resolution than RELION even without iteration.     

Differences Help Recognition: A Probabilistic Interpretation

This paper presents a computational model to address one prominent psychological behavior of human beings to recognize images. The basic pursuit of our method can be concluded as that differences among multiple images help visual recognition. Generally speaking, we propose a statistical framework to distinguish what kind of image features capture sufficient category information and what kind of image features are common ones shared in multiple classes. Mathematically, the whole formulation is subject to a generative probabilistic model. Meanwhile, a discriminative functionality is incorporated into the model to interpret the differences among all kinds of images. The whole Bayesian formulation is solved in an Expectation-Maximization paradigm. After finding those discriminative patterns among different images, we design an image categorization algorithm to interpret how these differences help visual recognition within the bag-of-feature framework. The proposed method is verified on a variety of image categorization tasks including outdoor scene images, indoor scene images as well as the airborne SAR images from different perspectives.     

基于Renyi熵滤波的光声图像重建算法设计与实现

针对光声图像重建过程中存在的原始光声信号信噪比差、重建图像对比度低、分辨率不足等问题,提出了基于Renyi熵的光声图像重建滤波算法.该算法首先根据原始光声信号的Renyi熵分布情况,确定分割阈值,并滤除杂波信号;再利用滤波后的光声数据进行延时叠加光声图像重建.利用该滤波算法分别处理铅笔芯横截面(零维)、头发丝(一维)以及小鼠大脑皮层血管(二维)等不同维度样本的光声信号,实验结果表明:相比Renyi熵处理之前,重建图像对比度平均增强了32.45%,分辨率平均提高了30.78%,信噪比提高了47.66%,均方误差降低了35.01%;相比典型的滤波处理算法(模极大值法和阈值去噪法),本研究中图像的对比度、分辨率和信噪比分别提高了25.94%/10.60%、27.90%/19.48%、35.21%/10.60%,均方误差减小了28.57%/16.66%.因此,选择利用Renyi熵滤波算法处理光声信号,从而使光声图像重建质量得到大幅改善.     

Automatic liver segmentation in MRI images using an iterative watershed algorithm and artificial neural network

Precise liver segmentation in abdominal MRI images is one of the most important steps for the computer-aided diagnosis of liver pathology. The first and essential step for diagnosis is automatic liver segmentation, and this process remains challenging. Extensive research has examined liver segmentation; however, it is challenging to distinguish which algorithm produces more precise segmentation results that are applicable to various medical imaging techniques. In this paper, we present a new automatic system for liver segmentation in abdominal MRI images. The system includes several successive steps. Preprocessing is applied to enhance the image (edge-preserved noise reduction) by using mathematical morphology. The proposed algorithm for liver region extraction is a combined algorithm that utilizes MLP neural networks and watershed algorithm. The traditional watershed transformation generally results in oversegmentation when directly applied to medical image segmentation. Therefore, we use trained neural networks to extract features of the liver region. The extracted features are used to monitor the quality of the segmentation using the watershed transform and adjust the required parameters automatically. The process of adjusting parameters is performed sequentially in several iterations. The proposed algorithm extracts liver region in one slice of the MRI images and the boundary tracking algorithm is suggested to extract the liver region in other slices, which is left as our future work. This system was applied to a series of test images to extract the liver region. Experimental results showed positive results for the proposed algorithm.     

Evaluation of radiomic texture feature error due to MRI acquisition and reconstruction: A simulation study utilizing ground truth

The purpose of this study was to examine the dependence of image texture features on MR acquisition parameters and reconstruction using a digital MR imaging phantom. MR signal was simulated in a parallel imaging radiofrequency coil setting as well as a single element volume coil setting, with varying levels of acquisition noise, three acceleration factors, and four image reconstruction algorithms. Twenty-six texture features were measured on the simulated images, ground truth images, and clinical brain images. Subtle algorithm-dependent errors were observed on reconstructed phantom images, even in the absence of added noise. Sources of image error include Gibbs ringing at image edge gradients (tissue interfaces) and well-known artifacts due to high acceleration; two of the iterative reconstruction algorithms studied were able to mitigate these image errors. The difference of the texture features from ground truth, and their variance over reconstruction algorithm and parallel imaging acceleration factor, were compared to the clinical “effect size”, i.e., the feature difference between high- and low-grade tumors on T1- and T2-weighted brain MR images of twenty glioma patients. The measured feature error (difference from ground truth) was small for some features, but substantial for others. The feature variance due to reconstruction algorithm and acceleration factor were generally smaller than the clinical effect size. Certain texture features may be preserved by MR imaging, but adequate precautions need to be taken regarding their validity and reliability. We present a general simulation framework for assessing the robustness and accuracy of radiomic textural features under various MR acquisition/reconstruction scenarios.     

Human stereovision without localized image features

Many theories of human stereovision are based on feature matching and the related correspondence problem. In this paper, we present psychophysical experiments indicating that localized image features such as Laplacian zerocrossings, intensity extrema, or centroids are not necessary for binocular depth perception. Smooth one-dimensional intensity profiles were combined into stereograms with mirror-symmetric half-images such that these localized image features were either absent or did not carry stereo information. In a discrimination task, subjects were asked to distinguish between stereograms differing only by an exchange of these half-images (ortho- vs. pseudoscopic stereograms). In a depth ordering task, subjects had to judge which of the two versions appeared in front. Subjects are able to solve both tasks even in the absence of the mentioned image features. The performance is compared to various possible stereo mechanisms. We conclude that localized image features and the correspondences between them are not necessary to perceive stereoscopic depth. One mechanism accounting for our data is correlation or mean square difference. Received: 8 February 1994 / Accepted in revised form: 15 September 1994     

A new image processing technique for determination of cell-generated deformations on substrata

This paper introduces a new image processing technique that determines the displacement field of a given substrate from “null-force” and “force-loaded” images. In this method, fluorescent elements used to track motion, which will be referred to as beads, can be seen in these images by locating the gray value that is normally distributed around their central point. Next comes a two-step process of matching the beads with displacements. The first step matches the beads with a small displacement using the correlation function of the characteristic pixels. Based on results from this initial step, another correlation function determines a pair of beads with a relatively large displacement. The entire matching process is done in this way, gradually working from the small displacement to the large one. Finally, using the cubic spline weight function, the whole displacement field is interpolated and filtered out of those displacements, which were initially found with the matched beads. Applying this new method on the cell migration yields satisfying results. Based on the particle tracking, the displacement field obtained by this new image processing technique has clear physical meaning. More importantly, this new method completes the matching of the displacement using the features of the displacement field, thus avoiding the direct matching with the image gray values for the relatively large strain of the substrate around the cell. Accordingly, it greatly decreases mismatching, making data checking unnecessary.     

A new image processing technique for determination of cell-generated deformations on substrata

This paper introduces a new image processing technique that determines the displacement field of a given substrate from "null-force" and "force-loaded" images. In this method, fluorescent elements used to track motion, which will be referred to as beads, can be seen in these images by locating the gray value that is normally distributed around their central point. Next comes a two-step process of matching the beads with displacements. The first step matches the beads with a small displacement using the correlation function of the characteristic pixels. Based on results from this initial step, another correlation function determines a pair of beads with a relatively large displacement. The entire matching process is done in this way, gradually working from the small displacement to the large one. Finally, using the cubic spline weight function, the whole displacement field is interpolated and filtered out of those displacements, which were initially found with the matched beads. Applying this new method on the cell migration yields satisfying results. Based on the particle tracking, the displacement field obtained by this new image processing technique has clear physical meaning. More importantly, this new method completes the matching of the displacement using the features of the displacement field, thus avoiding the direct matching with the image gray values for the relatively large strain of the substrate around the cell. Accordingly, it greatly decreases mismatching, making data checking unnecessary.     

The search for functional correspondences in molecular structure between two dissimilar molecules

Where structural similarities between molecular ligands are suspected in competitive binding, these similarities may be represented by a set of correspondences between analogous ligand points in the two molecules. This paper describes an algorithm which searches through all possible sets of this form, to find the one which gives the best geometric fit between matched points. Two parameters are supplied to the algorithm, giving the number of correspondences required and the tolerance permitted in the fit. A tree-search technique is used, and methods are described which prune the tree and thus limit the search. The marine neurotoxins, saxitoxin and tetrodotoxin, are used to test a computer implementation of the procedure.     

Toward objective selection of representative microscope images

Scientists wishing to communicate the essential characteristics of a pattern (such as an immunofluorescence distribution) currently must make a subjective choice of one or two images to publish. We therefore developed methods for objectively choosing a typical image from a set, with emphasis on images from cell biology. The methods involve calculation of numerical features to describe each image, calculation of similarity between images as a distance in feature space, and ranking of images by distance from the center of the feature distribution. Two types of features were explored, image texture measures and Zernike polynomial moments, and various distance measures were utilized. Criteria for evaluating methods for assigning typicality were proposed and applied to sets of images containing more than one pattern. The results indicate the importance of using distance measures that are insensitive to the presence of outliers. For collections of images of the distributions of a lysosomal protein, a Golgi protein, and nuclear DNA, the images chosen as most typical were in good agreement with the conventional understanding of organelle morphologies. The methods described here have been implemented in a web server (http://murphylab.web.cmu.edu/services/TyplC).     

胰腺内镜超声图像纹理特征提取与分类研究

提出了胰腺内镜超声图像的纹理特征提取与分类方法,可应用于胰腺癌内镜超声图像的计算机辅助诊断。对胰腺内镜超声图像采用数字图像处理算法提取9大类共69个纹理特征。使用类间距作为可分性判据,实现特征的初步筛选,之后使用顺序前进搜索算法进一步筛选特征,并由支撑向量机实现分类。对216例病例随机选取训练集和测试集,通过多次随机实验表明。本文提出的算法实现了较高的分类准确率,为胰腺癌的临床诊断提供有价值的参考意见。     

Validation of a deformable image registration produced by a commercial treatment planning system in head and neck

In recent years one of the areas of interest in radiotherapy has been adaptive radiation therapy (ART), with the most efficient way of performing ART being the use of deformable image registration (DIR). In this paper we use the distances between points of interest (POIs) in the computed tomography (CT) and the cone beam computed tomography (CBCT) acquisition images and the inverse consistence (IC) property to validate the RayStation treatment planning system (TPS) DIR algorithm. This study was divided into two parts: Firstly the distance-accuracy of the TPS DIR algorithm was ascertained by placing POIs on anatomical features in the CT and CBCT images from five head and neck cancer patients. Secondly, a method was developed for studying the implication of these distances on the dose by using the IC. This method compared the dose received by the structures in the CT, and the structures that were quadruply-deformed. The accuracy of the TPS was 1.7 ± 0.8 mm, and the distance obtained with the quadruply-deformed IC method was 1.7 ± 0.9 mm, i.e. the difference between the IC method multiplied by two, and that of the TPS validation method, was negligible. Moreover, the IC method shows very little variation in the dose-volume histograms when comparing the original and quadruply-deformed structures. This indicates that this algorithm is useful for planning adaptive radiation treatments using CBCT in head and neck cancer patients, although these variations must be taken into account when making a clinical decision to adapt a treatment plan.     

POLCA, a library running in a modern environment, implements a protocol for averaging randomly oriented images

The library POLCA implements the averaging of biological structureswhose images are recorded in digital form from electron micrographs.The averaging protocol is based upon a method developed aboutten years ago, which allows one to operate on a sequence ofobjects oriented and displaced at random within their frame;the relative rotations and the displacements of the structuresare detected with the use of correlation algorithms and modifiedto make all objects appear the same, apart from their noisycomponents. The average image is then obtained by a simple additionand the signal-to-noise ratio is improved by a factor equalto the square root of the number of objects used to calculatethe average. With respect to the original implementation ofthe method, two novel features characterize the library: thefirst one deals with the functions that are cross-correlatedto determine the relative rotations of the structures; the functionsused here are the inverse transforms of the amplitude spectra(IAS functions), which give rise to sharp maxima when they arecross-correlated. The second peculiarity is the systematic adoption,in the transformations of coordinates and in other circumstances,of an interpolation technique based upon the Fourier serieskernel. POLCA is written in C and runs on a VME machine underthe UNIX V/68 operating system. A programming style has beenadopted to exploit fully the machine resources. Received on December 8, 1989; accepted on January 31, 1990     

Machine vision photogrammetry: a technique for measurement of microstructural strain in cortical bone.

Understanding local microstructural deformations and strains in cortical bone may lead to a better understanding of cortical bone damage development, fracture, and remodeling. Traditional experimental techniques for measuring deformation and strain do not allow characterization of these quantities at the microstructural level in cortical bone. This study describes a technique based on digital stereoimaging used to measure the microstructural strain fields in cortical bone. The technique allows the measurement of material surface displacements and strains by comparing images acquired from a specimen at two distinct stress states. The accuracy of the system is investigated by analyzing an undeformed image set; the test image is identical to the reference image but translated by a known pixel amount. An increase in the correlation sub-image train parameter results in an increase in displacement measurement accuracy from 0.049 to 0.012 pixels. Errors in strain calculated from the measured displacement field were between 39 and 564 microstrain depending upon the sub-image train size and applied image displacement. The presence of a microcrack in cortical bone results in local strain at the crack tip reaching 0.030 (30,000 microstrain) and 0.010 (10,000 microstrain) near osteocyte lacunae. It is expected that the use of this technique will allow a greater understanding of bone strength and fracture as well as bone mechanotransduction.