Image Intensity Features Research Articles

Multibeam water column image super-resolution by combining morphological and intensity features

ABSTRACT Multibeam water column images (WCI) play a crucial role in the detection and recognition of underwater targets. However, WCI is not a complete image of underwater space due to the gaps between beams inherent in multibeam systems. In this study, we design the WCI super-resolution network (WCISRN) based on Swin-transformer to adapt to the uneven and sparse distribution of water column data. To enable WCISRN to learn morphological features effectively, we produced simulated datasets for pre-training. Subsequently, we conduct self-supervised training on the measured WCI dataset to fine-tune the network parameters, aiming to better adapt WCISRN to the backscattering intensity features of WCI. Finally, by performing network cross-fusion, the pre-trained network and self-supervised training network are combined to form a new network that achieves a balance between image morphology and intensity features. The proposed method is evaluated through visual analysis and quantitative comparison using simulated and real-world datasets. The experimental results demonstrate that our method exhibits stronger detail restoration ability and clearer image morphology. The average peak signal-to-noise ratio (PSNR) on the test set improved from 23.75–26.14, indicating a significant enhancement in the imaging quality of WCI.

A Radiomics Model for the Differentiation of Intracranial Solitary Fibrous Tumor/Hemangiopericytoma and Meningioma Based on Multiparametric Magnetic Resonance Imaging.

Although the imaging findings of intracranial solitary fibrous tumor (SFT)/hemangiopericytoma (HPC) and meningioma are similar, their treatment and prognosis are quite different. Accurate preoperative identification of these two types of tumors is crucial for individualized treatment. The aim of this study was to develop a radiomics model for the differentiation of intracranial SFT/HPC and meningioma based on multiparametric magnetic resonance imaging (mpMRI). A total of 99 patients from July 2012 to July 2018 with histologically and immunohistochemically confirmed SFT/HPC (n = 40) or meningiomas (n = 59) were retrospectively analyzed. A total of 1118 features were extracted based on its image shape, intensity and texture features. The logistic regression (LR) and multi-layer artificial neural network (ANN) classifiers were used to classify SFT/HPC and meningioma. The predictive performance was calculated using receiver operating characteristic curves (ROC). We found significant difference in terms of sex between the SFT/HPC and meningioma group (χ2= 4.829, P < 0.05), but no significant difference was found in age (P > 0.05). The most significant radiomics features included five shape and four first-order level features. For the LR classifier, the prediction accuracy of SFT/HPC was 71.0% and meningioma was 78.7%. For the ANN classifier, the prediction accuracy of SFT/HPC was 83.9% and meningioma was 80.9%. Both of the two classifiers achieved a high accuracy rate, but ANN was better. Radiomics features, especially when combined with an ANN classifier, can provide satisfactory performance in distinguishing SFT/HPC and meningioma.

An Integrated Clinical-MR Radiomics Model to Estimate Survival Time in Patients With Endometrial Cancer.

Determination of survival time in women with endometrial cancer using clinical features remains imprecise. Features from MRI may improve the survival estimation allowing improved treatment planning. To identify clinical features and imaging signatures on T2-weighted MRI that can be used in an integrated model to estimate survival time for endometrial cancer subjects. Retrospective. Four hundred thirteen patients with endometrial cancer as training (N=330, 66.41 ± 11.42 years) and validation (N=83, 67.60 ± 11.89 years) data and an independent set of 82 subjects as testing data (63.26 ± 12.38 years). 1.5-T and 3-T scanners with sagittal T2-weighted spin echo sequence. Tumor regions were manually segmented on T2-weighted images. Features were extracted from segmented masks, and clinical variables including age, cancer histologic grade and risk score were included in a Cox proportional hazards (CPH) model. A group least absolute shrinkage and selection operator method was implemented to determine the model from the training and validation datasets. A likelihood-ratio test and decision curve analysis were applied to compare the models. Concordance index (CI) and area under the receiver operating characteristic curves (AUCs) were calculated to assess the model. Three radiomic features (two image intensity and volume features) and two clinical variables (age and cancer grade) were selected as predictors in the integrated model. The CI was 0.797 for the clinical model (includes clinical variables only) and 0.818 for the integrated model using training and validation datasets, the associated mean AUC value was 0.805 and 0.853. Using the testing dataset, the CI was 0.792 and 0.882, significantly different and the mean AUC was 0.624 and 0.727 for the clinical model and integrated model, respectively. The proposed CPH model with radiomic signatures may serve as a tool to improve estimated survival time in women with endometrial cancer. 4 TECHNICAL EFFICACY: Stage 2.

An Estimate of Uncertainty in Deformable Image Registration-Based Accumulated Biological Equivalent Dose for Re-Irradiation

<h3>Purpose/Objective(s)</h3> We describe a dose volume histogram (DVH) overlay technique to estimate uncertainty in deformable image registration (DIR) based accumulated biologically equivalent dose (BED) for re-irradiation planning. We compare applicability of two DIR methods, contour-based (C-DIR) and image intensity and contour hybrid (H-DIR) DIR for BED accumulation. <h3>Materials/Methods</h3> Patient CT-based re-irradiation plans to the same anatomic regions as in their initial irradiations over a four-year period were analyzed. Among the organs-at-risk (OARs) for which BED was accumulated were stomach, heart, and esophagus. Physical dose distributions were converted to BED using OAR-specific parameters based on a linear-quadratic-linear model. For C-DIR, the registration was based only upon the contours drawn on both images. H-DIR is an image intensity-based DIR technique which includes contour-based registration to augment the DIR results. All prior BEDs were warped to the most recent CT image for accumulation. Data input to the DVH overlay workflow were the two CT images to be registered, the deformation vector field, the BED on the earlier CT, and the contours on the later CT. The later-CT contours were warped to the earlier CT, and the earlier-CT BED was warped to the later CT; BED DVHs from both images were then calculated and overlaid. For a fully invertible DIR, the two DVHs for the OAR should be identical; differences between the DVHs were interpreted as BED uncertainties due to inverse consistency error. For a given DVH point, the uncertainty was obtained from the differences between the overlaid DVHs. <h3>Results</h3> For an abdomen case, the stomach accumulated BED_max is 3% higher using C-DIR versus H-DIR; ΔBED_max is approximately 2% for both DIR methods. The higher isodoses were distal to the stomach for all plans; H-DIR, which accounts for regions distal to the OAR, is appropriate for re-irradiation BED calculations. For a thoracic case, both DIR methods yield similar results for the heart. The difference between H-DIR and C-DIR for accumulated heart BED_max is 2.4%; ΔBED_max is 0.9% and 0.6% for H-DIR and C-DIR, respectively. For the esophagus, accumulated BED_max is 54% higher using H-DIR instead of C-DIR, and ΔBED_max is much lower for C-DIR (0.2%) than for H-DIR (1.7%). Visual inspection showed that the BED distribution on the esophagus using H-DIR is unreasonable, attributed to H-DIR relying too heavily upon image intensity features. For accurate BED accumulation in the esophagus, C-DIR is essential during the re-irradiation planning for this case. <h3>Conclusion</h3> The DVH overlay technique can estimate the uncertainty in accumulated BED for re-irradiation scenarios. Caution should be exercised in using various DIR methods before applying DIR dose accumulation for re-irradiation planning. Contour-based DIR may be the preferred registration method for re-irradiation dose accumulation.

High-order Feature Learning for Multi-atlas based Label Fusion: Application to Brain Segmentation with MRI.

Multi-atlas based segmentation methods have shown their effectiveness in brain regions-of-interesting (ROIs) segmentation, by propagating labels from multiple atlases to a target image based on the similarity between patches in the target image and multiple atlas images. Most of the existing multiatlas based methods use image intensity features to calculate the similarity between a pair of image patches for label fusion. In particular, using only low-level image intensity features cannot adequately characterize the complex appearance patterns (e.g., the high-order relationship between voxels within a patch) of brain magnetic resonance (MR) images. To address this issue, this paper develops a high-order feature learning framework for multi-atlas based label fusion, where high-order features of image patches are extracted and fused for segmenting ROIs of structural brain MR images. Specifically, an unsupervised feature learning method (i.e., means-covariances restricted Boltzmann machine, mcRBM) is employed to learn high-order features (i.e., mean and covariance features) of patches in brain MR images. Then, a group-fused sparsity dictionary learning method is proposed to jointly calculate the voting weights for label fusion, based on the learned high-order and the original image intensity features. The proposed method is compared with several state-of-the-art label fusion methods on ADNI, NIREP and LONI-LPBA40 datasets. The Dice ratio achieved by our method is 88:30%, 88:83%, 79:54% and 81:02% on left and right hippocampus on the ADNI, NIREP and LONI-LPBA40 datasets, respectively, while the best Dice ratio yielded by the other methods are 86:51%, 87:39%, 78:48% and 79:65% on three datasets, respectively.

Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach.

Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-refined bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localisation tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, a refinement step is designed to explicitly impose shape prior knowledge and improve segmentation quality. This step is effective for overcoming image artefacts (e.g. due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The pipeline is fully automated, due to network’s ability to infer landmarks, which are then used downstream in the pipeline to initialise atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution and anatomically smooth bi-ventricular 3D models, despite the presence of artefacts in input CMR volumes.

Automated fluorescence intensity and gradient analysis enables detection of rare fluorescent mutant cells deep within the tissue of RaDR mice

Homologous recombination (HR) events are key drivers of cancer-promoting mutations, and the ability to visualize these events in situ provides important information regarding mutant cell type, location, and clonal expansion. We have previously created the Rosa26Direct Repeat (RaDR) mouse model wherein HR at an integrated substrate gives rise to a fluorescent cell. To fully leverage this in situ approach, we need better ways to quantify rare fluorescent cells deep within tissues. Here, we present a robust, automated event quantification algorithm that uses image intensity and gradient features to detect fluorescent cells in deep tissue specimens. To analyze the performance of our algorithm, we simulate fluorescence behavior in tissue using Monte Carlo methods. Importantly, this approach reduces the potential for bias in manual counting and enables quantification of samples with highly dense HR events. Using this approach, we measured the relative frequency of HR within a chromosome and between chromosomes and found that HR within a chromosome is more frequent, which is consistent with the close proximity of sister chromatids. Our approach is both objective and highly rapid, providing a powerful tool, not only to researchers interested in HR, but also to many other researchers who are similarly using fluorescence as a marker for understanding mammalian biology in tissues.

Voxel-based automated detection of focal cortical dysplasia lesions using diffusion tensor imaging and T2-weighted MRI data

The aim of this study was to automatically detect focal cortical dysplasia (FCD) lesions in patients with extratemporal lobe epilepsy by relying on diffusion tensor imaging (DTI) and T2-weighted magnetic resonance imaging (MRI) data. We implemented an automated classifier using voxel-based multimodal features to identify gray and white matter abnormalities of FCD in patient cohorts. In addition to the commonly used T2-weighted image intensity feature, DTI-based features were also utilized. A Gaussian processes for machine learning (GPML) classifier was tested on 12 patients with FCD (8 with histologically confirmed FCD) scanned at 1.5 T and cross-validated using a leave-one-out strategy. Moreover, we compared the multimodal GPML paradigm's performance with that of single modal GPML and classical support vector machine (SVM). Our results demonstrated that the GPML performance on DTI-based features (mean AUC = 0.63) matches with the GPML performance on T2-weighted image intensity feature (mean AUC = 0.64). More promisingly, GPML yielded significantly improved performance (mean AUC = 0.76) when applying DTI-based features to multimodal paradigm. Based on the results, it can also be clearly stated that the proposed GPML strategy performed better and is robust to unbalanced dataset contrary to SVM that performed poorly (AUC = 0.69). Therefore, the GPML paradigm using multimodal MRI data containing DTI modality has promising result towards detection of the FCD lesions and provides an effective direction for future researches.

Longitudinally and inter-site consistent multi-atlas based parcellation of brain anatomy using harmonized atlases

As longitudinal and multi-site studies become increasingly frequent in neuroimaging, maintaining longitudinal and inter-scanner consistency of brain parcellation has become a major challenge due to variation in scanner models and/or image acquisition protocols across scanners and sites. We present a new automated segmentation method specifically designed to achieve a consistent parcellation of anatomical brain structures in such heterogeneous datasets. Our method combines a site-specific atlas creation strategy with a state-of-the-art multi-atlas anatomical label fusion framework. Site-specific atlases are computed such that they preserve image intensity characteristics of each site's scanner and acquisition protocol, while atlas pairs share anatomical labels in a way consistent with inter-scanner acquisition variations. This harmonization of atlases improves inter-study and longitudinal consistency of segmentations in the subsequent consensus labeling step. We tested this approach on a large sample of older adults from the Baltimore Longitudinal Study of Aging (BLSA) who had longitudinal scans acquired using two scanners that vary with respect to vendor and image acquisition protocol. We compared the proposed method to standard multi-atlas segmentation for both cross-sectional and longitudinal analyses. The harmonization significantly reduced scanner-related differences in the age trends of ROI volumes, improved longitudinal consistency of segmentations, and resulted in higher across-scanner intra-class correlations, particularly in the white matter.

Early Assessment of Treatment Responses During Radiation Therapy for Lung Cancer Using Quantitative Analysis of Daily Computed Tomography

To investigate early tumor and normal tissue responses during the course of radiation therapy (RT) for lung cancer using quantitative analysis of daily computed tomography (CT) scans. Daily diagnostic-quality CT scans acquired using CT-on-rails during CT-guided RT for 20 lung cancer patients were quantitatively analyzed. On each daily CT set, the contours of the gross tumor volume (GTV) and lungs were generated and the radiation dose delivered was reconstructed. The changes in CT image intensity (Hounsfield unit [HU]) features in the GTV and the multiple normal lung tissue shells around the GTV were extracted from the daily CT scans. The associations between the changes in the mean HUs, GTV, accumulated dose during RT delivery, and patient survival rate were analyzed. During the RT course, radiation can induce substantial changes in the HU histogram features on the daily CT scans, with reductions in the GTV mean HUs (dH) observed in the range of 11 to 48 HU (median 30). The dH is statistically related to the accumulated GTV dose (R2>0.99) and correlates weakly with the change in GTV (R2=0.3481). Statistically significant increases in patient survival rates (P=.038) were observed for patients with a higher dH in the GTV. In the normal lung, the 4 regions proximal to the GTV showed statistically significant (P<.001) HU reductions from the first to last fraction. Quantitative analysis of the daily CT scans indicated that the mean HUs in lung tumor and surrounding normal tissue were reduced during RT delivery. This reduction was observed in the early phase of the treatment, is patient specific, and correlated with the delivered dose. A larger HU reduction in the GTV correlated significantly with greater patient survival. The changes in daily CT features, such as the mean HU, can be used for early assessment of the radiation response during RT delivery for lung cancer.

In Vivo Two-Photon Imaging of Astrocytes in GFAP-GFP Transgenic Mice.

Astrocytes play important roles in normal brain function and neurological diseases. In vivo two-photon excitation laser scanning microscopy has the potential to reveal rapid, dynamic structural changes in cells in a variety of physiological and pathological conditions. The type of in vivo imaging method has been shown to affect the plasticity of dendritic spines of neurons, but the optimal in vivo imaging methods of astrocytes have not been established. We compared open-skull and thinned-skull imaging methods for two-photon laser microscopy of live astrocytes in neocortex of GFAP-GFP transgenic mice. The thinned-skull method provided stable image intensity and morphological features of astrocytes in vivo over at least one week, with no evidence of astrogliosis. In contrast, the open-skull method resulted in significant changes in image intensity and induced astrogliosis. The thinned-skull method is the preferred approach for in vivo imaging of astrocytes under most conditions involving gross astrocyte modulation or causing astrogliosis.

A Methodology for Texture Feature-based Quality Assessment in Nucleus Segmentation of Histopathology Image

Context: Image segmentation pipelines often are sensitive to algorithm input parameters. Algorithm parameters optimized for a set of images do not necessarily produce good-quality-segmentation results for other images. Even within an image, some regions may not be well segmented due to a number of factors, including multiple pieces of tissue with distinct characteristics, differences in staining of the tissue, normal versus tumor regions, and tumor heterogeneity. Evaluation of quality of segmentation results is an important step in image analysis. It is very labor intensive to do quality assessment manually with large image datasets because a whole-slide tissue image may have hundreds of thousands of nuclei. Semi-automatic mechanisms are needed to assist researchers and application developers to detect image regions with bad segmentations efficiently. Aims: Our goal is to develop and evaluate a machine-learning-based semi-automated workflow to assess quality of nucleus segmentation results in a large set of whole-slide tissue images. Methods: We propose a quality control methodology, in which machine-learning algorithms are trained with image intensity and texture features to produce a classification model. This model is applied to image patches in a whole-slide tissue image to predict the quality of nucleus segmentation in each patch. The training step of our methodology involves the selection and labeling of regions by a pathologist in a set of images to create the training dataset. The image regions are partitioned into patches. A set of intensity and texture features is computed for each patch. A classifier is trained with the features and the labels assigned by the pathologist. At the end of this process, a classification model is generated. The classification step applies the classification model to unlabeled test images. Each test image is partitioned into patches. The classification model is applied to each patch to predict the patch’s label. Results: The proposed methodology has been evaluated by assessing the segmentation quality of a segmentation method applied to images from two cancer types in The Cancer Genome Atlas; WHO Grade II lower grade glioma (LGG) and lung adenocarcinoma (LUAD). The results show that our method performs well in predicting patches with good-quality segmentations and achieves F1 scores 84.7% for LGG and 75.43% for LUAD. Conclusions: As image scanning technologies advance, large volumes of whole-slide tissue images will be available for research and clinical use. Efficient approaches for the assessment of quality and robustness of output from computerized image analysis workflows will become increasingly critical to extracting useful quantitative information from tissue images. Our work demonstrates the feasibility of machine-learning-based semi-automated techniques to assist researchers and algorithm developers in this process.

A robust, high-throughput method for computing maize ear, cob, and kernel attributes automatically from images.

Grain yield of the maize plant depends on the sizes, shapes, and numbers of ears and the kernels they bear. An automated pipeline that can measure these components of yield from easily-obtained digital images is needed to advance our understanding of this globally important crop. Here we present three custom algorithms designed to compute such yield components automatically from digital images acquired by a low-cost platform. One algorithm determines the average space each kernel occupies along the cob axis using a sliding-window Fourier transform analysis of image intensity features. A second counts individual kernels removed from ears, including those in clusters. A third measures each kernel's major and minor axis after a Bayesian analysis of contour points identifies the kernel tip. Dimensionless ear and kernel shape traits that may interrelate yield components are measured by principal components analysis of contour point sets. Increased objectivity and speed compared to typical manual methods are achieved without loss of accuracy as evidenced by high correlations with ground truth measurements and simulated data. Millimeter-scale differences among ear, cob, and kernel traits that ranged more than 2.5-fold across a diverse group of inbred maize lines were resolved. This system for measuring maize ear, cob, and kernel attributes is being used by multiple research groups as an automated Web service running on community high-throughput computing and distributed data storage infrastructure. Users may create their own workflow using the source code that is staged for download on a public repository.

An Effective Brain Tumor Detection and Segmentation Technique by Using Watershed Algorithm and Optimized Neural Network

In recent years brain tumor detection using MRI images is an effective clinical research area since MRI images does not make any tissue damage with its radiation and provides useful information about the tissue we are using MRI images in our proposed work for the brain tumor detection. Our proposed brain tumor detection method consists of four sections, i.e., pre-processing, segmentation, feature extraction and classification. Initially the input image fetched from the MRI database will be subjected to skull stripping in order to remove the unwanted region from the image. Then the skull stripped image is segmented using efficient watershed segmentation algorithm. Afterwards from the segmented image shape, intensity and texture features will be extracted. Then that extracted features is given as the input to the ANN classifier. Here the ANN classifier is optimized by well-known ABC optimization technique in order to get the enhanced classification accuracy. Thus from the classified abnormal images the tumor and edema region will be separated using modified region growing algorithm. The results will be analyzed to demonstrate the performance of the proposed segmentation and classification technique with other existing techniques.

Segmenting pectoralis muscle on digital mammograms by a Markov random field-maximum a posteriori model.

Accurate and automatic segmentation of the pectoralis muscle is essential in many breast image processing procedures, for example, in the computation of volumetric breast density from digital mammograms. Its segmentation is a difficult task due to the heterogeneity of the region, neighborhood complexities, and shape variability. The segmentation is achieved by pixel classification through a Markov random field (MRF) image model. Using the image intensity feature as observable data and local spatial information as a priori, the posterior distribution is estimated in a stochastic process. With a variable potential component in the energy function, by the maximum a posteriori (MAP) estimate of the labeling image, given the image intensity feature which is assumed to follow a Gaussian distribution, we achieved convergence properties in an appropriate sense by Metropolis sampling the posterior distribution of the selected energy function. By proposing an adjustable spatial constraint, the MRF-MAP model is able to embody the shape requirement and provide the required flexibility for the model parameter fitting process. We demonstrate that accurate and robust segmentation can be achieved for the curving-triangle-shaped pectoralis muscle in the medio-lateral-oblique (MLO) view, and the semielliptic-shaped muscle in cranio-caudal (CC) view digital mammograms. The applicable mammograms can be either "For Processing" or "For Presentation" image formats. The algorithm was developed using 56 MLO-view and 79 CC-view FFDM "For Processing" images, and quantitatively evaluated against a random selection of 122 MLO-view and 173 CC-view FFDM images of both presentation intent types.

SU-D-BRF-03: Improvement of TomoTherapy Megavoltage Topogram Image Quality for Automatic Registration During Patient Localization

Purpose: To improve the quality of mega-voltage orthogonal scout images (MV topograms) for a fast and low-dose alternative technique for patient localization on the TomoTherapy HiART system. Methods: Digitally reconstructed radiographs (DRR) of anthropomorphic head and pelvis phantoms were synthesized from kVCT under TomoTherapy geometry (kV-DRR). Lateral (LAT) and anterior-posterior (AP) aligned topograms were acquired with couch speeds of 1cm/s, 2cm/s, and 3cm/s. The phantoms were rigidly translated in all spatial directions with known offsets in increments of 5mm, 10mm, and 15mm to simulate daily positioning errors. The contrast of the MV topograms was automatically adjusted based on the image intensity characteristics. A low-pass fast Fourier transform filter removed high-frequency noise and a Weiner filter reduced stochastic noise caused by scattered radiation to the detector array. An intensity-based image registration algorithm was used to register the MV topograms to a corresponding kV-DRR by minimizing the mean square error between corresponding pixel intensities. The registration accuracy was assessed by comparing the normalized cross correlation coefficients (NCC) between the registered topograms and the kV-DRR. The applied phantom offsets were determined by registering the MV topograms with the kV-DRR and recovering the spatial translation of the MV topograms. Results: The automatic registration technique provided millimeter accuracy and was robust for the deformed MV topograms for three tested couch speeds. The lowest average NCC for all AP and LAT MV topograms was 0.96 for the head phantom and 0.93 for the pelvis phantom. The offsets were recovered to within 1.6mm and 6.5mm for the processed and the original MV topograms respectively. Conclusion: Automatic registration of the processed MV topograms to a corresponding kV-DRR recovered simulated daily positioning errors that were accurate to the order of a millimeter. These results suggest the clinical use of MV topograms as a promising alternative to MVCT patient alignment.

New region-scalable discriminant and fitting energy functional for driving geometric active contours in medical image segmentation.

We propose a novel region-based geometric active contour model that uses region-scalable discriminant and fitting energy functional for handling the intensity inhomogeneity and weak boundary problems in medical image segmentation. The region-scalable discriminant and fitting energy functional is defined to capture the image intensity characteristics in local and global regions for driving the evolution of active contour. The discriminant term in the model aims at separating background and foreground in scalable regions while the fitting term tends to fit the intensity in these regions. This model is then transformed into a variational level set formulation with a level set regularization term for accurate computation. The new model utilizes intensity information in the local and global regions as much as possible; so it not only handles better intensity inhomogeneity, but also allows more robustness to noise and more flexible initialization in comparison to the original global region and regional-scalable based models. Experimental results for synthetic and real medical image segmentation show the advantages of the proposed method in terms of accuracy and robustness.

Local label learning (LLL) for subcortical structure segmentation: Application to hippocampus segmentation

Automatic and reliable segmentation of subcortical structures is an important but difficult task in quantitative brain image analysis. Multi-atlas based segmentation methods have attracted great interest due to their promising performance. Under the multi-atlas based segmentation framework, using deformation fields generated for registering atlas images onto a target image to be segmented, labels of the atlases are first propagated to the target image space and then fused to get the target image segmentation based on a label fusion strategy. While many label fusion strategies have been developed, most of these methods adopt predefined weighting models that are not necessarily optimal. In this study, we propose a novel local label learning strategy to estimate the target image's segmentation label using statistical machine learning techniques. In particular, we use a L1-regularized support vector machine (SVM) with a k nearest neighbor (kNN) based training sample selection strategy to learn a classifier for each of the target image voxel from its neighboring voxels in the atlases based on both image intensity and texture features. Our method has produced segmentation results consistently better than state-of-the-art label fusion methods in validation experiments on hippocampal segmentation of over 100 MR images obtained from publicly available and in-house datasets. Volumetric analysis has also demonstrated the capability of our method in detecting hippocampal volume changes due to Alzheimer's disease.

Compass Detection Algorithm based on Image Corner

To improve the Features from Accelerated Segment Test (FAST) algorithm such as artificial threshold setting and the choice and ordering of continuous points on circle, a novel compass detection algorithm is proposed. The algorithm uses four compasses as the test mask and calculates threshold value based on image intensity feature. Four compasses are used to pre-detect corners. In order to improve the location accuracy of corners, pseudo response on skewed edges is eliminated. Finally, multiple adjacent responses are tackled by keeping only points which have extremal value of Laplacian. Comparative experiments between FAST and the proposed algorithm are carried out with respect to validity, robustness and efficiency. The results show that the detected corners by the proposed algorithm are accurately located and well-distributed.

Quantitative image analysis approaches for probing Rab GTPase localization and function in mammalian cells

Membrane traffic pathways play an essential role in cells, providing a mechanism for organelles of the endomembrane system to communicate and exchange material between each other. A significant number of infections and diseases are associated with trafficking pathways, and as such gaining a greater understanding of their regulation is essential. Fluorescence-based imaging techniques are widely used to probe the trafficking machinery within cells, and many of these methods have the potential to be applied in a quantitative manner. In the present mini-review, we highlight several recent examples of how image intensity, kinetic measurements, co-localization and texture feature analysis have been used to study the function of one key family of membrane traffic regulators, the Rab GTPases. We give specific emphasis to the importance of the quantitative nature of these recent studies and comment on their potential applicability to a high-throughput format.