Automated segmentation and classification of high throughput yeast assay spots

Memristive competitive hopfield neural network for image segmentation application

Image segmentation implementation provides simplified and effective feature information of image. Neural network algorithms have made significant progress in the application of image segmentation task. However, few studies focus on the implementation of hardware circuits with high-efficiency analog calculations and parallel operations for image segmentation problem. In this paper, a memristor-based competitive Hopfield neural network circuit is proposed to deal with the image segmentation problem. In this circuit, the memristive cross array is applied to store synaptic weights and perform matrix operations. The competition module based on the Winner-take-all mechanism is composed of the competition neurons and the competition control circuit, which simplifies the energy function of the Hopfield neural network and realizes the output function. Operational amplifiers and ABM modules are used to integrate operations and process external input information, respectively. Based on these designs, the circuit can automatically implement iteration and update of data. A series of PSPICE simulations are designed to verify the image segmentation capability of this circuit. Comparative experimental results and analysis show that this circuit has effective improvements both in processing speed and segmentation accuracy compared with other methods. Moreover, the proposed circuit shows good robustness to noise and memristive variation.

Review on 2D and 3D MRI Image Segmentation Techniques

BACKGROUND

Magnetic Resonance Imaging is most widely used for early diagnosis of abnormalities in human organs. Due to the technical advancement in digital image processing, automatic computer aided medical image segmentation has been widely used in medical diagnostics.

DISCUSSION

Image segmentation is an image processing technique which is used for extracting image features, searching and mining the medical image records for better and accurate medical diagnostics. Commonly used segmentation techniques are threshold based image segmentation, clustering based image segmentation, edge based image segmentation, region based image segmentation, atlas based image segmentation, and artificial neural network based image segmentation.

CONCLUSION

This survey aims at providing an insight about different 2-Dimensional and 3- Dimensional MRI image segmentation techniques and to facilitate better understanding to the people who are new in this field. This comparative study summarizes the benefits and limitations of various segmentation techniques.

A Novel Radial Basis Neural Network-Leveraged Fast Training Method for Identifying Organs in MR Images

We propose a new method for fast organ classification and segmentation of abdominal magnetic resonance (MR) images. Magnetic resonance imaging (MRI) is a new type of high-tech imaging examination fashion in recent years. Recognition of specific target areas (organs) based on MR images is one of the key issues in computer-aided diagnosis of medical images. Artificial neural network technology has made significant progress in image processing based on the multimodal MR attributes of each pixel in MR images. However, with the generation of large-scale data, there are few studies on the rapid processing of large-scale MRI data. To address this deficiency, we present a fast radial basis function artificial neural network (Fast-RBF) algorithm. The importance of our efforts is as follows: (1) The proposed algorithm achieves fast processing of large-scale image data by introducing the ε-insensitive loss function, the structural risk term, and the core-set principle. We apply this algorithm to the identification of specific target areas in MR images. (2) For each abdominal MRI case, we use four MR sequences (fat, water, in-phase (IP), and opposed-phase (OP)) and the position coordinates (x, y) of each pixel as the input of the algorithm. We use three classifiers to identify the liver and kidneys in the MR images. Experiments show that the proposed method achieves a higher precision in the recognition of specific regions of medical images and has better adaptability in the case of large-scale datasets than the traditional RBF algorithm.

Knee Meniscus Segmentation and Tear Detection from MRI: A Review

Background:

Automatic diagnostic systems in medical imaging provide useful information to support radiologists and other relevant experts. The systems that help radiologists in their analysis and diagnosis appear to be increasing.

Discussion:

Knee joints are intensively studied structures, as well. In this review, studies that automatically segment meniscal structures from the knee joint MR images and detect tears have been investigated. Some of the studies in the literature merely perform meniscus segmentation, while others include classification procedures that detect both meniscus segmentation and anomalies on menisci. The studies performed on the meniscus were categorized according to the methods they used. The methods used and the results obtained from such studies were analyzed along with their drawbacks, and the aspects to be developed were also emphasized.

Conclusion:

The work that has been done in this area can effectively support the decisions that will be made by radiology and orthopedics specialists. Furthermore, these operations, which were performed manually on MR images, can be performed in a shorter time with the help of computeraided systems, which enables early diagnosis and treatment.

A comprehensive preclinical assessment of late-term imaging markers of radiation-induced brain injury

Background

Cranial radiotherapy (CRT) is an important part of brain tumor treatment, and although highly effective, survivors suffer from long-term cognitive side effects. In this study we aim to establish late-term imaging markers of CRT-induced brain injury and identify functional markers indicative of cognitive performance. Specifically, we aim to identify changes in executive function, brain metabolism, and neuronal organization.

Methods

Male Sprague Dawley rats were fractionally irradiated at 28 days of age to a total dose of 30 Gy to establish a radiation-induced brain injury model. Animals were trained at 3 months after CRT using the 5-choice serial reaction time task. At 12 months after CRT, animals were evaluated for cognitive and imaging changes, which included positron emission tomography (PET) and magnetic resonance imaging (MRI).

Results

Cognitive deficit with signs of neuroinflammation were found at 12 months after CRT in irradiated animals. CRT resulted in significant volumetric changes in 38% of brain regions as well as overall decrease in brain volume and reduced gray matter volume. PET imaging showed higher brain glucose uptake in CRT animals. Using MRI, irradiated brains had an overall decrease in fractional anisotropy, lower global efficiency, increased transitivity, and altered regional connectivity. Cognitive measurements were found to be significantly correlated with six image features that included myelin integrity and local organization of the neural network.

Conclusions

These results demonstrate that CRT leads to late-term morphological changes, reorganization of neural connections, and metabolic dysfunction. The correlation between imaging markers and cognitive deficits can be used to assess late-term side effects of brain tumor treatment and evaluate efficacy of new interventions.

f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks

Obtaining expert labels in clinical imaging is difficult since exhaustive annotation is time-consuming. Furthermore, not all possibly relevant markers may be known and sufficiently well described a priori to even guide annotation. While supervised learning yields good results if expert labeled training data is available, the visual variability, and thus the vocabulary of findings, we can detect and exploit, is limited to the annotated lesions. Here, we present fast AnoGAN (f-AnoGAN), a generative adversarial network (GAN) based unsupervised learning approach capable of identifying anomalous images and image segments, that can serve as imaging biomarker candidates. We build a generative model of healthy training data, and propose and evaluate a fast mapping technique of new data to the GAN's latent space. The mapping is based on a trained encoder, and anomalies are detected via a combined anomaly score based on the building blocks of the trained model - comprising a discriminator feature residual error and an image reconstruction error. In the experiments on optical coherence tomography data, we compare the proposed method with alternative approaches, and provide comprehensive empirical evidence that f-AnoGAN outperforms alternative approaches and yields high anomaly detection accuracy. In addition, a visual Turing test with two retina experts showed that the generated images are indistinguishable from real normal retinal OCT images. The f-AnoGAN code is available at https://github.com/tSchlegl/f-AnoGAN.

Disrupted development and integrity of frontal white matter in patients treated for pediatric medulloblastoma

Background

Treatment of pediatric medulloblastoma is associated with known neurocognitive deficits that we hypothesize are caused by microstructural damage to frontal white matter (WM).

Methods

Longitudinal MRI examinations were collected from baseline (after surgery but before therapy) to 36 months in 146 patients and at 3 time points in 72 controls. Regional analyses of frontal WM volume and diffusion tensor imaging metrics were performed and verified with tract-based spatial statistics. Age-adjusted, linear mixed-effects models were used to compare patient and control images and to associate imaging changes with Woodcock-Johnson Tests of Cognitive Abilities.

Results

At baseline, WM volumes in patients were similar to those in controls; fractional anisotropy (FA) was lower bilaterally (P < 0.001) and was associated with decreased Processing Speed (P = 0.014) and Broad Attention (P = 0.025) performance at 36 months. During follow-up, WM volumes increased in controls but decreased in patients (P < 0.001) bilaterally. Smaller WM volumes in patients at 36 months were associated with concurrent decreased Working Memory (P = 0.026) performance.

Conclusions

Lower FA in patients with pediatric medulloblastoma compared with age-similar controls indicated that patients suffer substantial acute microstructural damage to supratentorial frontal WM following surgery but before radiation therapy or chemotherapy. Additionally, this damage to the frontal WM was associated with decreased cognitive performance in executive function 36 months later. This early damage also likely contributed to posttherapeutic failure of age-appropriate WM development and to the known association between decreased WM volumes and decreased cognitive performance.

Hair Segmentation Using Heuristically-Trained Neural Networks

We present a method for binary classification using neural networks (NNs) that performs training and classification on the same data using the help of a pretraining heuristic classifier. The heuristic classifier is initially used to segment data into three clusters of high-confidence positives, high-confidence negatives, and low-confidence sets. The high-confidence sets are used to train an NN, which is then used to classify the low-confidence set. Applying this method to the binary classification of hair versus nonhair patches, we obtain a 2.2% performance increase using the heuristically trained NN over the current state-of-the-art hair segmentation method.

Artificial Neural Network to Predict Vine Water Status Spatial Variability Using Multispectral Information Obtained from an Unmanned Aerial Vehicle (UAV)

Water stress, which affects yield and wine quality, is often evaluated using the midday stem water potential (Ψ_stem). However, this measurement is acquired on a per plant basis and does not account for the assessment of vine water status spatial variability. The use of multispectral cameras mounted on unmanned aerial vehicle (UAV) is capable to capture the variability of vine water stress in a whole field scenario. It has been reported that conventional multispectral indices (CMI) that use information between 500–800 nm, do not accurately predict plant water status since they are not sensitive to water content. The objective of this study was to develop artificial neural network (ANN) models derived from multispectral images to predict the Ψ_stem spatial variability of a drip-irrigated Carménère vineyard in Talca, Maule Region, Chile. The coefficient of determination (R²) obtained between ANN outputs and ground-truth measurements of Ψ_stem were between 0.56–0.87, with the best performance observed for the model that included the bands 550, 570, 670, 700 and 800 nm. Validation analysis indicated that the ANN model could estimate Ψ_stem with a mean absolute error (MAE) of 0.1 MPa, root mean square error (RMSE) of 0.12 MPa, and relative error (RE) of −9.1%. For the validation of the CMI, the MAE, RMSE and RE values were between 0.26–0.27 MPa, 0.32–0.34 MPa and −24.2–25.6%, respectively.

Measurable Supratentorial White Matter Volume Changes in Patients with Diffuse Intrinsic Pontine Glioma Treated with an Anti-Vascular Endothelial Growth Factor Agent, Steroids, and Radiation

BACKGROUND AND PURPOSE

Assessing the response to treatment in infiltrative brain tumors by using lesion volume-based response criteria is challenging. We hypothesized that in such tumors, volume measurements alone may not accurately capture changes in actual tumor burden during treatment. We longitudinally evaluated volume changes in both normal-appearing supratentorial white matter and the brain stem lesions in patients treated for diffuse intrinsic pontine glioma to determine to what extent adjuvant systemic therapies may skew the accuracy of tumor response assessments based on volumetric analysis.

MATERIALS AND METHODS

The anatomic MR imaging and diffusion tensor imaging data of 26 patients with diffuse intrinsic pontine glioma were retrospectively analyzed. Treatment included conformal radiation therapy in conjunction with vandetanib and dexamethasone. Volumetric and diffusion data were analyzed with time, and differences between time points were evaluated statistically.

RESULTS

Normalized brain stem lesion volume decreased during combined treatment (slope = -0.222, P < .001) and increased shortly after completion of radiation therapy (slope = 0.422, P < .001). Supratentorial white matter volume steadily and significantly decreased with time (slope = -0.057, P < .001).

CONCLUSIONS

Longitudinal changes in brain stem lesion volume are robust; less pronounced but measurable changes occur in the supratentorial white matter. Volume changes in nonirradiated supratentorial white matter during the disease course reflect the effects of systemic medication on the water homeostasis of normal parenchyma. Our data suggest that adjuvant nontumor-targeted therapies may have a more substantial effect on lesion volume changes than previously thought; hence, an apparent volume decrease in infiltrative tumors receiving combined therapies may lead to overestimation of the actual response and tumor control.

Visualization of heterogeneity and regional grading of gliomas by multiple features using magnetic resonance-based clustered images

Preoperative glioma grading is important for therapeutic strategies and influences prognosis. Intratumoral heterogeneity can cause an underestimation of grading because of the sampling error in biopsies. We developed a voxel-based unsupervised clustering method with multiple magnetic resonance imaging (MRI)-derived features using a self-organizing map followed by K-means. This method produced novel magnetic resonance-based clustered images (MRcIs) that enabled the visualization of glioma grades in 36 patients. The 12-class MRcIs revealed the highest classification performance for the prediction of glioma grading (area under the receiver operating characteristic curve = 0.928; 95% confidential interval = 0.920–0.936). Furthermore, we also created 12-class MRcIs in four new patients using the previous data from the 36 patients as training data and obtained tissue sections of the classes 11 and 12, which were significantly higher in high-grade gliomas (HGGs), and those of classes 4, 5 and 9, which were not significantly different between HGGs and low-grade gliomas (LGGs), according to a MRcI-based navigational system. The tissues of classes 11 and 12 showed features of malignant glioma, whereas those of classes 4, 5 and 9 showed LGGs without anaplastic features. These results suggest that the proposed voxel-based clustering method provides new insights into preoperative regional glioma grading.

SEGMENTATION OF BRAIN MRIs BY SUPPORT VECTOR MACHINE: DETECTION AND CHARACTERIZATION OF STROKES

The aim of our work is the segmentation of healthy and pathological brains to obtain brain structures and extract strokes. We used real magnetic resonance (MR) images weighted on diffusion. The brain was isolated, and the images were filtered by an anisotropic filter, and then segmented by support vector machines (SVMs). We first applied the method on synthetic images to test the performance of the algorithm and adjust the parameters. Then, we compared our results with those obtained by a cooperative approach proposed in a previous paper.

Partial volume effect modeling for segmentation and tissue classification of brain magnetic resonance images: A review

Quantitative analysis of magnetic resonance (MR) brain images are facilitated by the development of automated segmentation algorithms. A single image voxel may contain of several types of tissues due to the finite spatial resolution of the imaging device. This phenomenon, termed partial volume effect (PVE), complicates the segmentation process, and, due to the complexity of human brain anatomy, the PVE is an important factor for accurate brain structure quantification. Partial volume estimation refers to a generalized segmentation task where the amount of each tissue type within each voxel is solved. This review aims to provide a systematic, tutorial-like overview and categorization of methods for partial volume estimation in brain MRI. The review concentrates on the statistically based approaches for partial volume estimation and also explains differences to other, similar image segmentation approaches.

Brain MR image segmentation with spatial constrained K-mean algorithm and dual-tree complex wavelet transform

In brain MR images, the noise and low-contrast significantly deteriorate the segmentation results. In this paper, we propose an automatic unsupervised segmentation method integrating dual-tree complex wavelet transform (DT-CWT) with K-mean algorithm for brain MR image. Firstly, a multi-dimensional feature vector is constructed based on the intensity, the low-frequency subband of DT-CWT and spatial position information. Then, a spatial constrained K-mean algorithm is presented as the segmentation system. The proposed method is validated by extensive experiments using both simulated and real T1-weighted MR images, and compared with the state-of-the-art algorithms.

Prognostic factors that increase the risk for reduced white matter volumes and deficits in attention and learning for survivors of childhood cancers

OBJECTIVE

In children, CNS-directed cancer therapy is thought to result in decreased cerebral white matter volumes (WMV) and subsequent neurocognitive deficits. This study was designed as a prospective validation of the purported reduction in WMV, associated influential factors, and its relationship to neurocognitive deficits in a very large cohort of both acute lymphoblastic leukemia (ALL) and malignant brain tumors (BT) survivors in comparison to an age similar cohort of healthy sibling controls.

PROCEDURES

The effects of host characteristics and CNS treatment intensity on WMV were investigated in 383 childhood cancer survivors (199 ALL, 184 BT) at least 12 months post-completion of therapy and 67 healthy siblings that served as a control group. t-Tests and multiple variable linear models were used to assess cross-sectional WMV and its relation with neurocognitive function.

RESULTS

BT survivors had lower WMV than ALL survivors, who had less than the control group. Increased CNS treatment intensity, younger age at treatment, and greater time since treatment were significantly associated with lower WMV. Additionally, cancer survivors did not perform as well as the control group on neurocognitive measures of intelligence, attention, and academic achievement. Reduced WMV had a larger impact on estimated IQ among females and children treated at a younger age.

CONCLUSIONS

Survivors of childhood cancer that have undergone higher intensity therapy at a younger age have significantly less WMV than their peers and this difference increases with time since therapy. Decreased WMV is associated with significantly lower scores in intelligence, attention, and academic performance in survivors.

Elevated cerebral blood volume contributes to increased FLAIR signal in the cerebral sulci of propofol-sedated children

BACKGROUND AND PURPOSE

Hyperintense FLAIR signal in the cerebral sulci of anesthetized children is attributed to supplemental oxygen (fraction of inspired oxygen) but resembles FLAIR hypersignal associated with perfusion abnormalities in Moyamoya disease and carotid stenosis. We investigated whether cerebral perfusion, known to be altered by anesthesia, contributes to diffuse signal intensity in sulci in children and explored the relative contributions of supplemental oxygen, cerebral perfusion, and anesthesia to signal intensity in sulci.

MATERIALS AND METHODS

Supraventricular signal intensity in sulci on pre- and postcontrast T2 FLAIR images of 24 propofol-sedated children (6.20 ± 3.28 years) breathing supplemental oxygen and 18 nonsedated children (14.28 ± 2.08 years) breathing room air was graded from 0 to 3. The Spearman correlation of signal intensity in sulci with the fraction of inspired oxygen and age in 42 subjects, and with dynamic susceptibility contrast measures of cortical CBF, CBV, and MTT available in 25 subjects, were evaluated overall and compared between subgroups. Factors most influential on signal intensity in sulci were identified by stepwise logistic regression.

RESULTS

CBV was more influential on noncontrast FLAIR signal intensity in sulci than the fraction of inspired oxygen or age in propofol-sedated children (CBV: r = 0.612, P = .026; fraction of inspired oxygen: r = -0.418, P = .042; age: r = 0.523, P = .009) and overall (CBV: r = 0.671, P = .0002; fraction of inspired oxygen: r = 0.442, P = .003; age: r = -0.374, P = .015). MTT (CBV/CBF) was influential in the overall cohort (r = 0.461, P = .020). Signal intensity in sulci increased with contrast in 45% of subjects, decreased in none, and was greater (P < .0001) in younger propofol-sedated subjects, in whom the signal intensity in sulci increased with age postcontrast (r = .600, P = .002).

CONCLUSIONS

Elevated cortical CBV appears to contribute to increased signal intensity in sulci on noncontrast FLAIR in propofol-sedated children. The effects of propofol on age-related cerebral perfusion and vascular permeability may play a role.

Comparing segmented ASL perfusion of vascular territories using manual versus semiautomated techniques in children with sickle cell anemia

PURPOSE

Elevated cerebral blood flow (CBF) in sickle cell anemia (SCA) is an adaptive pathophysiologic response associated with decreased vascular reserve and increased risk for ischemia. We compared manual (M) and semiautomated (SA) vascular territory delineation to facilitate standardized evaluation of CBF in children with SCA.

MATERIALS AND METHODS

ASL perfusion values from 21 children were compared for gray matter and white matter (WM) in vascular territories defined by M and SA delineation. SA delineated CBF was compared with clinical and hematologic variables acquired within 4 weeks of the MRI.

RESULTS

CBF measurements from M (MCA 82 left, 79 right) and SA (MCA 81 left, 81 right) delineated territories were highly correlated (R = 0.99, P < 0.0001). Bland-Altman plots had close-fitting limits of agreement of -1.8 to -3.5 lower limit and 0 to 1.8 upper limit. SA vascular territory delineation was comparable to the expert delineation with a kappa index of 0.62-0.85 and was considerably faster. Median territorial CBF values did not differ by gender or age. WM perfusion in the posterior cerebral artery territories was positively correlated with degree of hemolysis (R = 0.58, P = 0.01 left, 0.73, P < 0.001 right) and negatively correlated with hemoglobin (R = -0.48; P = 0.03 left; -0.47; P = 0.04 right) and hemoglobin F (R = -0.42; P = .09 left; -0.47; P = 0.049 right).

CONCLUSION

We established the validity of the SA method, which in our experience was much faster than the M method for delineation of vascular territories. Associations between CBF and hematologic variables may demonstrate pathophysiologic changes that contribute to clinical variation in CBF.

SELF-SUPERVISED MRI TISSUE SEGMENTATION BY DISCRIMINATIVE CLUSTERING

The study of brain lesions can benefit from a clear identification of transitions between healthy and pathological tissues, through the analysis of brain imaging data. Current signal processing methods, able to address these issues, often rely on strong prior information. In this article, a new method for tissue segmentation is proposed. It is based on a discriminative strategy, in a self-supervised machine learning approach. This method avoids the use of prior information, which makes it very versatile, and able to cope with different tissue types. It also returns tissue probabilities for each voxel, crucial for a good characterization of the evolution of brain lesions. Simulated as well as real benchmark data were used to validate the accuracy of the method and compare it against other segmentation algorithms.

State of the art survey on MRI brain tumor segmentation

Brain tumor segmentation consists of separating the different tumor tissues (solid or active tumor, edema, and necrosis) from normal brain tissues: gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). In brain tumor studies, the existence of abnormal tissues may be easily detectable most of the time. However, accurate and reproducible segmentation and characterization of abnormalities are not straightforward. In the past, many researchers in the field of medical imaging and soft computing have made significant survey in the field of brain tumor segmentation. Both semiautomatic and fully automatic methods have been proposed. Clinical acceptance of segmentation techniques has depended on the simplicity of the segmentation, and the degree of user supervision. Interactive or semiautomatic methods are likely to remain dominant in practice for some time, especially in these applications where erroneous interpretations are unacceptable. This article presents an overview of the most relevant brain tumor segmentation methods, conducted after the acquisition of the image. Given the advantages of magnetic resonance imaging over other diagnostic imaging, this survey is focused on MRI brain tumor segmentation. Semiautomatic and fully automatic techniques are emphasized.

The effects of propofol on cerebral perfusion MRI in children

INTRODUCTION

The effects of anesthesia are infrequently considered when interpreting pediatric perfusion magnetic resonance imaging (MRI). The objectives of this study were to test for measurable differences in MR measures of cerebral blood flow (CBF) and cerebral blood volume (CBV) between non-sedated and propofol-sedated children, and to identify influential factors.

METHODS

Supratentorial cortical CBF and CBV measured by dynamic susceptibility contrast perfusion MRI in 37 children (1.8-18 years) treated for infratentorial brain tumors receiving propofol (IV, n = 19) or no sedation (NS, n = 18) were compared between groups and correlated with age, hematocrit (Hct), end-tidal CO₂ (ETCO₂), dose, weight, and history of radiation therapy (RT). The model most predictive of CBF and CBV was identified by multiple linear regression.

RESULTS

Anterior cerebral artery (ACA) and middle cerebral artery (MCA) territory CBF were significantly lower, and MCA territory CBV greater (p = 0.03), in IV than NS patients (p = 0.01, 0.04). The usual trend of decreasing CBF with age was reversed with propofol in ACA and MCA territories (r = 0.53, r = 0.47; p < 0.05). ACA and MCA CBF (r = 0.59, 0.49; p < 0.05) and CBV in ACA, MCA, and posterior cerebral artery territories (r = 0.73, 0.80, 0.52; p < 0.05) increased with weight in propofol-sedated children, with no significant additional influence from age, ETCO₂, hematocrit, or RT.

CONCLUSION

In propofol-sedated children, usual age-related decreases in CBF were reversed, and increases in CBF and CBV were weight-dependent, not previously described. Weight-dependent increases in propofol clearance may diminish suppression of CBF and CBV. Prospective study is required to establish anesthetic-specific models of CBF and CBV in children.

A prior feature SVM-MRF based method for mouse brain segmentation

We introduce an automated method, called prior feature Support Vector Machine-Markov Random Field (pSVMRF), to segment three-dimensional mouse brain Magnetic Resonance Microscopy (MRM) images. Our earlier work, extended MRF (eMRF) integrated Support Vector Machine (SVM) and Markov Random Field (MRF) approaches, leading to improved segmentation accuracy; however, the computation of eMRF is very expensive, which may limit its performance on segmentation and robustness. In this study pSVMRF reduces training and testing time for SVM, while boosting segmentation performance. Unlike the eMRF approach, where MR intensity information and location priors are linearly combined, pSVMRF combines this information in a nonlinear fashion, and enhances the discriminative ability of the algorithm. We validate the proposed method using MR imaging of unstained and actively stained mouse brain specimens, and compare segmentation accuracy with two existing methods: eMRF and MRF. C57BL/6 mice are used for training and testing, using cross validation. For formalin fixed C57BL/6 specimens, pSVMRF outperforms both eMRF and MRF. The segmentation accuracy for C57BL/6 brains, stained or not, was similar for larger structures like hippocampus and caudate putamen, (~87%), but increased substantially for smaller regions like susbtantia nigra (from 78.36% to 91.55%), and anterior commissure (from ~50% to ~80%). To test segmentation robustness against increased anatomical variability we add two strains, BXD29 and a transgenic mouse model of Alzheimer's disease. Segmentation accuracy for new strains is 80% for hippocampus, and caudate putamen, indicating that pSVMRF is a promising approach for phenotyping mouse models of human brain disorders.

Attention and working memory abilities in children treated for acute lymphoblastic leukemia

BACKGROUND

To extend investigation beyond global cognitive measures prevalent in the literature, this study examined attention and working memory (WM) abilities of survivors of childhood acute lymphoblastic leukemia (ALL), the separate contributions of attention and WM to intelligence quotient (IQ), and their association with neuroimaging changes.

METHODS

Ninety-seven children with ALL received risk-directed therapy based on presenting clinical and biological factors. During consolidation therapy, low-risk patients received half the dose of intravenous methotrexate that standard-risk/high-risk patients received, and fewer doses of triple intrathecal therapy. Patients were classified according to end of consolidation magnetic resonance imaging scans (normal or leukoencephalopathy), and continuous measures of white matter structure were computed. As part of the protocol study, children completed cognitive assessment 2 years later (completion of therapy), using Digit Span Forward (DSF) for attention and Digit Span Backward (DSB) for WM.

RESULTS

For the total sample and the standard-/high-risk group, Total Digit Span (TDS), DSF, and DSB were impaired relative to norms (P<.05). In the low-risk group, only DSB was impaired (P<.0001). Across groups, a higher percentage of patients performed below the average range (scale score<7) on DSB (66%) compared with the DSF (14%) or TDS (18%). Regression analysis indicated that DSB predicted estimated IQ (P<.05), after accounting for DSF. Leukoencephalopathy was predictive of lower TDS (P<.05).

CONCLUSIONS

WM appears to be especially sensitive to treatment-related changes in ALL survivors, detecting difficulties potentially missed by global intelligence measures. These findings may facilitate the identification of vulnerable neural pathways and the development of targeted cognitive interventions.

Artificial Neural Network-Based System for PET Volume Segmentation

Tumour detection, classification, and quantification in positron emission tomography (PET) imaging at early stage of disease are important issues for clinical diagnosis, assessment of response to treatment, and radiotherapy planning. Many techniques have been proposed for segmenting medical imaging data; however, some of the approaches have poor performance, large inaccuracy, and require substantial computation time for analysing large medical volumes. Artificial intelligence (AI) approaches can provide improved accuracy and save decent amount of time. Artificial neural networks (ANNs), as one of the best AI techniques, have the capability to classify and quantify precisely lesions and model the clinical evaluation for a specific problem. This paper presents a novel application of ANNs in the wavelet domain for PET volume segmentation. ANN performance evaluation using different training algorithms in both spatial and wavelet domains with a different number of neurons in the hidden layer is also presented. The best number of neurons in the hidden layer is determined according to the experimental results, which is also stated Levenberg-Marquardt backpropagation training algorithm as the best training approach for the proposed application. The proposed intelligent system results are compared with those obtained using conventional techniques including thresholding and clustering based approaches. Experimental and Monte Carlo simulated PET phantom data sets and clinical PET volumes of nonsmall cell lung cancer patients were utilised to validate the proposed algorithm which has demonstrated promising results.

The brain MR Image segmentation techniques and use of diagnostic packages

RATIONALE AND OBJECTIVES

This article provides a survey of segmentation methods for medical images. Usually, classification of segmentation methods is done based on the approaches adopted and the domain of application.

MATERIALS AND METHODS

This survey is conducted on the recent segmentation methods used in biomedical image processing and explores the methods useful for better segmentation. A critical appraisal of the current status of semiautomated and automated methods is made for the segmentation of anatomical medical images emphasizing the advantages and disadvantages. Computer-aided diagnosis (CAD) used by radiologists as a second opinion has become one of the major research areas in medical imaging and diagnostic radiology. A picture archiving communication system (PACS) is an integrated workflow system for managing images and related data that is designed to streamline operations throughout the whole patient care delivery process.

RESULTS

By using PACS, the medical image interpretation may be changed from conventional hard-copy images to soft-copy studies viewed on the systems workstations.

CONCLUSION

The automatic segmentations assist the doctors in making quick diagnosis. The CAD need not be comparable to that of physicians, but is surely complementary.

Automated classification of multi-spectral MR images using Linear Discriminant Analysis

Magnetic resonance imaging (MRI) is a valuable instrument in medical science owing to its capabilities in soft tissue characterization and 3D visualization. A potential application of MRI in clinical practice is brain parenchyma classification. This work proposes a novel approach called "Unsupervised Linear Discriminant Analysis (ULDA)" to classify and segment the three major tissues, i.e. gray matter (GM), white matter (WM) and cerebral spinal fluid (CSF), from a multi-spectral MR image of the human brain. The ULDA comprises two processes, namely Target Generation Process (TGP) and Linear Discriminant Analysis (LDA) classification. TGP is a fuzzy-set process that generates a set of potential targets from unknown information, and applies these targets to train the optimal division boundary by LDA, such that three tissues GM, WM and CSF are separated. Finally, two sets of images, namely computer-generated phantom images and real MR images are used in the experiments to evaluate the effectiveness of ULDA. Experiment results reveal that UDLA segments a multi-spectral MR image much more effectively than either FMRIB's Automated Segmentation Tool (FAST) or Fuzzy C-means (FC).

Automated ventricular systems segmentation in brain CT images by combining low-level segmentation and high-level template matching

Background

Accurate analysis of CT brain scans is vital for diagnosis and treatment of Traumatic Brain Injuries (TBI). Automatic processing of these CT brain scans could speed up the decision making process, lower the cost of healthcare, and reduce the chance of human error. In this paper, we focus on automatic processing of CT brain images to segment and identify the ventricular systems. The segmentation of ventricles provides quantitative measures on the changes of ventricles in the brain that form vital diagnosis information.

Methods

First all CT slices are aligned by detecting the ideal midlines in all images. The initial estimation of the ideal midline of the brain is found based on skull symmetry and then the initial estimate is further refined using detected anatomical features. Then a two-step method is used for ventricle segmentation. First a low-level segmentation on each pixel is applied on the CT images. For this step, both Iterated Conditional Mode (ICM) and Maximum A Posteriori Spatial Probability (MASP) are evaluated and compared. The second step applies template matching algorithm to identify objects in the initial low-level segmentation as ventricles. Experiments for ventricle segmentation are conducted using a relatively large CT dataset containing mild and severe TBI cases.

Results

Experiments show that the acceptable rate of the ideal midline detection is over 95%. Two measurements are defined to evaluate ventricle recognition results. The first measure is a sensitivity-like measure and the second is a false positive-like measure. For the first measurement, the rate is 100% indicating that all ventricles are identified in all slices. The false positives-like measurement is 8.59%. We also point out the similarities and differences between ICM and MASP algorithms through both mathematically relationships and segmentation results on CT images.

Conclusion

The experiments show the reliability of the proposed algorithms. The novelty of the proposed method lies in its incorporation of anatomical features for ideal midline detection and the two-step ventricle segmentation method. Our method offers the following improvements over existing approaches: accurate detection of the ideal midline and accurate recognition of ventricles using both anatomical features and spatial templates derived from Magnetic Resonance Images.

Cerebellocerebral diaschisis is the likely mechanism of postsurgical posterior fossa syndrome in pediatric patients with midline cerebellar tumors

BACKGROUND AND PURPOSE

PFS occurs in approximately 25% of pediatric patients receiving surgery for midline posterior fossa tumors. Increasing evidence suggests that PFS represents a complex supratentorial cortical dysfunction related to surgery-induced disruption of critical cerebellocerebral connections. The purpose of this study was to determine whether a consistent surgical damage pattern may be identified in patients with PFS by early postoperative anatomic imaging analysis of the pECP and to test whether DSC can detect corresponding changes in cerebral cortical perfusion to indicate a secondary, remote functional disturbance, which could suggest a diaschisis-like pathomechanism.

MATERIALS AND METHODS

Eleven patients with postoperative PFS were evaluated retrospectively and were paired with age- and sex-matched control subjects in whom PFS did not develop. MR imaging work-up included DSC within 3 to 4 weeks after surgery as well as early postoperative anatomic imaging to evaluate components of the pECP.

RESULTS

DSC showed significant decreases in CBF within frontal regions (P < .05) and a trend to global cerebral cortical hypoperfusion in patients with PFS. Logistic regression analysis suggested a strong (potentially predictive) relationship between bilateral damage to pECP and the development of PFS (P = .04).

CONCLUSIONS

Our data suggest that the primary cause of PFS is the bilateral surgical damage to the pECP. This leads to a trans-synaptic cerebral cortical dysfunction (a form of bilateral crossed cerebellocerebral diaschisis), which manifests with DSC-detectable global, but dominantly frontal, cortical hypoperfusion in patients with patients with PFS compared with age- and sex-matched control subjects.

Gaussian mixture model-based segmentation of MR images taken from premature infant brains

Segmentation of Magnetic Resonance multi-layer images of premature infant brain has additional challenges in comparison to normal adult brain segmentation. Images of premature infants contain lower signal to noise ratio due to shorter scanning times. Further, anatomic structure include still greater variations which can impair the accuracy of standard brain models. A fully automatic brain segmentation method for T1-weighted images is proposed in present paper. The method uses watershed segmentation with Gaussian mixture model clustering for segmenting cerebrospinal fluid from brain matter and other head tissues. The effect of the myelination process is considered by utilizing information from T2-weighted images. The performance of the new method is compared voxel-by-voxel to the corresponding expert segmentation. The proposed method is found to produce more uniform results in comparison to three accustomary segmentation methods originally developed for adults. This is the case in particular when anatomic forms are still under development and differ in their form from those of adults.

Automatic segmentation of the human brain ventricles from MR images by knowledge-based region growing and trimming

Automatic segmentation of the human brain ventricular system from MR images is useful in studies of brain anatomy and its diseases. Existing intensity-based segmentation methods are adaptive to large shape and size variations of the ventricular system, but may leak to the non-ventricular regions due to the non-homogeneity, noise and partial volume effect in the images. Deformable model-based methods are more robust to noise and alleviate the leakage problem, but may generate wrong results when the shape or size of the ventricle to be segmented in the images has a large difference in comparison to its model. In this paper, we propose a knowledge-based region growing and trimming approach where: (1) a model of a ventricular system is used to define regions of interest (ROI) for the four ventricles (i.e., left, right, third and fourth); (2) to segment a ventricle in its ROI, a region growing procedure is first applied to obtain a connected region that contains the ventricle, and (3) a region trimming procedure is then employed to trim the non-ventricle regions. A hysteretic thresholding is developed for the region growing procedure to cope with the partial volume effect and minimize non-ventricular regions. The domain knowledge on the shape and intensity features of the ventricular system is used for the region trimming procedure. Due to the joint use of the model-based and intensity-based approaches, our method is robust to noise and large shape and size variations. Experiments on 18 simulated and 58 clinical MR images show that the proposed approach is able to segment the ventricular system accurately with the dice similarity coefficient ranging from 91% to 99%.

Automatic cropping of MRI rat brain volumes using pulse coupled neural networks

The Pulse Coupled Neural Network (PCNN) was developed by Eckhorn to model the observed synchronization of neural assemblies in the visual cortex of small mammals such as a cat. In this paper we show the use of the PCNN as an image segmentation strategy to crop MR images of rat brain volumes. We then show the use of the associated PCNN image 'signature' to automate the brain cropping process with a trained artificial neural network. We tested this novel algorithm on three T2 weighted acquisition configurations comprising a total of 42 rat brain volumes. The datasets included 40 ms, 48 ms and 53 ms effective TEs, acquisition field strengths of 4.7 T and 9.4 T, image resolutions from 64x64 to 256x256, slice locations ranging from +6 mm to -11 mm AP, two different surface coil manufacturers and imaging protocols. The results were compared against manually segmented gold standards and Brain Extraction Tool (BET) V2.1 results. The Jaccard similarity index was used for numerical evaluation of the proposed algorithm. Our novel PCNN cropping system averaged 0.93 compared to BET scores circa 0.84.