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

Automated ventricular segmentation and shunt failure detection using convolutional neural networks

While ventricular shunts are the main treatment for adult hydrocephalus, shunt malfunction remains a common problem that can be challenging to diagnose. Computer vision-derived algorithms present a potential solution. We designed a feasibility study to see if such an algorithm could automatically predict ventriculomegaly indicative of shunt failure in a real-life adult hydrocephalus population. We retrospectively identified a consecutive series of adult shunted hydrocephalus patients over an eight-year period. Associated computed tomography scans were extracted and each scan was reviewed by two investigators. A machine learning algorithm was trained to identify the lateral and third ventricles, and then applied to test scans. Results were compared to human performance using Sørensen-Dice coefficients, calculated total ventricular volumes, and ventriculomegaly as documented in the electronic medical record. 5610 axial images from 191 patients were included for final analysis, with 52 segments (13.6% of total data) reserved for testing. Algorithmic performance on the test group averaged a Dice score of 0.809 ± 0.094. Calculated total ventricular volumes did not differ significantly between computer-derived volumes and volumes marked by either the first reviewer or second reviewer (p > 0.05). Algorithm detection of ventriculomegaly was correct in all test cases and this correlated with correct prediction of need for shunt revision in 92.3% of test cases. Though development challenges remain, it is feasible to create automated algorithms that detect ventriculomegaly in adult hydrocephalus shunt malfunction with high reliability and accuracy.

Deep learning-based segmentation of brain parenchyma and ventricular system in CT scans in the presence of anomalies

INTRODUCTION

The automatic segmentation of brain parenchyma and cerebrospinal fluid-filled spaces such as the ventricular system is the first step for quantitative and qualitative analysis of brain CT data. For clinical practice and especially for diagnostics, it is crucial that such a method is robust to anatomical variability and pathological changes such as (hemorrhagic or neoplastic) lesions and chronic defects. This study investigates the increase in overall robustness of a deep learning algorithm that is gained by adding hemorrhage training data to an otherwise normal training cohort.

METHODS

A 2D U-Net is trained on subjects with normal appearing brain anatomy. In a second experiment the training data includes additional subjects with brain hemorrhage on image data of the RSNA Brain CT Hemorrhage Challenge with custom reference segmentations. The resulting networks are evaluated on normal and hemorrhage test casesseparately, and on an independent test set of patients with brain tumors of the publicly available GLIS-RT dataset.

RESULTS

Adding data with hemorrhage to the training set significantly improves the segmentation performance over an algorithm trained exclusively on normally appearing data, not only in the hemorrhage test set but also in the tumor test set. The performance on normally appearing data is stable. Overall, the improved algorithm achieves median Dice scores of 0.98 (parenchyma), 0.91 (left ventricle), 0.90 (right ventricle), 0.81 (third ventricle), and 0.80 (fourth ventricle) on the hemorrhage test set. On the tumor test set, the median Dice scores are 0.96 (parenchyma), 0.90 (left ventricle), 0.90 (right ventricle), 0.75 (third ventricle), and 0.73 (fourth ventricle).

CONCLUSION

Training on an extended data set that includes pathologies is crucial and significantly increases the overall robustness of a segmentation algorithm for brain parenchyma and ventricular system in CT data, also for anomalies completely unseen during training. Extension of the training set to include other diseases may further improve the generalizability of the algorithm.

ICUnet++: an Inception-CBAM network based on Unet++ for MR spine image segmentation

In recent years, more attention paid to the spine caused by related diseases, spinal parsing (the multi-class segmentation of vertebrae and intervertebral disc) is an important part of the diagnosis and treatment of various spinal diseases. The more accurate the segmentation of medical images, the more convenient and quick the clinicians can evaluate and diagnose spinal diseases. Traditional medical image segmentation is often time consuming and energy consuming. In this paper, an efficient and novel automatic segmentation network model for MR spine images is designed. The proposed Inception-CBAM Unet++ (ICUnet++) model replaces the initial module with the Inception structure in the encoder-decoder stage base on Unet++ , which uses the parallel connection of multiple convolution kernels to obtain the features of different receptive fields during in the feature extraction. According to the characteristics of the attention mechanism, Attention Gate module and CBAM module are used in the network to make the attention coefficient highlight the characteristics of the local area. To evaluate the segmentation performance of network model, four evaluation metrics, namely intersection over union (IoU), dice similarity coefficient(DSC), true positive rate(TPR), positive predictive value(PPV) are used in the study. The published SpineSagT2Wdataset3 spinal MRI dataset is used during the experiments. In the experiment results, IoU reaches 83.16%, DSC is 90.32%, TPR is 90.40%, and PPV is 90.52%. It can be seen that the segmentation indicators have been significantly improved, which reflects the effectiveness of the model.

AI-based medical e-diagnosis for fast and automatic ventricular volume measurement in patients with normal pressure hydrocephalus

Based on CT and MRI images acquired from normal pressure hydrocephalus (NPH) patients, using machine learning methods, we aim to establish a multimodal and high-performance automatic ventricle segmentation method to achieve an efficient and accurate automatic measurement of the ventricular volume. First, we extract the brain CT and MRI images of 143 definite NPH patients. Second, we manually label the ventricular volume (VV) and intracranial volume (ICV). Then, we use the machine learning method to extract features and establish automatic ventricle segmentation model. Finally, we verify the reliability of the model and achieved automatic measurement of VV and ICV. In CT images, the Dice similarity coefficient (DSC), intraclass correlation coefficient (ICC), Pearson correlation, and Bland-Altman analysis of the automatic and manual segmentation result of the VV were 0.95, 0.99, 0.99, and 4.2 ± 2.6, respectively. The results of ICV were 0.96, 0.99, 0.99, and 6.0 ± 3.8, respectively. The whole process takes 3.4 ± 0.3 s. In MRI images, the DSC, ICC, Pearson correlation, and Bland-Altman analysis of the automatic and manual segmentation result of the VV were 0.94, 0.99, 0.99, and 2.0 ± 0.6, respectively. The results of ICV were 0.93, 0.99, 0.99, and 7.9 ± 3.8, respectively. The whole process took 1.9 ± 0.1 s. We have established a multimodal and high-performance automatic ventricle segmentation method to achieve efficient and accurate automatic measurement of the ventricular volume of NPH patients. This can help clinicians quickly and accurately understand the situation of NPH patient's ventricles.

Methodology, clinical applications, and future directions of body composition analysis using computed tomography (CT) images: A review

PURPOSE OF THE REVIEW

We aim to review the methods, current research evidence, and future directions in body composition analysis (BCA) with CT imaging.

RECENT FINDINGS

CT images can be used to evaluate muscle tissue, visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT) compartments. Manual and semiautomatic segmentation methods are still the gold standards. The segmentation of skeletal muscle tissue and VAT and SAT compartments is most often performed at the level of the 3rd lumbar vertebra. A decreased amount of CT-determined skeletal muscle mass is a marker of impaired survival in many patient populations, including patients with most types of cancer, some surgical patients, and those admitted to the intensive care unit (ICU). Patients with increased VAT are more susceptible to impaired survival / worse outcomes; however, those patients who are critically ill or admitted to the ICU or who will undergo surgery appear to be exceptions. The independent significance of SAT is less well established. Recently, the roles of the CT-determined decrease of muscle mass and increased VAT area and epicardial adipose tissue (EAT) volume have been shown to predict a more debilitating course of illness in patients suffering from severe acute respiratory syndrome coronavirus 2 (COVID-19) infection.

SUMMARY

The field of CT-based body composition analysis is rapidly evolving and shows great potential for clinical implementation.

IBA-U-Net: Attentive BConvLSTM U-Net with Redesigned Inception for medical image segmentation

Accurate segmentation of medical images plays an essential role in their analysis and has a wide range of research and application values in fields of practice such as medical research, disease diagnosis, disease analysis, and auxiliary surgery. In recent years, deep convolutional neural networks have been developed that show strong performance in medical image segmentation. However, because of the inherent challenges of medical images, such as irregularities of the dataset and the existence of outliers, segmentation approaches have not demonstrated sufficiently accurate and reliable results for clinical employment. Our method is based on three key ideas: (1) integrating the BConvLSTM block and the Attention block to reduce the semantic gap between the encoder and decoder feature maps to make the two feature maps more homogeneous, (2) factorizing convolutions with a large filter size by Redesigned Inception, which uses a multiscale feature fusion method to significantly increase the effective receptive field, and (3) devising a deep convolutional neural network with multiscale feature fusion and a Attentive BConvLSTM mechanism, which integrates the Attentive BConvLSTM block and the Redesigned Inception block into an encoder-decoder model called Attentive BConvLSTM U-Net with Redesigned Inception (IBA-U-Net). Our proposed architecture, IBA-U-Net, has been compared with the U-Net and state-of-the-art segmentation methods on three publicly available datasets, the lung image segmentation dataset, skin lesion image dataset, and retinal blood vessel image segmentation dataset, each with their unique challenges, and it has improved the prediction performance even with slightly less calculation expense and fewer network parameters. By devising a deep convolutional neural network with a multiscale feature fusion and Attentive BConvLSTM mechanism, medical image segmentation of different tasks can be completed effectively and accurately with only 45% of U-Net parameters.

Systematic and Comprehensive Automated Ventricle Segmentation on Ventricle Images of the Elderly Patients: A Retrospective Study

Background and Objective: Ventricle volume is closely related to hydrocephalus, brain atrophy, Alzheimer's, Parkinson's syndrome, and other diseases. To accurately measure the volume of the ventricles for elderly patients, we use deep learning to establish a systematic and comprehensive automated ventricle segmentation framework.

Methods: The study participation included 20 normal elderly people, 20 patients with cerebral atrophy, 64 patients with normal pressure hydrocephalus, and 51 patients with acquired hydrocephalus. Second, get their imaging data through the picture archiving and communication systems (PACS) system. Then use ITK software to manually label participants' ventricular structures. Finally, extract imaging features through machine learning.

Results: This automated ventricle segmentation method can be applied not only to CT and MRI images but also to images with different scan slice thicknesses. More importantly, it produces excellent segmentation results (Dice > 0.9).

Conclusion: This automated ventricle segmentation method has wide applicability and clinical practicability. It can help clinicians find early disease, diagnose disease, understand the patient's disease progression, and evaluate the patient's treatment effect.

Coronary angiography video segmentation method for assisting cardiovascular disease interventional treatment

Background

Coronary heart disease is one of the diseases with the highest mortality rate. Due to the important position of cardiovascular disease prevention and diagnosis in the medical field, the segmentation of cardiovascular images has gradually become a research hotspot. How to segment accurate blood vessels from coronary angiography videos to assist doctors in making accurate analysis has become the goal of our research.

Method

Based on the U-net architecture, we use a context-based convolutional network for capturing more information of the vessel in the video. The proposed method includes three modules: the sequence encoder module, the sequence decoder module, and the sequence filter module. The high-level information of the feature is extracted in the encoder module. Multi-kernel pooling layers suitable for the extraction of blood vessels are added before the decoder module. In the filter block, we add a simple temporal filter to reducing inter-frame flickers.

Results

The performance comparison with other method shows that our work can achieve 0.8739 in Sen, 0.9895 in Acc. From the performance of the results, the accuracy of our method is significantly improved. The performance benefit from the algorithm architecture and our enlarged dataset.

Conclusion

Compared with previous methods that only focus on single image analysis, our method can obtain more coronary information through image sequences. In future work, we will extend the network to 3D networks.

CTumorGAN: a unified framework for automatic computed tomography tumor segmentation

PURPOSE

Unlike the normal organ segmentation task, automatic tumor segmentation is a more challenging task because of the existence of similar visual characteristics between tumors and their surroundings, especially on computed tomography (CT) images with severe low contrast resolution, as well as the diversity and individual characteristics of data acquisition procedures and devices. Consequently, most of the recently proposed methods have become increasingly difficult to be applied on a different tumor dataset with good results, and moreover, some tumor segmentors usually fail to generalize beyond those datasets and modalities used in their original evaluation experiments.

METHODS

In order to alleviate some of the problems with the recently proposed methods, we propose a novel unified and end-to-end adversarial learning framework for automatic segmentation of any kinds of tumors from CT scans, called CTumorGAN, consisting of a Generator network and a Discriminator network. Specifically, the Generator attempts to generate segmentation results that are close to their corresponding golden standards, while the Discriminator aims to distinguish between generated samples and real tumor ground truths. More importantly, we deliberately design different modules to take into account the well-known obstacles, e.g., severe class imbalance, small tumor localization, and the label noise problem with poor expert annotation quality, and then use these modules to guide the CTumorGAN training process by utilizing multi-level supervision more effectively.

RESULTS

We conduct a comprehensive evaluation on diverse loss functions for tumor segmentation and find that mean square error is more suitable for the CT tumor segmentation task. Furthermore, extensive experiments with multiple evaluation criteria on three well-established datasets, including lung tumor, kidney tumor, and liver tumor databases, also demonstrate that our CTumorGAN achieves stable and competitive performance compared with the state-of-the-art approaches for CT tumor segmentation.

CONCLUSION

In order to overcome those key challenges arising from CT datasets and solve some of the main problems existing in the current deep learning-based methods, we propose a novel unified CTumorGAN framework, which can be effectively generalized to address any kinds of tumor datasets with superior performance.

Automated CT registration tool improves sensitivity to change in ventricular volume in patients with shunts and drains

OBJECTIVE

CT is the mainstay imaging modality for assessing change in ventricular volume in patients with ventricular shunts or external ventricular drains (EVDs). We evaluated the performance of a novel fully automated CT registration and subtraction method to improve reader accuracy and confidence compared with standard CT.

METHODS

In a retrospective evaluation of 49 ventricular shunt or EVD patients who underwent sequential head CT scans with an automated CT registration tool (CT CoPilot), three readers were assessed on their ability to discern change in ventricular volume between scans using standard axial CT images versus reformats and subtraction images generated by the registration tool. The inter-rater reliability among the readers was calculated using an intraclass correlation coefficient (ICC). Bland-Altman tests were performed to determine reader performance compared to semi-quantitative assessment using the bifrontal horn and third ventricular width. McNemar's test was used to determine whether the use of the registration tool increased the reader's level of confidence.

RESULTS

Inter-rater reliability was higher when using the output of the registration tool (single measure ICC of 0.909 with versus 0.755 without the tool). Agreement between the readers' assessment of ventricular volume change and the semi-quantitative assessment improved with the registration tool (limits of agreement 4.1 vs 4.3). Furthermore, the tool improved reader confidence in determining increased or decreased ventricular volume (p < 0.001).

CONCLUSION

Automated CT registration and subtraction improves the reader's ability to detect change in ventricular volume between sequential scans in patients with ventricular shunts or EVDs.

ADVANCES IN KNOWLEDGE

Our automated CT registration and subtraction method may serve as a promising generalizable tool for accurate assessment of change in ventricular volume, which can significantly affect clinical management.

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Medical image segmentation is an important step in medical image analysis. With the rapid development of a convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc segmentation, blood vessel detection, lung segmentation, cell segmentation, and so on. Previously, U-net based approaches have been proposed. However, the consecutive pooling and strided convolutional operations led to the loss of some spatial information. In this paper, we propose a context encoder network (CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation. CE-Net mainly contains three major components: a feature encoder module, a context extractor, and a feature decoder module. We use the pretrained ResNet block as the fixed feature extractor. The context extractor module is formed by a newly proposed dense atrous convolution block and a residual multi-kernel pooling block. We applied the proposed CE-Net to different 2D medical image segmentation tasks. Comprehensive results show that the proposed method outperforms the original U-Net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation, cell contour segmentation, and retinal optical coherence tomography layer segmentation.

Automatic Midline Shift Detection in Traumatic Brain Injury

Fast and accurate midline shift (MLS) estimation has a significant impact on diagnosis and treatment of patients with Traumatic Brain Injury (TBI). In this paper, we propose an automated method to calculate the amount of shift in the midline structure of TBI patients. The MLS values were annotated by a neuroradiologist. We first select a number of slices among all the slices in a CT scan based on metadata as well as information extracted from the images. After the slice selection, we propose an efficient segmentation technique to detect the ventricles. We use the ventricular geometric patterns to calculate the actual midline and also anatomical information to detect the ideal midline. The distance between these two lines is used as an estimate of MLS. The proposed methods are applied on a TBI dataset where they show a significant improvement of the the proposed method upon existing approach.

Brain Midline Shift Measurement and Its Automation: A Review of Techniques and Algorithms

Midline shift (MLS) of the brain is an important feature that can be measured using various imaging modalities including X-ray, ultrasound, computed tomography, and magnetic resonance imaging. Shift of midline intracranial structures helps diagnosing intracranial lesions, especially traumatic brain injury, stroke, brain tumor, and abscess. Being a sign of increased intracranial pressure, MLS is also an indicator of reduced brain perfusion caused by an intracranial mass or mass effect. We review studies that used the MLS to predict outcomes of patients with intracranial mass. In some studies, the MLS was also correlated to clinical features. Automated MLS measurement algorithms have significant potentials for assisting human experts in evaluating brain images. In symmetry-based algorithms, the deformed midline is detected and its distance from the ideal midline taken as the MLS. In landmark-based ones, MLS was measured following identification of specific anatomical landmarks. To validate these algorithms, measurements using these algorithms were compared to MLS measurements made by human experts. In addition to measuring the MLS on a given imaging study, there were newer applications of MLS that included comparing multiple MLS measurement before and after treatment and developing additional features to indicate mass effect. Suggestions for future research are provided.

Falx Cerebri Segmentation via Multi-atlas Boundary Fusion

The falx cerebri is a meningeal projection of dura in the brain, separating the cerebral hemispheres. It has stiffer mechanical properties than surrounding tissue and must be accurately segmented for building computational models of traumatic brain injury. In this work, we propose a method to segment the falx using T1-weighted magnetic resonance images (MRI) and susceptibility-weighted MRI (SWI). Multi-atlas whole brain segmentation is performed using the T1-weighted MRI and the gray matter cerebrum labels are extended into the longitudinal fissure using fast marching to find an initial estimate of the falx. To correct the falx boundaries, we register and then deform a set of SWI with manually delineated falx boundaries into the subject space. The continuous-STAPLE algorithm fuses sets of corresponding points to produce an estimate of the corrected falx boundary. Correspondence between points on the deformed falx boundaries is obtained using coherent point drift. We compare our method to manual ground truth, a multi-atlas approach without correction, and single-atlas approaches.

Objective Ventricle Segmentation in Brain CT with Ischemic Stroke Based on Anatomical Knowledge

Ventricle segmentation is a challenging technique for the development of detection system of ischemic stroke in computed tomography (CT), as ischemic stroke regions are adjacent to the brain ventricle with similar intensity. To address this problem, we developed an objective segmentation system of brain ventricle in CT. The intensity distribution of the ventricle was estimated based on clustering technique, connectivity, and domain knowledge, and the initial ventricle segmentation results were then obtained. To exclude the stroke regions from initial segmentation, a combined segmentation strategy was proposed, which is composed of three different schemes: (1) the largest three-dimensional (3D) connected component was considered as the ventricular region; (2) the big stroke areas were removed by the image difference methods based on searching optimal threshold values; (3) the small stroke regions were excluded by the adaptive template algorithm. The proposed method was evaluated on 50 cases of patients with ischemic stroke. The mean Dice, sensitivity, specificity, and root mean squared error were 0.9447, 0.969, 0.998, and 0.219 mm, respectively. This system can offer a desirable performance. Therefore, the proposed system is expected to bring insights into clinic research and the development of detection system of ischemic stroke in CT.

Quantitative estimation of a ratio of intracranial cerebrospinal fluid volume to brain volume based on segmentation of CT images in patients with extra-axial hematoma

Background Diminishing volume of intracranial cerebrospinal fluid (CSF) in patients with space-occupying masses have been attributed to unfavorable outcome associated with reduction of cerebral perfusion pressure and subsequent brain ischemia. Objective The objective of this article is to employ a ratio of CSF volume to brain volume for longitudinal assessment of space-volume relationships in patients with extra-axial hematoma and to determine variability of the ratio among patients with different types and stages of hematoma. Patients and methods In our retrospective study, we reviewed 113 patients with surgical extra-axial hematomas. We included 28 patients (age 61.7 +/- 17.7 years; 19 males, nine females) with an acute epidural hematoma (EDH) ( n = 5) and subacute/chronic subdural hematoma (SDH) ( n = 23). We excluded 85 patients, in order, due to acute SDH ( n = 76), concurrent intraparenchymal pathology ( n = 6), and bilateral pathology ( n = 3). Noncontrast CT images of the head were obtained using a CT scanner (2004 GE LightSpeed VCT CT system, tube voltage 140 kVp, tube current 310 mA, 5 mm section thickness) preoperatively, postoperatively (3.8 ± 5.8 hours from surgery), and at follow-up clinic visit (48.2 ± 27.7 days after surgery). Each CT scan was loaded into an OsiriX (Pixmeo, Switzerland) workstation to segment pixels based on radiodensity properties measured in Hounsfield units (HU). Based on HU values from -30 to 100, brain, CSF spaces, vascular structures, hematoma, and/or postsurgical fluid were segregated from bony structures, and subsequently hematoma and/or postsurgical fluid were manually selected and removed from the images. The remaining images represented overall brain volume-containing only CSF spaces, vascular structures, and brain parenchyma. Thereafter, the ratio between the total number of voxels representing CSF volume (based on values between 0 and 15 HU) to the total number of voxels representing overall brain volume was calculated. Results CSF/brain volume ratio varied significantly during the course of the disease, being the lowest preoperatively, 0.051 ± 0.032; higher after surgical evacuation of hematoma, 0.067 ± 0.040; and highest at follow-up visit, 0.083 ± 0.040 ( p < 0.01). Using a repeated regression analysis, we found a significant association ( p < 0.01) of the ratio with age (odds ratio, 1.019; 95% CI, 1.009-1.029) and type of hematoma (odds ratio, 0.405; 95% CI, 0.303-0.540). Conclusion CSF/brain volume ratio calculated from CT images has potential to reflect dynamics of intracranial volume changes in patients with space-occupying mass.

Automatic brain matter segmentation of computed tomography images using a statistical model: A tool to gain working time!

Brain computed tomography (CT) is useful diagnostic tool for the evaluation of several neurological disorders due to its accuracy, reliability, safety and wide availability. In this field, a potentially interesting research topic is the automatic segmentation and recognition of medical regions of interest (ROIs). Herein, we propose a novel automated method, based on the use of the active appearance model (AAM) for the segmentation of brain matter in CT images to assist radiologists in the evaluation of the images. The method described, that was applied to 54 CT images coming from a sample of outpatients affected by cognitive impairment, enabled us to obtain the generation of a model overlapping with the original image with quite good precision. Since CT neuroimaging is in widespread use for detecting neurological disease, including neurodegenerative conditions, the development of automated tools enabling technicians and physicians to reduce working time and reach a more accurate diagnosis is needed.

CT image segmentation in traumatic brain injury

Traumatic brain injury (TBI) is a major cause of disability and death. Speed and accuracy are vital in diagnosing TBI for which computer-aided imaging analysis may speedup and improve the efficiency of diagnosis and help reduce mortality, long-term complications, and the associated costs. However, developing such a system is challenging due to some factors such as the inherent noise associated with obtaining the images, artifacts and quality of the images. An automated system that can preliminary identify, localize and quantify the imaging features of TBI would be beneficial in guiding real-time clinical diagnosis as well as for quality assurance. In this paper we propose an automated system to segment the hematoma region from CT images. The proposed method first performs denoising and image enhancement and then by developing a Gaussian mixture model, segmentation is carried out. We show the performance of the system by comparing the results with ground truth generated by specialists.

An active contour model for medical image segmentation with application to brain CT image

PURPOSE

Cerebrospinal fluid (CSF) segmentation in computed tomography (CT) is a key step in computer-aided detection (CAD) of acute ischemic stroke. Because of image noise, low contrast and intensity inhomogeneity, CSF segmentation has been a challenging task. A region-based active contour model, which is insensitive to contour initialization and robust to intensity inhomogeneity, was developed for segmenting CSF in brain CT images.

METHODS

The energy function of the region-based active contour model is composed of a range domain kernel function, a space domain kernel function, and an edge indicator function. By minimizing the energy function, the region of edge elements of the target could be automatically identified in images with less dependence on initial contours. The energy function was optimized by means of the deepest descent method with a level set framework. An overlap rate between segmentation results and the reference standard was used to assess the segmentation accuracy. The authors evaluated the performance of the proposed method on both synthetic data and real brain CT images. They also compared the performance level of our method to those of region-scalable fitting (RSF) and global convex segment (GCS) models.

RESULTS

For the experiment of CSF segmentation in 67 brain CT images, their method achieved an average overlap rate of 66% compared to the average overlap rates of 16% and 46% from the RSF model and the GCS model, respectively.

CONCLUSIONS

Their region-based active contour model has the ability to achieve accurate segmentation results in images with high noise level and intensity inhomogeneity. Therefore, their method has great potential in the segmentation of medical images and would be useful for developing CAD schemes for acute ischemic stroke in brain CT images.

Automated midline shift and intracranial pressure estimation based on brain CT images

In this paper we present an automated system based mainly on the computed tomography (CT) images consisting of two main components: the midline shift estimation and intracranial pressure (ICP) pre-screening system. To estimate the midline shift, first an estimation of the ideal midline is performed based on the symmetry of the skull and anatomical features in the brain CT scan. Then, segmentation of the ventricles from the CT scan is performed and used as a guide for the identification of the actual midline through shape matching. These processes mimic the measuring process by physicians and have shown promising results in the evaluation. In the second component, more features are extracted related to ICP, such as the texture information, blood amount from CT scans and other recorded features, such as age, injury severity score to estimate the ICP are also incorporated. Machine learning techniques including feature selection and classification, such as Support Vector Machines (SVMs), are employed to build the prediction model using RapidMiner. The evaluation of the prediction shows potential usefulness of the model. The estimated ideal midline shift and predicted ICP levels may be used as a fast pre-screening step for physicians to make decisions, so as to recommend for or against invasive ICP monitoring.

Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique

PURPOSE

An automatic, accurate and fast segmentation of hemorrhage in brain Computed Tomography (CT) images is necessary for quantification and treatment planning when assessing a large number of data sets. Though manual segmentation is accurate, it is time consuming and tedious. Semi-automatic methods need user interactions and might introduce variability in results. Our study proposes a modified distance regularized level set evolution (MDRLSE) algorithm for hemorrhage segmentation.

METHODS

Study data set (from the ongoing CLEAR-IVH phase III clinical trial) is comprised of 200 sequential CT scans of 40 patients collected at 10 different hospitals using different machines/vendors. Data set contained both constant and variable slice thickness scans. Our study included pre-processing (filtering and skull removal), segmentation (MDRLSE which is a two-stage method with shrinking and expansion) with modified parameters for faster convergence and higher accuracy and post-processing (reduction in false positives and false negatives).

RESULTS

Results are validated against the gold standard marked manually by a trained CT reader and neurologist. Data sets are grouped as small, medium and large based on the volume of blood. Statistical analysis is performed for both training and test data sets in each group. The median Dice statistical indices (DSI) for the 3 groups are 0.8971, 0.8580 and 0.9173 respectively. Pre- and post-processing enhanced the DSI by 8 and 4% respectively.

CONCLUSIONS

The MDRLSE improved the accuracy and speed for segmentation and calculation of the hemorrhage volume compared to the original DRLSE method. The method generates quantitative information, which is useful for specific decision making and reduces the time needed for the clinicians to localize and segment the hemorrhagic regions.

An automated method for analysis of microcirculation videos for accurate assessment of tissue perfusion

Background

Imaging of the human microcirculation in real-time has the potential to detect injuries and illnesses that disturb the microcirculation at earlier stages and may improve the efficacy of resuscitation. Despite advanced imaging techniques to monitor the microcirculation, there are currently no tools for the near real-time analysis of the videos produced by these imaging systems. An automated system tool that can extract microvasculature information and monitor changes in tissue perfusion quantitatively might be invaluable as a diagnostic and therapeutic endpoint for resuscitation.

Methods

The experimental algorithm automatically extracts microvascular network and quantitatively measures changes in the microcirculation. There are two main parts in the algorithm: video processing and vessel segmentation. Microcirculatory videos are first stabilized in a video processing step to remove motion artifacts. In the vessel segmentation process, the microvascular network is extracted using multiple level thresholding and pixel verification techniques. Threshold levels are selected using histogram information of a set of training video recordings. Pixel-by-pixel differences are calculated throughout the frames to identify active blood vessels and capillaries with flow.

Results

Sublingual microcirculatory videos are recorded from anesthetized swine at baseline and during hemorrhage using a hand-held Side-stream Dark Field (SDF) imaging device to track changes in the microvasculature during hemorrhage. Automatically segmented vessels in the recordings are analyzed visually and the functional capillary density (FCD) values calculated by the algorithm are compared for both health baseline and hemorrhagic conditions. These results were compared to independently made FCD measurements using a well-known semi-automated method. Results of the fully automated algorithm demonstrated a significant decrease of FCD values. Similar, but more variable FCD values were calculated using a commercially available software program requiring manual editing.

Conclusions

An entirely automated system for analyzing microcirculation videos to reduce human interaction and computation time is developed. The algorithm successfully stabilizes video recordings, segments blood vessels, identifies vessels without flow and calculates FCD in a fully automated process. The automated process provides an equal or better separation between healthy and hemorrhagic FCD values compared to currently available semi-automatic techniques. The proposed method shows promise for the quantitative measurement of changes occurring in microcirculation during injury.

Automatic segmentation of ventricular cerebrospinal fluid from ischemic stroke CT images

Accurate segmentation of ventricular cerebrospinal fluid (CSF) regions in stroke CT images is important in assessing stroke patients. Manual segmentation is subjective, time consuming and error prone. There are currently no methods dedicated to extracting ventricular CSF regions in stroke CT images. 102 ischemic stroke CT scans (slice thickness between 3 and 6 mm, voxel size in the axial plane between 0.390 and 0.498 mm) were acquired. An automated template-based algorithm is proposed to extract ventricular CSF regions which accounts for the presence of ischemic infarct regions, image noise, and variations in orientation. First, template VT(2) is registered to the scan using landmark-based piecewise linear scaling and then template VT(1) is used to further refine the registration by partial segmentation of the fourth ventricle. A region of interest (ROI) is found using the registered VT(2). Automated thresholding is then applied to the ROI and the artifacts are removed in the final phase. Sensitivity, dice similarity coefficient, volume error, conformity and sensibility of segmentation results were 0.74 ± 0.12, 0.8 ± 0.09, 0.16 ± 0.11, 0.45 ± 0.39, 0.88 ± 0.09, respectively. The processing time for a 512 × 512 × 30 CT scan takes less than 30 s on a 2.49 GHz dual core processor PC with 4 GB RAM. Experiments with clinical stroke CT scans showed that the proposed algorithm can generate acceptable results in the presence of noise, size variations and orientation differences of ventricular systems and in the presence of ischemic infarcts.

A Brain Parenchyma Model-Based Segmentation of Intraventricular and Intracerebral Haemorrhage in CT Scans

Accurate quantification of haemorrhage volume in a computed tomography (CT) scan is critical in the management and treatment planning of intraventricular (IVH) and intracerebral haemorrhage (ICH). Manual and semi-automatic methods are laborious and time-consuming limiting their applicability to small data sets. In clinical trials measurements are done at different locations and on a large number of data; an accurate, consistent and automatic method is preferred. A fast and efficient method based on texture energy for identification and segmentation of hemorrhagic regions in the CT scans is proposed. The data set for the study was obtained from CLEAR-IVH clinical trial phase III (41 patients’ 201 sequential CT scans from ten different hospitals, slice thickness 2.5–10 mm and from different scanners). The DICOM data were windowed, skull stripped, convolved with textural energy masks and segmented using a hybrid method (a combination of thresholding and fuzzy c-means). Artifacts were removed by statistical analysis and morphological processing. Segmentation results were compared with the ground truth. Descriptive statistics, Dice statistical index (DSI), Bland-Altman and mean difference analysis were carried out. The median sensitivity, specificity and DSI for slice identification and haemorrhage segmentation were 86.25%, 100%, 0.9254 and 84.90%, 99.94%, 0.8710, respectively. The algorithm takes about one minute to process a scan in MATLAB®. A hybrid method-based volumetry of haemorrhage in CT is reliable, observer independent, efficient, reduces the time and labour. It also generates quantitative data that is important for precise therapeutic decision-making.