State of the art survey on MRI brain tumor segmentation

Supervised learning based multimodal MRI brain tumour segmentation using texture features from supervoxels

BACKGROUND

Accurate segmentation of brain tumour in magnetic resonance images (MRI) is a difficult task due to various tumour types. Using information and features from multimodal MRI including structural MRI and isotropic (p) and anisotropic (q) components derived from the diffusion tensor imaging (DTI) may result in a more accurate analysis of brain images.

METHODS

We propose a novel 3D supervoxel based learning method for segmentation of tumour in multimodal MRI brain images (conventional MRI and DTI). Supervoxels are generated using the information across the multimodal MRI dataset. For each supervoxel, a variety of features including histograms of texton descriptor, calculated using a set of Gabor filters with different sizes and orientations, and first order intensity statistical features are extracted. Those features are fed into a random forests (RF) classifier to classify each supervoxel into tumour core, oedema or healthy brain tissue.

RESULTS

The method is evaluated on two datasets: 1) Our clinical dataset: 11 multimodal images of patients and 2) BRATS 2013 clinical dataset: 30 multimodal images. For our clinical dataset, the average detection sensitivity of tumour (including tumour core and oedema) using multimodal MRI is 86% with balanced error rate (BER) 7%; while the Dice score for automatic tumour segmentation against ground truth is 0.84. The corresponding results of the BRATS 2013 dataset are 96%, 2% and 0.89, respectively.

CONCLUSION

The method demonstrates promising results in the segmentation of brain tumour. Adding features from multimodal MRI images can largely increase the segmentation accuracy. The method provides a close match to expert delineation across all tumour grades, leading to a faster and more reproducible method of brain tumour detection and delineation to aid patient management.

Learning-based stochastic object models for characterizing anatomical variations

It is widely known that the optimization of imaging systems based on objective, task-based measures of image quality via computer-simulation requires the use of a stochastic object model (SOM). However, the development of computationally tractable SOMs that can accurately model the statistical variations in human anatomy within a specified ensemble of patients remains a challenging task. Previously reported numerical anatomic models lack the ability to accurately model inter-patient and inter-organ variations in human anatomy among a broad patient population, mainly because they are established on image data corresponding to a few of patients and individual anatomic organs. This may introduce phantom-specific bias into computer-simulation studies, where the study result is heavily dependent on which phantom is used. In certain applications, however, databases of high-quality volumetric images and organ contours are available that can facilitate this SOM development. In this work, a novel and tractable methodology for learning a SOM and generating numerical phantoms from a set of volumetric training images is developed. The proposed methodology learns geometric attribute distributions (GAD) of human anatomic organs from a broad patient population, which characterize both centroid relationships between neighboring organs and anatomic shape similarity of individual organs among patients. By randomly sampling the learned centroid and shape GADs with the constraints of the respective principal attribute variations learned from the training data, an ensemble of stochastic objects can be created. The randomness in organ shape and position reflects the learned variability of human anatomy. To demonstrate the methodology, a SOM of an adult male pelvis is computed and examples of corresponding numerical phantoms are created.

Quantitative image analysis for evaluation of tumor response in clinical oncology

The objective, accurate, and standardized evaluation of tumor response to treatment is an indispensable procedure in clinical oncology. Compared to manual measurement, computer-assisted linear measurement can significantly improve the accuracy and reproducibility of tumor burden quantification. For irregular-shaped and infiltrating or diffuse tumors, which are difficult to quantify by linear measurement, computer-assisted volumetric measurement may provide a more objective and sensitive quantification to evaluate tumor response to treatment than linear measurement does. In the evaluation of tumor response to novel oncologic treatments such as targeted therapy, changes in overall tumor size do not necessarily reflect tumor response to therapy due to the presence of internal necrosis or hemorrhages. This leads to a new generation of imaging biomarkers to evaluate tumor response by using texture analysis methods, also called radiomics. Computer-assisted texture analysis technology offers a more comprehensive and in-depth imaging biomarker to evaluate tumor response. The application of computer-assisted quantitative imaging analysis techniques not only reduces the inaccuracy and improves the reliability in tumor burden quantification, but facilitates the development of more comprehensive and intelligent approaches to evaluate treatment response, and hence promotes precision imaging in the evaluation of tumor response in clinical oncology. This article summarizes the state-of-the-art technical developments and clinical applications of quantitative imaging analysis in evaluation of tumor response in clinical oncology.

Mathematical model of perineural tumor spread: a pilot study

BACKGROUND

Perineural spread (PNS) of pelvic cancer along the lumbosacral plexus is an emerging explanation for neoplastic lumbosacral plexopathy (nLSP) and an underestimated source of patient morbidity and mortality. Despite the increased incidence of PNS, these patients are often times a clinical conundrum-to diagnose and to treat. Building on previous results in modeling glioblastoma multiforme (GBM), we present a mathematical model for predicting the course and extent of the PNS of recurrent tumors.

METHODS

We created three-dimensional models of perineurally spreading tumor along the lumbosacral plexus from consecutive magnetic resonance imaging scans of two patients (one each with prostate cancer and cervical cancer). We adapted and applied a previously reported mathematical model of GBM to progression of tumor growth along the nerves on an anatomical model obtained from a healthy subject.

RESULTS

We were able to successfully model and visualize perineurally spreading pelvic cancer in two patients; average growth rates were 60.7 mm/year for subject 1 and 129 mm/year for subject 2. The model correlated well with extent of PNS on MRI scans at given time points.

CONCLUSIONS

This is the first attempt to model perineural tumor spread and we believe that it provides a glimpse into the future of disease progression monitoring. Every tumor and every patient are different, and the possibility to report treatment response using a unified scale-as "days gained"-will be a necessity in the era of individualized medicine. We hope our work will serve as a springboard for future connections between mathematics and medicine.

Deep learning for segmentation of brain tumors: Impact of cross-institutional training and testing

BACKGROUND AND PURPOSE

Convolutional neural networks (CNNs) are commonly used for segmentation of brain tumors. In this work, we assess the effect of cross-institutional training on the performance of CNNs.

METHODS

We selected 44 glioblastoma (GBM) patients from two institutions in The Cancer Imaging Archive dataset. The images were manually annotated by outlining each tumor component to form ground truth. To automatically segment the tumors in each patient, we trained three CNNs: (a) one using data for patients from the same institution as the test data, (b) one using data for the patients from the other institution and (c) one using data for the patients from both of the institutions. The performance of the trained models was evaluated using Dice similarity coefficients as well as Average Hausdorff Distance between the ground truth and automatic segmentations. The 10-fold cross-validation scheme was used to compare the performance of different approaches.

RESULTS

Performance of the model significantly decreased (P < 0.0001) when it was trained on data from a different institution (dice coefficients: 0.68 ± 0.19 and 0.59 ± 0.19) as compared to training with data from the same institution (dice coefficients: 0.72 ± 0.17 and 0.76 ± 0.12). This trend persisted for segmentation of the entire tumor as well as its individual components.

CONCLUSIONS

There is a very strong effect of selecting data for training on performance of CNNs in a multi-institutional setting. Determination of the reasons behind this effect requires additional comprehensive investigation.

Computational methods for corpus callosum segmentation on MRI: A systematic literature review

BACKGROUND AND OBJECTIVE

The corpus callosum (CC) is the largest white matter structure in the brain and has a significant role in central nervous system diseases. Its volume correlates with the severity and/or extent of neurodegenerative disease. Even though the CC's role has been extensively studied over the last decades, and different algorithms and methods have been published regarding CC segmentation and parcellation, no reviews or surveys covering such developments have been reported so far. To bridge this gap, this paper presents a systematic literature review of computational methods focusing on CC segmentation and parcellation acquired on magnetic resonance imaging.

METHODS

IEEExplore, PubMed, EBSCO Host, and Scopus database were searched with the following search terms: ((Segmentation OR Parcellation) AND (Corpus Callosum) AND (DTI OR MRI OR Diffusion Tensor Imag* OR Diffusion Tractography OR Magnetic Resonance Imag*)), resulting in 802 publications. Two reviewers independently evaluated all articles and 36 studies were selected through the systematic literature review process.

RESULTS

This work reviewed four main segmentation methods groups: model-based, region-based, thresholding, and machine learning; 32 different validity metrics were reported. Even though model-based techniques are the most recurrently used for the segmentation task (13 articles), machine learning approaches achieved better outcomes of 95% when analyzing mean values for segmentation and classification metrics results. Moreover, CC segmentation is better established in T₁-weighted images, having more methods implemented and also being tested in larger datasets, compared with diffusion tensor images.

CONCLUSIONS

The analyzed computational methods used to perform CC segmentation on magnetic resonance imaging have not yet overcome all presented challenges owing to metrics variability and lack of traceable materials.

A novel fully automatic multilevel thresholding technique based on optimized intuitionistic fuzzy sets and tsallis entropy for MR brain tumor image segmentation

In the present paper, a hybrid multilevel thresholding technique that combines intuitionistic fuzzy sets and tsallis entropy has been proposed for the automatic delineation of the tumor from magnetic resonance images having vague boundaries and poor contrast. This novel technique takes into account both the image histogram and the uncertainty information for the computation of multiple thresholds. The benefit of the methodology is that it provides fast and improved segmentation for the complex tumorous images with imprecise gray levels. To further boost the computational speed, the mutation based particle swarm optimization is used that selects the most optimal threshold combination. The accuracy of the proposed segmentation approach has been validated on simulated, real low-grade glioma tumor volumes taken from MICCAI brain tumor segmentation (BRATS) challenge 2012 dataset and the clinical tumor images, so as to corroborate its generality and novelty. The designed technique achieves an average Dice overlap equal to 0.82010, 0.78610 and 0.94170 for three datasets. Further, a comparative analysis has also been made between the eight existing multilevel thresholding implementations so as to show the superiority of the designed technique. In comparison, the results indicate a mean improvement in Dice by an amount equal to 4.00% (p < 0.005), 9.60% (p < 0.005) and 3.58% (p < 0.005), respectively in contrast to the fuzzy tsallis approach.

Population Pharmacokinetics of Tracers: A New Tool for Medical Imaging?

Positron emission tomography-computed tomography is a medical imaging method measuring the activity of a radiotracer chosen to accumulate in cancer cells. A recent trend of medical imaging analysis is to account for the radiotracer's pharmacokinetic properties at a voxel (three-dimensional-pixel) level to separate the different tissues. These analyses are closely linked to population pharmacokinetic-pharmacodynamic modelling. Kineticists possess the cultural background to improve medical imaging analysis. This article stresses the common points with population pharmacokinetics and highlights the methodological locks that need to be lifted.

Brain MR image segmentation using NAMS in pseudo-color

Image segmentation plays a crucial role in various biomedical applications. In general, the segmentation of brain Magnetic Resonance (MR) images is mainly used to represent the image with several homogeneous regions instead of pixels for surgical analyzing and planning. This paper proposes a new approach for segmenting MR brain images by using pseudo-color based segmentation with Non-symmetry and Anti-packing Model with Squares (NAMS). First of all, the NAMS model is presented. The model can represent the image with sub-patterns to keep the image content and largely reduce the data redundancy. Second, the key idea is proposed that convert the original gray-scale brain MR image into a pseudo-colored image and then segment the pseudo-colored image with NAMS model. The pseudo-colored image can enhance the color contrast in different tissues in brain MR images, which can improve the precision of segmentation as well as directly visual perceptional distinction. Experimental results indicate that compared with other brain MR image segmentation methods, the proposed NAMS based pseudo-color segmentation method performs more excellent in not only segmenting precisely but also saving storage.

A segmentation of brain MRI images utilizing intensity and contextual information by Markov random field

BACKGROUND AND OBJECTIVE

Image segmentation is a preliminary and fundamental step in computer aided magnetic resonance imaging (MRI) images analysis. But the performance of most current image segmentation methods is easily depreciated by noise in MRI images. A precise and anti-noise segmentation of MRI images is desired in modern medical image diagnosis.

METHODS

This paper presents a segmentation of MRI images which combines fuzzy clustering and Markov random field (MRF). In order to utilize gray level information sufficiently and alleviate noise disturbance, fuzzy clustering is carried out on the original image and the coarse scale image of multi-scale decomposition. The spatial constraints between neighboring pixels are modeled by a defined potential function in the MRF to reduce the effect of noise and increase the integrity of segmented regions. Spatial constraints and the gray level information refined by Fuzzy C-Means (FCM) algorithm are integrated by maximum a posteriori Markov random field (MAP-MRF). In the proposed method, the fuzzy clustering membership obtained from the original image and the coarse scale image is integrated into the single-site clique potential functions by MAP-MRF. The defined potential functions and the distance weight are introduced to model the neighborhood constraint with MRF.

RESULTS

The experiments are carried out on noised synthetic images, simulated brain MR images and real MR images. The experimental results show that the proposed method has strong robustness and satisfying performance. Meanwhile the method is compared with FCM, FGFCM and FLICM algorithms visually and statistically in the experiments. In the comparison, the proposed method has achieved the best results. In the statistical comparison, the proposed method has an average similarity index of 36.8%, 33.7%, 2.75% increase against FCM, FGFCM and FLICM.

CONCLUSIONS

This paper proposes a MRI segmentation method combining fuzzy clustering and Markov random field. The method is tested in the noised image databases and comparison experiments, which shows that it is a precise and robust MRI segmentation method.

Computer-based radiological longitudinal evaluation of meningiomas following stereotactic radiosurgery

PURPOSE

Stereotactic radiosurgery (SRS) is a common treatment for intracranial meningiomas. SRS is planned on a pre-therapy gadolinium-enhanced T1-weighted MRI scan (Gd-T1w MRI) in which the meningioma contours have been delineated. Post-SRS therapy serial Gd-T1w MRI scans are then acquired for longitudinal treatment evaluation. Accurate tumor volume change quantification is required for treatment efficacy evaluation and for treatment continuation.

METHOD

We present a new algorithm for the automatic segmentation and volumetric assessment of meningioma in post-therapy Gd-T1w MRI scans. The inputs are the pre- and post-therapy Gd-T1w MRI scans and the meningioma delineation in the pre-therapy scan. The output is the meningioma delineations and volumes in the post-therapy scan. The algorithm uses the pre-therapy scan and its meningioma delineation to initialize an extended Chan-Vese active contour method and as a strong patient-specific intensity and shape prior for the post-therapy scan meningioma segmentation. The algorithm is automatic, obviates the need for independent tumor localization and segmentation initialization, and incorporates the same tumor delineation criteria in both the pre- and post-therapy scans.

RESULTS

Our experimental results on retrospective pre- and post-therapy scans with a total of 32 meningiomas with volume ranges 0.4-26.5 cm[Formula: see text] yield a Dice coefficient of [Formula: see text]% with respect to ground-truth delineations in post-therapy scans created by two clinicians. These results indicate a high correspondence to the ground-truth delineations.

CONCLUSION

Our algorithm yields more reliable and accurate tumor volume change measurements than other stand-alone segmentation methods. It may be a useful tool for quantitative meningioma prognosis evaluation after SRS.

A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery

Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases.

Semi-Automated Volumetric and Morphological Assessment of Glioblastoma Resection with Fluorescence-Guided Surgery

PURPOSE

Glioblastoma (GBM) neurosurgical resection relies on contrast-enhanced MRI-based neuronavigation. However, it is well-known that infiltrating tumor extends beyond contrast enhancement. Fluorescence-guided surgery (FGS) using 5-aminolevulinic acid (5-ALA) was evaluated to improve extent of resection (EOR) of GBMs. Preoperative morphological tumor metrics were also assessed.

PROCEDURES

Thirty patients from a phase II trial evaluating 5-ALA FGS in newly diagnosed GBM were assessed. Tumors were segmented preoperatively to assess morphological features as well as postoperatively to evaluate EOR and residual tumor volume (RTV).

RESULTS

Median EOR and RTV were 94.3 % and 0.821 cm(3), respectively. Preoperative surface area to volume ratio and RTV were significantly associated with overall survival, even when controlling for the known survival confounders.

CONCLUSIONS

This study supports claims that 5-ALA FGS is helpful at decreasing tumor burden and prolonging survival in GBM. Moreover, morphological indices are shown to impact both resection and patient survival.

Expertise Affects Inter-Observer Agreement at Peripheral Locations within a Brain Tumor

Magnetic resonance imaging (MRI) is a crucial tool for clinical brain tumor detection and delineation. Since the process of gross tumor volume delineation resides with clinicians, a better understanding of how they perform this task is required if improvements in life expectancy are to be made. Novice-expert comparison studies have been used to examine the effect of expertise on abnormality detection, but little research has investigated expertise-related differences in brain tumor delineation. In this study, undergraduate students (novices) and radiologists (experts) inspected a combination of T1 and T2 single and whole brain MRI scans, each containing a tumor. Using a tablet and stylus to provide an interactive environment, participants had an unlimited amount of time to scroll freely through the MRI slices and were instructed to delineate (i.e., draw a boundary) around any tumorous tissue. There was no reliable evidence for a difference in the gross tumor volume or total number of slices delineated between experts and novices. Agreement was low across both expertise groups and significantly lower at peripheral locations within a tumor than central locations. There was an interaction between expertise level and location within a tumor with experts displaying higher agreement at the peripheral slices than novices. An effect of brain image set on the order in which participants inspected the slices was also observed. The implications of these results for the training undertaken by early career radiologists and current practices in hospitals are discussed.

Reproducibility and relative stability in magnetic resonance imaging indices of tumor vascular physiology over a period of 24h in a rat 9L gliosarcoma model

PURPOSE

The objective was to study temporal changes in tumor vascular physiological indices in a period of 24h in a 9L gliosarcoma rat model.

METHODS

Fischer-344 rats (N=14) were orthotopically implanted with 9L cells. At 2weeks post-implantation, they were imaged twice in a 24h interval using dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). Data-driven model-selection-based analysis was used to segment tumor regions with varying vascular permeability characteristics. The region with the maximum number of estimable parameters of vascular kinetics was chosen for comparison across the two time points. It provided estimates of three parameters for an MR contrast agent (MRCA): i) plasma volume (v_p), ii) forward volumetric transfer constant (K^trans) and interstitial volume fraction (v_e, ratio of K^trans to reverse transfer constant, k_ep). In addition, MRCA extracellular distribution volume (V_D) was estimated in the tumor and its borders, along with tumor blood flow (TBF) and peritumoral MRCA flux. Descriptors of parametric distributions were compared between the two times. Tumor extent was examined by hematoxylin and eosin (H&E) staining. Picrosirus red staining of secreted collagen was performed as an additional index for 9L cells.

RESULTS

Test-retest differences between population summaries for any parameter were not significant (paired t and Wilcoxon signed rank tests). Bland-Altman plots showed no apparent trends between the differences and averages of the test-retest measures for all indices. The intraclass correlation coefficients showed moderate to almost perfect reproducibility for all of the parameters, except v_p. H&E staining showed tumor infiltration in parenchyma, perivascular space and white matter tracts. Collagen staining was observed along the outer edges of main tumor mass.

CONCLUSION

The data suggest the relative stability of these MR indices of tumor microenvironment over a 24h duration in this gliosarcoma model.

Relationship between necrotic patterns in glioblastoma and patient survival: fractal dimension and lacunarity analyses using magnetic resonance imaging

Necrosis is a hallmark feature of glioblastoma (GBM). This study investigated the prognostic role of necrotic patterns in GBM using fractal dimension (FD) and lacunarity analyses of magnetic resonance imaging (MRI) data and evaluated the role of lacunarity in the biological processes leading to necrosis. We retrospectively reviewed clinical and MRI data of 95 patients with GBM. FD and lacunarity of the necrosis on MRI were calculated by fractal analysis and subjected to survival analysis. We also performed gene ontology analysis in 32 patients with available RNA-seq data. Univariate analysis revealed that FD < 1.56 and lacunarity > 0.46 significantly correlated with poor progression-free survival (p = 0.006 and p = 0.012, respectively) and overall survival (p = 0.008 and p = 0.005, respectively). Multivariate analysis revealed that both parameters were independent factors for unfavorable progression-free survival (p = 0.001 and p = 0.015, respectively) and overall survival (p = 0.002 and p = 0.007, respectively). Gene ontology analysis revealed that genes positively correlated with lacunarity were involved in the suppression of apoptosis and necrosis-associated biological processes. We demonstrate that the fractal parameters of necrosis in GBM can predict patient survival and are associated with the biological processes of tumor necrosis.

Semiautomatic Segmentation of Glioma on Mobile Devices

Brain tumor segmentation is the first and the most critical step in clinical applications of radiomics. However, segmenting brain images by radiologists is labor intense and prone to inter- and intraobserver variability. Stable and reproducible brain image segmentation algorithms are thus important for successful tumor detection in radiomics. In this paper, we propose a supervised brain image segmentation method, especially for magnetic resonance (MR) brain images with glioma. This paper uses hard edge multiplicative intrinsic component optimization to preprocess glioma medical image on the server side, and then, the doctors could supervise the segmentation process on mobile devices in their convenient time. Since the preprocessed images have the same brightness for the same tissue voxels, they have small data size (typically 1/10 of the original image size) and simple structure of 4 types of intensity value. This observation thus allows follow-up steps to be processed on mobile devices with low bandwidth and limited computing performance. Experiments conducted on 1935 brain slices from 129 patients show that more than 30% of the sample can reach 90% similarity; over 60% of the samples can reach 85% similarity, and more than 80% of the sample could reach 75% similarity. The comparisons with other segmentation methods also demonstrate both efficiency and stability of the proposed approach.

State-of-the-Art Methods for Brain Tissue Segmentation: A Review

Brain tissue segmentation is one of the most sought after research areas in medical image processing. It provides detailed quantitative brain analysis for accurate disease diagnosis, detection, and classification of abnormalities. It plays an essential role in discriminating healthy tissues from lesion tissues. Therefore, accurate disease diagnosis and treatment planning depend merely on the performance of the segmentation method used. In this review, we have studied the recent advances in brain tissue segmentation methods and their state-of-the-art in neuroscience research. The review also highlights the major challenges faced during tissue segmentation of the brain. An effective comparison is made among state-of-the-art brain tissue segmentation methods. Moreover, a study of some of the validation measures to evaluate different segmentation methods is also discussed. The brain tissue segmentation, content in terms of methodologies, and experiments presented in this review are encouraging enough to attract researchers working in this field.

Brain tumor classification and segmentation using sparse coding and dictionary learning

This paper presents a novel fully automatic framework for multi-class brain tumor classification and segmentation using a sparse coding and dictionary learning method. The proposed framework consists of two steps: classification and segmentation. The classification of the brain tumors is based on brain topology and texture. The segmentation is based on voxel values of the image data. Using K-SVD, two types of dictionaries are learned from the training data and their associated ground truth segmentation: feature dictionary and voxel-wise coupled dictionaries. The feature dictionary consists of global image features (topological and texture features). The coupled dictionaries consist of coupled information: gray scale voxel values of the training image data and their associated label voxel values of the ground truth segmentation of the training data. For quantitative evaluation, the proposed framework is evaluated using different metrics. The segmentation results of the brain tumor segmentation (MICCAI-BraTS-2013) database are evaluated using five different metric scores, which are computed using the online evaluation tool provided by the BraTS-2013 challenge organizers. Experimental results demonstrate that the proposed approach achieves an accurate brain tumor classification and segmentation and outperforms the state-of-the-art methods.

REtroSpective Evaluation of Cerebral Tumors (RESECT): A clinical database of pre-operative MRI and intra-operative ultrasound in low-grade glioma surgeries

PURPOSE

The advancement of medical image processing techniques, such as image registration, can effectively help improve the accuracy and efficiency of brain tumor surgeries. However, it is often challenging to validate these techniques with real clinical data due to the rarity of such publicly available repositories.

ACQUISITION AND VALIDATION METHODS

Pre-operative magnetic resonance images (MRI), and intra-operative ultrasound (US) scans were acquired from 23 patients with low-grade gliomas who underwent surgeries at St. Olavs University Hospital between 2011 and 2016. Each patient was scanned by Gadolinium-enhanced T1w and T2-FLAIR MRI protocols to reveal the anatomy and pathology, and series of B-mode ultrasound images were obtained before, during, and after tumor resection to track the surgical progress and tissue deformation. Retrospectively, corresponding anatomical landmarks were identified across US images of different surgical stages, and between MRI and US, and can be used to validate image registration algorithms. Quality of landmark identification was assessed with intra- and inter-rater variability.

DATA FORMAT AND ACCESS

In addition to co-registered MRIs, each series of US scans are provided as a reconstructed 3D volume. All images are accessible in MINC2 and NIFTI formats, and the anatomical landmarks were annotated in MNI tag files. Both the imaging data and the corresponding landmarks are available online as the RESECT database at https://archive.norstore.no (search for "RESECT").

POTENTIAL IMPACT

The proposed database provides real high-quality multi-modal clinical data to validate and compare image registration algorithms that can potentially benefit the accuracy and efficiency of brain tumor resection. Furthermore, the database can also be used to test other image processing methods and neuro-navigation software platforms.

Semi-automated brain tumor segmentation on multi-parametric MRI using regularized non-negative matrix factorization

Background

Segmentation of gliomas in multi-parametric (MP-)MR images is challenging due to their heterogeneous nature in terms of size, appearance and location. Manual tumor segmentation is a time-consuming task and clinical practice would benefit from (semi-) automated segmentation of the different tumor compartments.

Methods

We present a semi-automated framework for brain tumor segmentation based on non-negative matrix factorization (NMF) that does not require prior training of the method. L1-regularization is incorporated into the NMF objective function to promote spatial consistency and sparseness of the tissue abundance maps. The pathological sources are initialized through user-defined voxel selection. Knowledge about the spatial location of the selected voxels is combined with tissue adjacency constraints in a post-processing step to enhance segmentation quality. The method is applied to an MP-MRI dataset of 21 high-grade glioma patients, including conventional, perfusion-weighted and diffusion-weighted MRI. To assess the effect of using MP-MRI data and the L1-regularization term, analyses are also run using only conventional MRI and without L1-regularization. Robustness against user input variability is verified by considering the statistical distribution of the segmentation results when repeatedly analyzing each patient’s dataset with a different set of random seeding points.

Results

Using L1-regularized semi-automated NMF segmentation, mean Dice-scores of 65%, 74 and 80% are found for active tumor, the tumor core and the whole tumor region. Mean Hausdorff distances of 6.1 mm, 7.4 mm and 8.2 mm are found for active tumor, the tumor core and the whole tumor region. Lower Dice-scores and higher Hausdorff distances are found without L1-regularization and when only considering conventional MRI data.

Conclusions

Based on the mean Dice-scores and Hausdorff distances, segmentation results are competitive with state-of-the-art in literature. Robust results were found for most patients, although careful voxel selection is mandatory to avoid sub-optimal segmentation.

What are the true volumes of SEGA tumors? Reliability of planimetric and popular semi-automated image segmentation methods

OBJECTIVE

To evaluate the reliability of the standard planimetric methodology of volumetric analysis and three different open-source semi-automated approaches of brain tumor segmentation.

MATERIALS AND METHODS

The volumes of subependymal giant cell astrocytomas (SEGA) examined by 30 MRI studies of 10 patients from a previous everolimus-related trial (EMINENTS study) were estimated using four methods: planimetric method (modified MacDonald ellipsoid method), ITK-Snap (pixel clustering, geodesic active contours, region competition methods), 3D Slicer (level-set thresholding), and NIRFast (k-means clustering, Markov random fields). The methods were compared, and a trial simulation was performed to determine how the choice of approach could influence the final decision about progression or response.

RESULTS

Intraclass correlation coefficient was high (0.95; 95% CI 0.91-0.98). The planimetric method always overestimated the size of the tumor, while virtually no mean difference was found between ITK-Snap and 3D Slicer (P = 0.99). NIRFast underestimated the volume and presented a proportional bias. During the trial simulation, a moderate level of agreement between all the methods (kappa 0.57-0.71, P < 0.002) was noted.

CONCLUSION

Semi-automated segmentation can ease oncological follow-up but the moderate level of agreement between segmentation methods suggests that the reference standard volumetric method for SEGA tumors should be revised and chosen carefully, as the selection of volumetry tool may influence the conclusion about tumor progression or response.

The Brain Tumor Segmentation Using Fuzzy C-Means Technique

Image segmentation is a technique which divides an image into its constituent regions or objects. Segmentation continues till we reach our area of interest or the specified object of target. This field offers vast future scope and challenges for the researchers. This proposal uses the fuzzy c mean technique to segment the different MRI brain tumor images. This proposal also shows the comparative results of Thresholding, K-means clustering and Fuzzy c- means clustering. Dice coefficient and Jaccards measure is used for accuracy of the segmentation in this proposal. Experimental results demonstrate the performance of the designed method.

Image Analysis for MRI Based Brain Tumor Detection and Feature Extraction Using Biologically Inspired BWT and SVM

The segmentation, detection, and extraction of infected tumor area from magnetic resonance (MR) images are a primary concern but a tedious and time taking task performed by radiologists or clinical experts, and their accuracy depends on their experience only. So, the use of computer aided technology becomes very necessary to overcome these limitations. In this study, to improve the performance and reduce the complexity involves in the medical image segmentation process, we have investigated Berkeley wavelet transformation (BWT) based brain tumor segmentation. Furthermore, to improve the accuracy and quality rate of the support vector machine (SVM) based classifier, relevant features are extracted from each segmented tissue. The experimental results of proposed technique have been evaluated and validated for performance and quality analysis on magnetic resonance brain images, based on accuracy, sensitivity, specificity, and dice similarity index coefficient. The experimental results achieved 96.51% accuracy, 94.2% specificity, and 97.72% sensitivity, demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from brain MR images. The experimental results also obtained an average of 0.82 dice similarity index coefficient, which indicates better overlap between the automated (machines) extracted tumor region with manually extracted tumor region by radiologists. The simulation results prove the significance in terms of quality parameters and accuracy in comparison to state-of-the-art techniques.

Automatic MRI segmentation of para-pharyngeal fat pads using interactive visual feature space analysis for classification

Background

Obstructive sleep apnea (OSA) is a public health problem. Detailed analysis of the para-pharyngeal fat pads can help us to understand the pathogenesis of OSA and may mediate the intervention of this sleeping disorder. A reliable and automatic para-pharyngeal fat pads segmentation technique plays a vital role in investigating larger data bases to identify the anatomic risk factors for the OSA.

Methods

Our research aims to develop a context-based automatic segmentation algorithm to delineate the fat pads from magnetic resonance images in a population-based study. Our segmentation pipeline involves texture analysis, connected component analysis, object-based image analysis, and supervised classification using an interactive visual analysis tool to segregate fat pads from other structures automatically.

Results

We developed a fully automatic segmentation technique that does not need any user interaction to extract fat pads. Our algorithm is fast enough that we can apply it to population-based epidemiological studies that provide a large amount of data. We evaluated our approach qualitatively on thirty datasets and quantitatively against the ground truths of ten datasets resulting in an average of approximately 78% detected volume fraction and a 79% Dice coefficient, which is within the range of the inter-observer variation of manual segmentation results.

Conclusion

The suggested method produces sufficiently accurate results and has potential to be applied for the study of large data to understand the pathogenesis of the OSA syndrome.

Radiomic Phenotyping in Brain Cancer to Unravel Hidden Information in Medical Images

Radiomics is a new area of research in the field of imaging with tremendous potential to unravel the hidden information in digital images. The scope of radiology has grown exponentially over the last two decades; since the advent of radiomics, many quantitative imaging features can now be extracted from medical images through high-throughput computing, and these can be converted into mineable data that can help in linking imaging phenotypes with clinical data, genomics, proteomics, and other "omics" information. In cancer, radiomic imaging analysis aims at extracting imaging features embedded in the imaging data, which can act as a guide in the disease or cancer diagnosis, staging and planning interventions for treating patients, monitor patients on therapy, predict treatment response, and determine patient outcomes.

Fast and robust brain tumor segmentation using level set method with multiple image information

BACKGROUND

Brain tumor segmentation is a challenging task for its variation in intensity. The phenomenon is caused by the inhomogeneous content of tumor tissue and the choice of imaging modality. In 2010 Zhang developed the Selective Binary Gaussian Filtering Regularizing Level Set (SBGFRLS) model that combined the merits of edge-based and region-based segmentation.

OBJECTIVE

To improve the SBGFRLS method by modifying the singed pressure force (SPF) term with multiple image information and demonstrate effectiveness of proposed method on clinical images.

METHODS

In original SBGFRLS model, the contour evolution direction mainly depends on the SPF. By introducing a directional term in SPF, the metric could control the evolution direction. The SPF is altered by statistic values enclosed by the contour. This concept can be extended to jointly incorporate multiple image information. The new SPF term is expected to bring a solution for blur edge problem in brain tumor segmentation. The proposed method is validated with clinical images including pre- and post-contrast magnetic resonance images. The accuracy and robustness is compared with sensitivity, specificity, DICE similarity coefficient and Jaccard similarity index.

RESULTS

Experimental results show improvement, in particular the increase of sensitivity at the same specificity, in segmenting all types of tumors except for the diffused tumor.

CONCLUSION

The novel brain tumor segmentation method is clinical-oriented with fast, robust and accurate implementation and a minimal user interaction. The method effectively segmented homogeneously enhanced, non-enhanced, heterogeneously-enhanced, and ring-enhanced tumor under MR imaging. Though the method is limited by identifying edema and diffuse tumor, several possible solutions are suggested to turn the curve evolution into a fully functional clinical diagnosis tool.

Automatic metastatic brain tumor segmentation for stereotactic radiosurgery applications

The objective of this study is to develop an automatic segmentation strategy for efficient and accurate metastatic brain tumor delineation on contrast-enhanced T1-weighted (T1c) magnetic resonance images (MRI) for stereotactic radiosurgery (SRS) applications. The proposed four-step automatic brain metastases segmentation strategy is comprised of pre-processing, initial contouring, contour evolution, and contour triage. First, T1c brain images are preprocessed to remove the skull. Second, an initial tumor contour is created using a multi-scaled adaptive threshold-based bounding box and a super-voxel clustering technique. Third, the initial contours are evolved to the tumor boundary using a regional active contour technique. Fourth, all detected false-positive contours are removed with geometric characterization. The segmentation process was validated on a realistic virtual phantom containing Gaussian or Rician noise. For each type of noise distribution, five different noise levels were tested. Twenty-one cases from the multimodal brain tumor image segmentation (BRATS) challenge dataset and fifteen clinical metastases cases were also included in validation. Segmentation performance was quantified by the Dice coefficient (DC), normalized mutual information (NMI), structural similarity (SSIM), Hausdorff distance (HD), mean value of surface-to-surface distance (MSSD) and standard deviation of surface-to-surface distance (SDSSD). In the numerical phantom study, the evaluation yielded a DC of 0.98  ±  0.01, an NMI of 0.97  ±  0.01, an SSIM of 0.999  ±  0.001, an HD of 2.2  ±  0.8 mm, an MSSD of 0.1  ±  0.1 mm, and an SDSSD of 0.3  ±  0.1 mm. The validation on the BRATS data resulted in a DC of 0.89  ±  0.08, which outperform the BRATS challenge algorithms. Evaluation on clinical datasets gave a DC of 0.86  ±  0.09, an NMI of 0.80  ±  0.11, an SSIM of 0.999  ±  0.001, an HD of 8.8  ±  12.6 mm, an MSSD of 1.5  ±  3.2 mm, and an SDSSD of 1.8  ±  3.4 mm when comparing to the physician drawn ground truth. The result indicated that the developed automatic segmentation strategy yielded accurate brain tumor delineation and presented as a useful clinical tool for SRS applications.

Investigating intracranial tumour growth patterns with multiparametric MRI incorporating Gd-DTPA and USPIO-enhanced imaging

High grade and metastatic brain tumours exhibit considerable spatial variations in proliferation, angiogenesis, invasion, necrosis and oedema. Vascular heterogeneity arising from vascular co-option in regions of invasive growth (in which the blood-brain barrier remains intact) and neoangiogenesis is a major challenge faced in the assessment of brain tumours by conventional MRI. A multiparametric MRI approach, incorporating native measurements and both Gd-DTPA (Magnevist) and ultrasmall superparamagnetic iron oxide (P904)-enhanced imaging, was used in combination with histogram and unsupervised cluster analysis using a k-means algorithm to examine the spatial distribution of vascular parameters, water diffusion characteristics and invasion in intracranially propagated rat RG2 gliomas and human MDA-MB-231 LM2-4 breast adenocarcinomas in mice. Both tumour models presented with higher ΔR1 (the change in transverse relaxation rate R1 induced by Gd-DTPA), fractional blood volume (fBV) and apparent diffusion coefficient than uninvolved regions of the brain. MDA-MB-231 LM2-4 tumours were less densely cellular than RG2 tumours and exhibited substantial local invasion, associated with oedema, whereas invasion in RG2 tumours was minimal. These additional features were reflected in the more heterogeneous appearance of MDA-MB-231 LM2-4 tumours on T2 -weighted images and maps of functional MRI parameters. Unsupervised cluster analysis separated subregions with distinct functional properties; areas with a low fBV and relatively impermeable blood vessels (low ΔR1 ) were predominantly located at the tumour margins, regions of MDA-MB-231 LM2-4 tumours with relatively high levels of water diffusion and low vascular permeability and/or fBV corresponded to histologically identified regions of invasion and oedema, and areas of mismatch between vascular permeability and blood volume were identified. We demonstrate that dual contrast MRI and evaluation of tissue diffusion properties, coupled with cluster analysis, allows for the assessment of heterogeneity within invasive brain tumours and the designation of functionally diverse subregions that may provide more informative predictive biomarkers.

Cluster analysis of dynamic contrast enhanced MRI reveals tumor subregions related to locoregional relapse for cervical cancer patients

BACKGROUND

Solid tumors are known to be spatially heterogeneous. Detection of treatment-resistant tumor regions can improve clinical outcome, by enabling implementation of strategies targeting such regions. In this study, K-means clustering was used to group voxels in dynamic contrast enhanced magnetic resonance images (DCE-MRI) of cervical cancers. The aim was to identify clusters reflecting treatment resistance that could be used for targeted radiotherapy with a dose-painting approach.

MATERIAL AND METHODS

Eighty-one patients with locally advanced cervical cancer underwent DCE-MRI prior to chemoradiotherapy. The resulting image time series were fitted to two pharmacokinetic models, the Tofts model (yielding parameters K^trans and ν_e) and the Brix model (A_Brix, k_ep and k_el). K-means clustering was used to group similar voxels based on either the pharmacokinetic parameter maps or the relative signal increase (RSI) time series. The associations between voxel clusters and treatment outcome (measured as locoregional control) were evaluated using the volume fraction or the spatial distribution of each cluster.

RESULTS

One voxel cluster based on the RSI time series was significantly related to locoregional control (adjusted p-value 0.048). This cluster consisted of low-enhancing voxels. We found that tumors with poor prognosis had this RSI-based cluster gathered into few patches, making this cluster a potential candidate for targeted radiotherapy. None of the voxels clusters based on Tofts or Brix parameter maps were significantly related to treatment outcome.

CONCLUSION

We identified one group of tumor voxels significantly associated with locoregional relapse that could potentially be used for dose painting. This tumor voxel cluster was identified using the raw MRI time series rather than the pharmacokinetic maps.

Glioblastoma Segmentation: Comparison of Three Different Software Packages

To facilitate a more widespread use of volumetric tumor segmentation in clinical studies, there is an urgent need for reliable, user-friendly segmentation software. The aim of this study was therefore to compare three different software packages for semi-automatic brain tumor segmentation of glioblastoma; namely BrainVoyager^TM QX, ITK-Snap and 3D Slicer, and to make data available for future reference. Pre-operative, contrast enhanced T₁-weighted 1.5 or 3 Tesla Magnetic Resonance Imaging (MRI) scans were obtained in 20 consecutive patients who underwent surgery for glioblastoma. MRI scans were segmented twice in each software package by two investigators. Intra-rater, inter-rater and between-software agreement was compared by using differences of means with 95% limits of agreement (LoA), Dice’s similarity coefficients (DSC) and Hausdorff distance (HD). Time expenditure of segmentations was measured using a stopwatch. Eighteen tumors were included in the analyses. Inter-rater agreement was highest for BrainVoyager with difference of means of 0.19 mL and 95% LoA from -2.42 mL to 2.81 mL. Between-software agreement and 95% LoA were very similar for the different software packages. Intra-rater, inter-rater and between-software DSC were ≥ 0.93 in all analyses. Time expenditure was approximately 41 min per segmentation in BrainVoyager, and 18 min per segmentation in both 3D Slicer and ITK-Snap. Our main findings were that there is a high agreement within and between the software packages in terms of small intra-rater, inter-rater and between-software differences of means and high Dice’s similarity coefficients. Time expenditure was highest for BrainVoyager, but all software packages were relatively time-consuming, which may limit usability in an everyday clinical setting.

Comparison of unsupervised classification methods for brain tumor segmentation using multi-parametric MRI

Tumor segmentation is a particularly challenging task in high-grade gliomas (HGGs), as they are among the most heterogeneous tumors in oncology. An accurate delineation of the lesion and its main subcomponents contributes to optimal treatment planning, prognosis and follow-up. Conventional MRI (cMRI) is the imaging modality of choice for manual segmentation, and is also considered in the vast majority of automated segmentation studies. Advanced MRI modalities such as perfusion-weighted imaging (PWI), diffusion-weighted imaging (DWI) and magnetic resonance spectroscopic imaging (MRSI) have already shown their added value in tumor tissue characterization, hence there have been recent suggestions of combining different MRI modalities into a multi-parametric MRI (MP-MRI) approach for brain tumor segmentation. In this paper, we compare the performance of several unsupervised classification methods for HGG segmentation based on MP-MRI data including cMRI, DWI, MRSI and PWI. Two independent MP-MRI datasets with a different acquisition protocol were available from different hospitals. We demonstrate that a hierarchical non-negative matrix factorization variant which was previously introduced for MP-MRI tumor segmentation gives the best performance in terms of mean Dice-scores for the pathologic tissue classes on both datasets.

•

Unsupervised classification algorithms are applied for brain tumor segmentation on multi-parametric MRI datasets.

•

Reported mean Dice-scores are in the range of state-of-the-art segmentation algorithms.

•

Hierarchical NMF obtained the best segmentation results in terms of mean Dice-scores for most of the tissue classes.

Fully automated, level set-based segmentation for knee MRIs using an adaptive force function and template: data from the osteoarthritis initiative

BACKGROUND

This study focuses on osteoarthritis (OA), which affects millions of adults and occurs in knee cartilage. Diagnosis of OA requires accurate segmentation of cartilage structures. Existing approaches to cartilage segmentation of knee imaging suffer from either lack of fully automatic algorithm, sub-par segmentation accuracy, or failure to consider all three cartilage tissues.

METHODS

We propose a novel segmentation algorithm for knee cartilages with level set-based segmentation method and novel template data. We used 20 normal subjects from osteoarthritis initiative database to construct new template data. We adopt spatial fuzzy C-mean clustering for automatic initialization of contours. Force function of our algorithm is modified to improve segmentation performance.

RESULTS

The proposed algorithm resulted in dice similarity coefficients (DSCs) of 87.1, 84.8 and 81.7 % for the femoral, patellar, and tibial cartilage, respectively from 10 subjects. The DSC results showed improvements of 8.8, 4.3 and 3.5 % for the femoral, patellar, and tibial cartilage respectively compared to existing approaches. Our algorithm could be applied to all three cartilage structures unlike existing approaches that considered only two cartilage tissues.

CONCLUSIONS

Our study proposes a novel fully automated segmentation algorithm adapted for three types of knee cartilage tissues. We leverage state-of-the-art level set approach with newly constructed knee template. The experimental results show that the proposed method improves the performance by an average of 5 % over existing methods.

Abnormality Detection via Iterative Deformable Registration and Basis-Pursuit Decomposition

We present a generic method for automatic detection of abnormal regions in medical images as deviations from a normative data base. The algorithm decomposes an image, or more broadly a function defined on the image grid, into the superposition of a normal part and a residual term. A statistical model is constructed with regional sparse learning to represent normative anatomical variations among a reference population (e.g., healthy controls), in conjunction with a Markov random field regularization that ensures mutual consistency of the regional learning among partially overlapping image blocks. The decomposition is performed in a principled way so that the normal part fits well with the learned normative model, while the residual term absorbs pathological patterns, which may then be detected through a statistical significance test. The decomposition is applied to multiple image features from an individual scan, detecting abnormalities using both intensity and shape information. We form an iterative scheme that interleaves abnormality detection with deformable registration, gradually improving robustness of the spatial normalization and precision of the detection. The algorithm is evaluated with simulated images and clinical data of brain lesions, and is shown to achieve robust deformable registration and localize pathological regions simultaneously. The algorithm is also applied on images from Alzheimer's disease patients to demonstrate the generality of the method.