Semi-automated brain tumor and edema segmentation using MRI

Recognizing Brain Tumors Using Adaptive Noise Filtering and Statistical Features

The human brain, primarily composed of white blood cells, is centered on the neurological system. Incorrectly positioned cells in the immune system, blood vessels, endocrine, glial, axon, and other cancer-causing tissues, can assemble to create a brain tumor. It is currently impossible to find cancer physically and make a diagnosis. The tumor can be found and recognized using the MRI-programmed division method. It takes a powerful segmentation technique to produce accurate output. This study examines a brain MRI scan and uses a technique to obtain a more precise image of the tumor-affected area. The critical aspects of the proposed method are the utilization of noisy MRI brain images, anisotropic noise removal filtering, segmentation with an SVM classifier, and isolation of the adjacent region from the normal morphological processes. Accurate brain MRI imaging is the primary goal of this strategy. The divided section of the cancer is placed on the actual image of a particular culture, but that is by no means the last step. The tumor is located by categorizing the pixel brightness in the filtered image. According to test findings, the SVM could partition data with 98% accuracy.

Brain tumor detection and classification using machine learning: a comprehensive survey

Brain tumor occurs owing to uncontrolled and rapid growth of cells. If not treated at an initial phase, it may lead to death. Despite many significant efforts and promising outcomes in this domain, accurate segmentation and classification remain a challenging task. A major challenge for brain tumor detection arises from the variations in tumor location, shape, and size. The objective of this survey is to deliver a comprehensive literature on brain tumor detection through magnetic resonance imaging to help the researchers. This survey covered the anatomy of brain tumors, publicly available datasets, enhancement techniques, segmentation, feature extraction, classification, and deep learning, transfer learning and quantum machine learning for brain tumors analysis. Finally, this survey provides all important literature for the detection of brain tumors with their advantages, limitations, developments, and future trends.

Fusion of Higher Order Spectra and Texture Extraction Methods for Automated Stroke Severity Classification with MRI Images

This paper presents a scientific foundation for automated stroke severity classification. We have constructed and assessed a system which extracts diagnostically relevant information from Magnetic Resonance Imaging (MRI) images. The design was based on 267 images that show the brain from individual subjects after stroke. They were labeled as either Lacunar Syndrome (LACS), Partial Anterior Circulation Syndrome (PACS), or Total Anterior Circulation Stroke (TACS). The labels indicate different physiological processes which manifest themselves in distinct image texture. The processing system was tasked with extracting texture information that could be used to classify a brain MRI image from a stroke survivor into either LACS, PACS, or TACS. We analyzed 6475 features that were obtained with Gray-Level Run Length Matrix (GLRLM), Higher Order Spectra (HOS), as well as a combination of Discrete Wavelet Transform (DWT) and Gray-Level Co-occurrence Matrix (GLCM) methods. The resulting features were ranked based on the p-value extracted with the Analysis Of Variance (ANOVA) algorithm. The ranked features were used to train and test four types of Support Vector Machine (SVM) classification algorithms according to the rules of 10-fold cross-validation. We found that SVM with Radial Basis Function (RBF) kernel achieves: Accuracy (ACC) = 93.62%, Specificity (SPE) = 95.91%, Sensitivity (SEN) = 92.44%, and Dice-score = 0.95. These results indicate that computer aided stroke severity diagnosis support is possible. Such systems might lead to progress in stroke diagnosis by enabling healthcare professionals to improve diagnosis and management of stroke patients with the same resources.

Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times

Objective

To evaluate the degree of similarity between manual and semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging (MRI).

Materials and Methods

This was a retrospective study of 15 MRI examinations of patients with histopathologically confirmed soft-tissue sarcomas acquired before therapeutic intervention. Manual and semiautomatic segmentations were performed by three radiologists, working independently, using the software 3D Slicer. The Dice similarity coefficient (DSC) and the Hausdorff distance were calculated in order to evaluate the similarity between manual and semiautomatic segmentation. To compare the two modalities in terms of the tumor volumes obtained, we also calculated descriptive statistics and intraclass correlation coefficients (ICCs).

Results

In the comparison between manual and semiautomatic segmentation, the DSC values ranged from 0.871 to 0.973. The comparison of the volumes segmented by the two modalities resulted in ICCs between 0.9927 and 0.9990. The DSC values ranged from 0.849 to 0.979 for intraobserver variability and from 0.741 to 0.972 for interobserver variability. There was no significant difference between the semiautomatic and manual modalities in terms of the segmentation times (p > 0.05).

Conclusion

There appears to be a high degree of similarity between manual and semiautomatic segmentation, with no significant difference between the two modalities in terms of the time required for segmentation.

Role of the noninvasive imaging techniques in monitoring and understanding the evolution of brain edema

Human brain injury elicits accumulation of water within the brain due to a variety of pathophysiological processes. As our understanding of edema emerged two temporally (and cellular) distinct processes were identified, cytotoxic and vasogenic edema. The emergence of both types of edema is reflected by the temporal evolution and is influenced by the underlying pathology (type and extent). However, this two-edema compartment model does not adequately describe the transition between cytotoxic and vasogenic edema. Hence, a third category has been proposed, termed ionic edema, that is observed in the transition between cytotoxic and vasogenic edema. Magnetic resonance neuroimaging of edema today primarily utilizes T2-weighted (T2WI) and diffusion-weighted imaging (DWI). Clinical diagnostics and translational science studies have clearly demonstrated the temporal ability of both T2WI and DWI to monitor edema content and evolution. DWI measures water mobility within the brain reflecting cytotoxic edema. T2WI at later time points when vasogenic edema develops visualizes increased water content in the brain. Clinically relevant imaging modalities, including ultrasound and positron emission tomography, are not typically used to assess edema. In sum, edema imaging is an important cornerstone of clinical diagnostics and translational studies and can guide effective therapeutics manage edema and improve patient outcomes.

Image-based state-of-the-art techniques for the identification and classification of brain diseases: a review

Detection and classification methods have a vital and important role in identifying brain diseases. Timely detection and classification of brain diseases enable an accurate identification and effective management of brain impairment. Brain disorders are commonly most spreadable diseases and the diagnosing process is time-consuming and highly expensive. There is an utmost need to develop effective and advantageous methods for brain diseases detection and characterization. Magnetic resonance imaging (MRI), computed tomography (CT), and other various brain imaging scans are used to identify different brain diseases and disorders. Brain imaging scans are the efficient tool to understand the anatomical changes in brain in fast and accurate manner. These different brain imaging scans used with segmentation techniques and along with machine learning and deep learning techniques give maximum accuracy and efficiency. This paper focuses on different conventional approaches, machine learning and deep learning techniques used for the detection, and classification of brain diseases and abnormalities. This paper also summarizes the research gap and problems in the existing techniques used for detection and classification of brain disorders. Comparison and evaluation of different machine learning and deep learning techniques in terms of efficiency and accuracy are also highlighted in this paper. Furthermore, different brain diseases like leukoariaosis, Alzheimer's, Parkinson's, and Wilson's disorder are studied in the scope of machine learning and deep learning techniques.

Peritumoral Edema Relative to Meningioma Size Predicts Functional Outcomes after Resection in Older Patients

BACKGROUND

Resection of meningiomas in older adults is associated with increased complications and postoperative functional deficits. Extent of peritumoral edema (PTE), which has been associated with surgical prognosis, may represent a preoperative risk marker for poorer outcomes in older adults.

OBJECTIVE

To quantitatively evaluate the relationship between preoperative PTE and postresection outcomes in older meningioma patients.

METHODS

One hundred twelve older meningioma patients (age ≥ 60) with evidence of PTE on MRI were reviewed. Extent of PTE, measured as a ratio of edema to tumor volume (edema index, EI) using semiautomatic image-processing software, was correlated with postresection outcomes. Other preoperative factors were included as covariates in multivariate analyses. Results were compared to matched nonedema older patients. Receiver operating characteristic (ROC) curve analysis was performed to identify cut-off EI values to predict postoperative outcomes.

RESULTS

EI was associated with functional decline (as measured by Karnofsky Performance Status, KPS) at 6 mo, 1, 2 yr, and most recent follow-up (Ps < .05), but not among the nonedema matched patients. Seizure or prior stroke additionally trended towards increasing the likelihood of lower KPS at 2 yr (odds ratio = 3.06) and last follow-up (odds ratio = 5.55), respectively. ROC curve analysis found optimal cut-off values for EI ranging from 2.01 to 3.37 to predict lower KPS at each follow-up interval. Sensitivities ranged from 60% to 80%, specificities from 78% to 89%, and positive and negative predictive values from 38% to 58% and 80% to 97%.

CONCLUSION

Preoperative PTE may represent a significant marker of poor functional outcome risk in older adults and provides a quantitative measurement to incorporate into surgical decision-making.

Risk of tumor recurrence in intracranial meningiomas: comparative analyses of the predictive value of the postoperative tumor volume and the Simpson classification

OBJECTIVE

In meningiomas, the Simpson grading system is applied to estimate the risk of postoperative recurrence, but might suffer from bias and limited overview of the resection cavity. In contrast, the value of the postoperative tumor volume as an objective predictor of recurrence is largely unexplored. The objective of this study was to compare the predictive value of residual tumor volume with the intraoperatively assessed extent of resection (EOR).

METHODS

The Simpson grade was determined in 939 patients after surgery for initially diagnosed intracranial meningioma. Tumor volume was measured on initial postoperative MRI within 6 months after surgery. Correlation between both variables and recurrence was compared using a tree-structured Cox regression model.

RESULTS

Recurrence correlated with Simpson grading (p = 0.003). In 423 patients (45%) with available imaging, residual tumor volume covered a broad range (0-78.5 cm3). MRI revealed tumor remnants in 8% after gross-total resection (Simpson grade I-III, range 0.12-33.5 cm3) with a Cohen's kappa coefficient of 0.7153. Postoperative tumor volume was correlated with recurrence in univariate analysis (HR 1.05 per cm3, 95% CI 1.02-1.08 per cm3, p < 0.001). A tree-structured Cox regression model revealed any postoperative tumor volume > 0 cm3 as a critical cutoff value for the prediction of relapse. Multivariate analysis confirmed the postoperative tumor volume (HR 1.05, p < 0.001) but not the Simpson grading (p = 0.398) as a predictor for recurrence.

CONCLUSIONS

EOR according to Simpson grading was overrated in 8% of tumors compared to postoperative imaging. Because the predictive value of postoperative imaging is superior to the Simpson grade, any residual tumor should be carefully considered during postoperative care of meningioma patients.

Improved model prediction of glioma growth utilizing tissue-specific boundary effects

Kinetic parameter estimates for mathematical models of glioblastoma multiforme (GBM), derived from clinical scans, have been used to predict the occurrence of hypoxia, necrosis, response to radiation therapy, and overall survival. Modeling GBM growth in a cerebral model encounters anatomical boundaries that interfere with model calibration from clinical measurements.

METHODS

The effect of boundaries is examined on both spherically symmetric and anatomical models of tumor growth. This effect is incorporated into a method that updates kinetic parameters. The efficacy of this method in reproducing clinical image-derived subject data is evaluated.

RESULTS

Spherically symmetric simulations of tumor growth with simple boundaries behave predictably when in a linear phase of growth. Anatomic simulations of eleven out of twenty subjects demonstrated improved fit to subject data with the new method. When only subjects exhibiting linear growth are considered, eight out of nine subject demonstrate improved fit to the data.

CONCLUSION

Anatomical boundaries to tumor growth measurably deflect progression and affect estimates of kinetic parameters. The presented method reliably updates kinetic parameters to fit anatomic computational models to clinically derived subject data when those data are in a linear regime.

On differentiation between vasogenic edema and non-enhancing tumor in high-grade glioma patients using a support vector machine classifier based upon pre and post-surgery MRI images

PURPOSE

High grade gliomas (HGGs) are infiltrative in nature. Differentiation between vasogenic edema and non-contrast enhancing tumor is difficult as both appear hyperintense in T₂-W/FLAIR images. Most studies involving differentiation between vasogenic edema and non-enhancing tumor consider radiologist-based tumor delineation as the ground truth. However, analysis by a radiologist can be subjective and there remain both inter- and intra-rater differences. The objective of the current study is to develop a methodology for differentiation between non-enhancing tumor and vasogenic edema in HGG patients based on T₁ perfusion MRI parameters, using a ground truth which is independent of a radiologist's manual delineation of the tumor.

MATERIAL AND METHODS

This study included 9 HGG patients with pre- and post-surgery MRI data and 9 metastasis patients with pre-surgery MRI data. MRI data included conventional T₁-W, T₂-W, and FLAIR images and DCE-MRI dynamic images. In this study, the authors hypothesize that surgeried non-enhancing FLAIR hyperintense tissue, which was obtained using pre- and post-surgery MRI images of glioma patients, should be largely comprised of non-enhancing tumor. Hence this could be used as an alternative ground truth for the non-enhancing tumor region. Histological examination of the resected tissue was done for validation. Vasogenic edema was obtained from the non-enhancing FLAIR hyperintense region of metastasis patients, as they have a clear boundary between enhancing tumor and edema. DCE-MRI data analysis was performed to obtain T₁ perfusion MRI parameters. Support Vector Machine (SVM) classification was performed using T₁ perfusion MRI parameters to differentiate between non-enhancing tumor and vasogenic edema. Receiver-operating-characteristic (ROC) analysis was done on the results of the SVM classifier. For improved classification accuracy, the SVM output was post-processed via neighborhood smoothing.

RESULTS

Histology results showed that resected tissue consists largely of tumorous tissue with 7.21 ± 4.05% edema and a small amount of healthy tissue. SVM-based classification provided a misclassification error of 8.4% in differentiation between non-enhancing tumor and vasogenic edema, which was further reduced to 2.4% using neighborhood smoothing.

CONCLUSION

The current study proposes a semiautomatic method for segmentation between non-enhancing tumor and vasogenic edema in HGG patients, based on an SVM classifier trained on an alternative ground truth to a radiologist's manual delineation of a tumor. The proposed methodology may prove to be a useful tool for pre- and post-operative evaluation of glioma patients.

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.

Relevance of two manual tumour volume estimation methods for diffuse low-grade gliomas

Management of diffuse low-grade glioma (DLGG) relies extensively on tumour volume estimation from MRI datasets. Two methods are currently clinically used to define this volume: the commonly used three-diameters solution and the more rarely used software-based volume reconstruction from the manual segmentations approach. The authors conducted an initial study of inter-practitioners’ variability of software-based manual segmentations on DLGGs MRI datasets. A panel of 13 experts from various specialties and years of experience delineated 12 DLGGs’ MRI scans. A statistical analysis on the segmented tumour volumes and pixels indicated that the individual practitioner, the years of experience and the specialty seem to have no significant impact on the segmentation of DLGGs. This is an interesting result as it had not yet been demonstrated and as it encourages cross-disciplinary collaboration. Their second study was with the three-diameters method, investigating its impact and that of the software-based volume reconstruction from manual segmentations method on tumour volume. They relied on the same dataset and on a participant from the first study. They compared the average of tumour volumes acquired by software reconstruction from manual segmentations method with tumour volumes obtained with the three-diameters method. The authors found that there is no statistically significant difference between the volumes estimated with the two approaches. These results correspond to non-operated and easily delineable DLGGs and are particularly interesting for time-consuming CUBE MRIs. Nonetheless, the three-diameters method has limitations in estimating tumour volumes for resected DLGGs, for which case the software-based manual segmentation method becomes more appropriate.

Statistical evaluation of manual segmentation of a diffuse low-grade glioma MRI dataset

Software-based manual segmentation is critical to the supervision of diffuse low-grade glioma patients and to the optimal treatment's choice. However, manual segmentation being time-consuming, it is difficult to include it in the clinical routine. An alternative to circumvent the time cost of manual segmentation could be to share the task among different practitioners, providing it can be reproduced. The goal of our work is to assess diffuse low-grade gliomas' manual segmentation's reproducibility on MRI scans, with regard to practitioners, their experience and field of expertise. A panel of 13 experts manually segmented 12 diffuse low-grade glioma clinical MRI datasets using the OSIRIX software. A statistical analysis gave promising results, as the practitioner factor, the medical specialty and the years of experience seem to have no significant impact on the average values of the tumor volume variable.

Detection and volume estimation of artificial hematomas in the subcutaneous fatty tissue: comparison of different MR sequences at 3.0 T

In legal medicine, reliable localization and analysis of hematomas in subcutaneous fatty tissue is required for forensic reconstruction. Due to the absence of ionizing radiation, magnetic resonance imaging (MRI) is particularly suited to examining living persons with forensically relevant injuries. However, there is limited experience regarding MRI signal properties of hemorrhage in soft tissue. The aim of this study was to evaluate MR sequences with respect to their ability to show high contrast between hematomas and subcutaneous fatty tissue as well as to reliably determine the volume of artificial hematomas. Porcine tissue models were prepared by injecting blood into the subcutaneous fatty tissue to create artificial hematomas. MR images were acquired at 3T and four blinded observers conducted manual segmentation of the hematomas. To assess segmentability, the agreement of measured volume with the known volume of injected blood was statistically analyzed. A physically motivated normalization taking into account partial volume effect was applied to the data to ensure comparable results among differently sized hematomas. The inversion recovery sequence exhibited the best segmentability rate, whereas the T1T2w turbo spin echo sequence showed the most accurate results regarding volume estimation. Both sequences led to reproducible volume estimations. This study demonstrates that MRI is a promising forensic tool to assess and visualize even very small amounts of blood in soft tissue. The presented results enable the improvement of protocols for detection and volume determination of hemorrhage in forensically relevant cases and also provide fundamental knowledge for future in-vivo examinations.

Gender-specific growth dynamics of neurofibromatosis type-2-related tumors of the central nervous system

BACKGROUND

To date, few studies have been published about the growth dynamics of tumors associated with neurofibromatosis type-2 (NF2), none of which evaluated gender-specific differences. Our aim was to compare radiographic data of female and male patients with NF2.

METHODS

MR images of 40 patients (20 female, 20 male) from the regional NF2 referral center were included in this analysis. Tumor sizes were determined by semi-automated volumetric measurement. Intracranial tumors were measured on post-contrast T1-weighted MRI datasets and volumes of intramedullary spinal tumors were determined from sagittal T2-weighted MRI datasets.

RESULTS

The median follow-up time was 91 months (range, 16-199 months) per patient. Intracranial tumors: On average, female patients had 13.4 neoplasms, while male patients had 6.75 (p = 0.042). The overall median time to tumor progression of ≥20 % was 20 months for females and 18 months for males. Tumors of the cerebellopontine angle (CPA) that had undergone previous surgery had shorter progression-free intervals in females than in males (16 and 24 months, respectively; p = 0.012). The median 1-year growth rate was 17.5 ± 44.6 % in females compared to 12.5 ± 44.9 % in males (p = 0.625). Intramedullary spinal tumors: On average, females had 2.05 tumors and males had 1.75 tumors (p = 0.721). Median time to tumor progression was 21 months in females and 44 months in males (p = 0.204). After 2 years, the median growth rate was 24.4 ± 56.8 % in female and 13.5 ± 40.4 % in male patients (p = 0.813).

CONCLUSIONS

The radiographic data in this study suggest that female patients are affected by a greater number of tumors than male patients and that post-surgery tumors of the CPA grow faster in females than in males.

Brain tumor segmentation from multimodal magnetic resonance images via sparse representation

OBJECTIVE

Accurately segmenting and quantifying brain gliomas from magnetic resonance (MR) images remains a challenging task because of the large spatial and structural variability among brain tumors. To develop a fully automatic and accurate brain tumor segmentation algorithm, we present a probabilistic model of multimodal MR brain tumor segmentation. This model combines sparse representation and the Markov random field (MRF) to solve the spatial and structural variability problem.

METHODS

We formulate the tumor segmentation problem as a multi-classification task by labeling each voxel as the maximum posterior probability. We estimate the maximum a posteriori (MAP) probability by introducing the sparse representation into a likelihood probability and a MRF into the prior probability. Considering the MAP as an NP-hard problem, we convert the maximum posterior probability estimation into a minimum energy optimization problem and employ graph cuts to find the solution to the MAP estimation.

RESULTS

Our method is evaluated using the Brain Tumor Segmentation Challenge 2013 database (BRATS 2013) and obtained Dice coefficient metric values of 0.85, 0.75, and 0.69 on the high-grade Challenge data set, 0.73, 0.56, and 0.54 on the high-grade Challenge LeaderBoard data set, and 0.84, 0.54, and 0.57 on the low-grade Challenge data set for the complete, core, and enhancing regions.

CONCLUSIONS

The experimental results show that the proposed algorithm is valid and ranks 2nd compared with the state-of-the-art tumor segmentation algorithms in the MICCAI BRATS 2013 challenge.

Rapid and Accurate MRI Segmentation of Peritumoral Brain Edema in Meningiomas

PURPOSE

The extent of peritumoral brain edema (PTBE) in meningiomas commonly affects the clinical outcome. Despite its importance, edema volume is usually highly inaccurately approximated to a spheroid shape. We tested the accuracy and the reproducibility of semiautomatic lesion management software for the analysis of PTBE in a homogeneous case series of surgically confirmed intracranial meningiomas.

METHODS

PTBE volume was calculated on magnetic resonance images in 50 patients with intracranial meningiomas using commercial lesion management software (Vue PACS Livewire, Carestream, Rochester, NY, USA). Inter and intraobserver agreement evaluation and a comparison between manual volume calculation, the semiautomatic software and spheroid approximation were performed in 22 randomly selected patients.

RESULTS

The calculation of edema volume was possible in all cases irrespective of the extent of the signal changes. The median time for each calculation was 3 min. Interobserver and intraobserver agreement confirmed the reproducibility of the method. Comparison with standard (fully manual) calculation confirmed the accuracy of this software.

CONCLUSIONS

Our study showed a high level of reproducibility of this semiautomatic computational method for peritumoral brain edema. It is rapid and easy to use after relatively short training and is suitable for implementation in clinical practice.

Prognostic Value of Dynamic Susceptibility Contrast-Enhanced and Diffusion-Weighted MR Imaging in Patients with Glioblastomas

BACKGROUND AND PURPOSE

Prediction of survival in patients with glioblastomas is important for individualized treatment planning. This study aimed to assess the prognostic utility of presurgical dynamic susceptibility contrast and diffusion-weighted imaging for overall survival in patients with glioblastoma.

MATERIALS AND METHODS

MR imaging data from pathologically proved glioblastomas between June 2006 to December 2013 in 58 patients (mean age, 62.7 years; age range, 22-89 years) were included in this retrospective study. Patients were divided into long survival (≥15 months) and short survival (<15 months) groups, depending on overall survival time. Patients underwent dynamic susceptibility contrast perfusion and DWI before surgery and were treated with chemotherapy and radiation therapy. The maximum relative cerebral blood volume and minimum mean diffusivity values were measured from the enhancing part of the tumor.

RESULTS

Maximum relative cerebral blood volume values in patients with short survival were significantly higher compared with those who demonstrated long survival (P < .05). No significant difference was observed in the minimum mean diffusivity between short and long survivors. Receiver operator curve analysis demonstrated that a maximum relative cerebral blood volume cutoff value of 5.79 differentiated patients with low and high survival with an area under the curve of 0.93, sensitivity of 0.89, and specificity of 0.90 (P < .001), while a minimum mean diffusivity cutoff value of 8.35 × 10(-4)mm(2)/s had an area under the curve of 0.55, sensitivity of 0.71, and specificity of 0.47 (P > .05) in separating the 2 groups.

CONCLUSIONS

Maximum relative cerebral blood volume may be used as a prognostic marker of overall survival in patients with glioblastomas.

Rough-fuzzy clustering and unsupervised feature selection for wavelet based MR image segmentation

Image segmentation is an indispensable process in the visualization of human tissues, particularly during clinical analysis of brain magnetic resonance (MR) images. For many human experts, manual segmentation is a difficult and time consuming task, which makes an automated brain MR image segmentation method desirable. In this regard, this paper presents a new segmentation method for brain MR images, integrating judiciously the merits of rough-fuzzy computing and multiresolution image analysis technique. The proposed method assumes that the major brain tissues, namely, gray matter, white matter, and cerebrospinal fluid from the MR images are considered to have different textural properties. The dyadic wavelet analysis is used to extract the scale-space feature vector for each pixel, while the rough-fuzzy clustering is used to address the uncertainty problem of brain MR image segmentation. An unsupervised feature selection method is introduced, based on maximum relevance-maximum significance criterion, to select relevant and significant textural features for segmentation problem, while the mathematical morphology based skull stripping preprocessing step is proposed to remove the non-cerebral tissues like skull. The performance of the proposed method, along with a comparison with related approaches, is demonstrated on a set of synthetic and real brain MR images using standard validity indices.

Could magnetic resonance provide in vivo histology?

The diagnosis of a suspected tumor lesion faces two basic problems: detection and identification of the specific type of tumor. Radiological techniques are commonly used for the detection and localization of solid tumors. Prerequisite is a high intrinsic or enhanced contrast between normal and neoplastic tissue. Identification of the tumor type is still based on histological analysis. The result depends critically on the sampling sites, which given the inherent heterogeneity of tumors, constitutes a major limitation. Non-invasive in vivo imaging might overcome this limitation providing comprehensive three-dimensional morphological, physiological, and metabolic information as well as the possibility for longitudinal studies. In this context, magnetic resonance based techniques are quite attractive since offer at the same time high spatial resolution, unique soft tissue contrast, good temporal resolution to study dynamic processes and high chemical specificity. The goal of this paper is to review the role of magnetic resonance techniques in characterizing tumor tissue in vivo both at morphological and physiological levels. The first part of this review covers methods, which provide information on specific aspects of tumor phenotypes, considered as indicators of malignancy. These comprise measurements of the inflammatory status, neo-vascular physiology, acidosis, tumor oxygenation, and metabolism together with tissue morphology. Even if the spatial resolution is not sufficient to characterize the tumor phenotype at a cellular level, this multiparametric information might potentially be used for classification of tumors. The second part discusses mathematical tools, which allow characterizing tissue based on the acquired three-dimensional data set. In particular, methods addressing tumor heterogeneity will be highlighted. Finally, we address the potential and limitation of using MRI as a tool to provide in vivo tissue characterization.

State of the art survey on MRI brain tumor segmentation

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

Appraisal of the current staging system for residual medulloblastoma by volumetric analysis

AIM

This study aims to investigate the accuracy of the current staging system of childhood medulloblastoma by using volumetric image analysis on immediate post-operative MRI scans.

MATERIAL AND METHODS

Tumour volume and maximum cross area of residual medulloblastoma were measured on immediate post-operative MR scans of 37 children operated between 1999 and 2005.

RESULTS

Mean preoperative volume was 32 cm(3) (range 4.5-71.9 cm(3)). Mean post-operative volume was 3.3 cm(3) (range 0-23.3 cm(3)). At mean follow-up of 50.08 months (range 6-129), 15 (40%) patients had died. Cut-off limit for residual post-operative tumour volume employed was maximum cross section of 1.5 cm(2), which corresponds to volume of 1.376 cm(3); 14 patients (38%) had no residual tumour, 7 patients (19%) had less than 1.5 cm(2) and 16 patients (43%) had more than 1.5 cm(2) residual tumour in its maximum cross section area. In three patients (8.2%) there was mismatch between the measured maximum cross section area and volume. In particular, in two patients, the cross section areas were more than 1.5 cm(2) but the residual tumour volumes were less than 1.376 cm(3) (the cross section area overestimated the residual volume) and in one case, the cross section area was less than 1.5 cm(2) but the residual tumour volume was more than 1.376 cm(3) (the cross section area underestimated the residual volume; difference statistically significant, Fisher's exact test, p < 0.01).

CONCLUSIONS

It appears that volumetric measurement of residual medulloblastoma on immediate post-operative MRI scans may further improve the accuracy of staging process.

Automatic segmentation of meningioma from non-contrasted brain MRI integrating fuzzy clustering and region growing

Background

In recent years, magnetic resonance imaging (MRI) has become important in brain tumor diagnosis. Using this modality, physicians can locate specific pathologies by analyzing differences in tissue character presented in different types of MR images.

This paper uses an algorithm integrating fuzzy-c-mean (FCM) and region growing techniques for automated tumor image segmentation from patients with menigioma. Only non-contrasted T1 and T2 -weighted MR images are included in the analysis. The study's aims are to correctly locate tumors in the images, and to detect those situated in the midline position of the brain.

Methods

The study used non-contrasted T1- and T2-weighted MR images from 29 patients with menigioma. After FCM clustering, 32 groups of images from each patient group were put through the region-growing procedure for pixels aggregation. Later, using knowledge-based information, the system selected tumor-containing images from these groups and merged them into one tumor image. An alternative semi-supervised method was added at this stage for comparison with the automatic method. Finally, the tumor image was optimized by a morphology operator. Results from automatic segmentation were compared to the "ground truth" (GT) on a pixel level. Overall data were then evaluated using a quantified system.

Results

The quantified parameters, including the "percent match" (PM) and "correlation ratio" (CR), suggested a high match between GT and the present study's system, as well as a fair level of correspondence. The results were compatible with those from other related studies. The system successfully detected all of the tumors situated at the midline of brain.

Six cases failed in the automatic group. One also failed in the semi-supervised alternative. The remaining five cases presented noticeable edema inside the brain. In the 23 successful cases, the PM and CR values in the two groups were highly related.

Conclusions

Results indicated that, even when using only two sets of non-contrasted MR images, the system is a reliable and efficient method of brain-tumor detection. With further development the system demonstrates high potential for practical clinical use.

MRI internal segmentation of optic pathway gliomas: clinical implementation of a novel algorithm

PURPOSE

Optic pathway gliomas (OPGs) are diagnosed based on typical MR features and require careful monitoring with serial MRI. Reliable, serial radiological comparison of OPGs is a difficult task, where accuracy becomes very important for clinical decisions on treatment initiation and results. Current radiological methodology usually includes linear measurements that are limited in terms of precision and reproducibility.

METHOD

We present a method that enables semiautomated segmentation and internal classification of OPGs using a novel algorithm. Our method begins with co-registration of the different sequences of an MR study so that T1 and T2 slices are realigned. The follow-up studies are then re-sliced according to the baseline study. The baseline tumor is segmented, with internal components classified into solid non-enhancing, solid-enhancing, and cystic components, and the volume is calculated. Tumor demarcation is then transferred onto the next study and the process repeated. Numerical values are correlated with clinical data such as treatment and visual ability.

RESULTS

We have retrospectively implemented our method on 24 MR studies of three OPG patients. Clinical case reviews are presented here. The volumetric results have been correlated with clinical data and their implications are also discussed.

CONCLUSIONS

The heterogeneity of OPGs, the long course, and the young age of the patients are all driving the demand for more efficient and accurate means of tumor follow-up. This method may allow better understanding of the natural history of the tumor and provide a more advanced means of treatment evaluation.

Application of Adaptive Resonance Theory Neural Network for MR Brain Tumor Image Classification

In the present study, the effectiveness of the adaptive resonance theory neural network (ART2) is illustrated in the context of automatic classification of abnormal brain tumor images. Abnormal images from four different classes namely metastase, meningioma, glioma and astrocytoma have been used in this work. Initially, textural features are extracted from these images. An extensive feature selection is performed to optimize the number of features. These optimized features are then used to classify the images using ART2 neural network. Experimental results show promising results for the ART2 network in terms of classification accuracy and convergence rate. A comparison is made with other conventional classifiers to show the superior nature of ART2 neural network. The classification accuracy of the ART2 classifier is significantly higher than the statistical classifiers. ART2 classifier is also computationally feasible over other neural classifiers. Thus this work suggests ART2 neural network as an optimal image classifier which finds application in clinical field.

Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov Random Field

A variety of algorithms have been proposed for brain tumor segmentation from multi-channel sequences, however, most of them require isotropic or pseudo-isotropic resolution of the MR images. Although co-registration and interpolation of low-resolution sequences, such as T2-weighted images, onto the space of the high-resolution image, such as T1-weighted image, can be performed prior to the segmentation, the results are usually limited by partial volume effects due to interpolation of low-resolution images. To improve the quality of tumor segmentation in clinical applications where low-resolution sequences are commonly used together with high-resolution images, we propose the algorithm based on Spatial accuracy-weighted Hidden Markov random field and Expectation maximization (SHE) approach for both automated tumor and enhanced-tumor segmentation. SHE incorporates the spatial interpolation accuracy of low-resolution images into the optimization procedure of the Hidden Markov Random Field (HMRF) to segment tumor using multi-channel MR images with different resolutions, e.g., high-resolution T1-weighted and low-resolution T2-weighted images. In experiments, we evaluated this algorithm using a set of simulated multi-channel brain MR images with known ground-truth tissue segmentation and also applied it to a dataset of MR images obtained during clinical trials of brain tumor chemotherapy. The results show that more accurate tumor segmentation results can be obtained by comparing with conventional multi-channel segmentation algorithms.

A deformable model-based system for 3D analysis and visualization of tumor in PET/CT images

This paper presents a tumor detecting system that allows interactive 3D tumor visualization and tumor volume measurements. An improved level set method is proposed to automatically segment the tumor images slice by slice. PET images are used to detect the tumor while CT images make a 3D representation of the patient's body possible. An initial slice with a seed within the tumor is firstly chosen by the operator. The system then performs automatically the tumor volume segmentation that allows the clinician to visualize the tumor, to measure it and to evaluate the best medical treatment adapted to the patient.

Lesion identification using unified segmentation-normalisation models and fuzzy clustering

In this paper, we propose a new automated procedure for lesion identification from single images based on the detection of outlier voxels. We demonstrate the utility of this procedure using artificial and real lesions. The scheme rests on two innovations: First, we augment the generative model used for combined segmentation and normalization of images, with an empirical prior for an atypical tissue class, which can be optimised iteratively. Second, we adopt a fuzzy clustering procedure to identify outlier voxels in normalised gray and white matter segments. These two advances suppress misclassification of voxels and restrict lesion identification to gray/white matter lesions respectively. Our analyses show a high sensitivity for detecting and delineating brain lesions with different sizes, locations, and textures. Our approach has important implications for the generation of lesion overlap maps of a given population and the assessment of lesion-deficit mappings. From a clinical perspective, our method should help to compute the total volume of lesion or to trace precisely lesion boundaries that might be pertinent for surgical or diagnostic purposes.

A validation framework for brain tumor segmentation

RATIONALE AND OBJECTIVES

We introduce a validation framework for the segmentation of brain tumors from magnetic resonance (MR) images. A novel unsupervised semiautomatic brain tumor segmentation algorithm is also presented.

MATERIALS AND METHODS

The proposed framework consists of 1) T1-weighted MR images of patients with brain tumors, 2) segmentation of brain tumors performed by four independent experts, 3) segmentation of brain tumors generated by a semiautomatic algorithm, and 4) a software tool that estimates the performance of segmentation algorithms.

RESULTS

We demonstrate the validation of the novel segmentation algorithm within the proposed framework. We show its performance and compare it with existent segmentation. The image datasets and software are available at http://www.brain-tumor-repository.org/.

CONCLUSIONS

We present an Internet resource that provides access to MR brain tumor image data and segmentation that can be openly used by the research community. Its purpose is to encourage the development and evaluation of segmentation methods by providing raw test and image data, human expert segmentation results, and methods for comparing segmentation results.