Intensity Inhomogeneity Correction Research Articles

Volume and surface coil simultaneous reception (VSSR) method for intensity inhomogeneity correction in MRI.

Addressing intensity inhomogeneity is critical in magnetic resonance imaging (MRI) because associated errors can adversely affect post-processing and quantitative analysis of images (i.e., segmentation, registration, etc.), as well as the accuracy of clinical diagnosis. Although several prior methods have been proposed to eliminate or correct intensity inhomogeneity, some significant disadvantages have remained, including alteration of tissue contrast, poor reliability and robustness of algorithms, and prolonged acquisition time. In this study, we propose an intensity inhomogeneity correction method based on volume and surface coils simultaneous reception (VSSR). The VSSR method comprises of two major steps: 1) simultaneous image acquisition from both volume and surface coils and 2) denoising of volume coil images and polynomial surface fitting of bias field. Extensive in vivo experiments were performed considering various anatomical structures, acquisition sequences, imaging resolutions, and orientations. In terms of correction performance, the proposed VSSR method was comparatively evaluated against several popular methods, including multiplicative intrinsic component optimization and improved nonparametric nonuniform intensity normalization bias correction methods. Experimental results show that VSSR is more robust and reliable and does not require prolonged acquisition time with the volume coil. The VSSR may be considered suitable for general implementation.

Active contour model driven by optimized energy functionals for MR brain tumor segmentation with intensity inhomogeneity correction

Segmentation of brain tumors is important for medical diagnosis, treatment planning, and disease development. However, the presence of image artifacts such as noise, intensity inhomogeneity, and partial volume effect in real-world images can aggressively affect the segmentation task. The manual segmentation of the tumor is highly error-prone and is a time-consuming task. Hence, in this work, we propose a methodology that can identify and segment the brain tumor slices in magnetic resonance (MRI) images. The work is composed of three main stages namely pre-processing, segmentation, and post-processing. In the pre-processing stage, N4ITK is applied to correct the intensity inhomogeneity and an Anisotropic diffusion filter is used to remove the noise present in MR images. In the segmentation stage, an active contour model that combines the region scalable fitting energy (RSF) and optimized laplacian of gaussian energy (OLoG) is proposed to segment the tumor region from MRI. The proposed segmentation method first presents an LoG energy term optimized by an energy functional that can smooth the homogeneous regions and enhance edge information simultaneously. Next, the optimized LoG energy term is combined with the RSF energy term which utilizes the local region information to drive the curve towards the boundaries. With the addition of the LoG term, the proposed model is insensitive to the positions of the initial contour and produces an accurate segmentation result. Finally, morphological operations and thresholding are used to extract the tumor region from the segmented image which is computed previously. The performance of the proposed segmentation method is evaluated using the BRATS, and J.Cheng dataset. The obtained experimental results demonstrate that our proposed method significantly outperforms the manual process and state of the art methods in brain tumor segmentation.

Intensity inhomogeneity correction of MRI images using InhomoNet

Intensity inhomogeneity is one of the major artifacts in magnetic resonance imaging (MRI). Bias field present in MRI images alters true pixel value and produces spurious varying pixel intensities. This artifact affects the diagnosis by radiologists in a detrimental manner and also degrades the performance of computer-aided diagnosis algorithms such as segmentation. The present work proposes a novel network called InhomoNet for intensity inhomogeneity correction of MRI image. The generator architecture of InhomoNet consists of a new multi-scale local information module at each encoder block that helps to capture features at multiple scales. The horizontal and vertical kernels help to reduce the problems like loss of neighborhood information, gridding issues caused due to large dilated convolution operations. The attention-driven skip connections in the generator network are utilized to transfer optimal semantic and spatial localization information from the encoder to decoder blocks. Further, the present work proposes two new losses functions, i.e. histogram correlation and 3D pixel loss. These losses help to realize pixel consistency across different regions of brain MRI. The inculcation of the L1 loss provides guidance to the upsampling process as it compares the prediction from each decoder block with the ground truth. The proposed method is evaluated on simulated and real MRI data. The comparative analysis with popular state-of-the-art methods depicts the ability of the proposed method to perform intensity inhomogeneity correction accurately.

Automated glioma grading on conventional MRI images using deep convolutional neural networks.

Gliomas are the most common primary tumor of the brain and are classified into grades I-IV of the World Health Organization (WHO), based on their invasively histological appearance. Gliomas grading plays an important role to determine the treatment plan and prognosis prediction. In this study we propose two novel methods for automatic, non-invasively distinguishing low-grade (Grades II and III) glioma (LGG) and high-grade (grade IV) glioma (HGG) on conventional MRI images by using deep convolutional neural networks (CNNs). All MRI images have been preprocessed first by rigid image registration and intensity inhomogeneity correction. Both proposed methods consist of two steps: (a) three-dimensional (3D) brain tumor segmentation based on a modification of the popular U-Net model; (b) tumor classification on segmented brain tumor. In the first method, the slice with largest area of tumor is determined and the state-of-the-art mask R-CNN model is employed for tumor grading. To improve the performance of the grading model, a two-dimensional (2D) data augmentation has been implemented to increase both the amount and the diversity of the training images. In the second method, denoted as 3DConvNet, a 3D volumetric CNNs is applied directly on bounding image regions of segmented tumor for classification, which can fully leverage the 3D spatial contextual information of volumetric image data. The proposed schemes were evaluated on The Cancer Imaging Archive (TCIA) low grade glioma (LGG) data, and the Multimodal Brain Tumor Image Segmentation (BraTS) Benchmark 2018 training datasets with fivefold cross validation. All data are divided into training, validation, and test sets. Based on biopsy-proven ground truth, the performance metrics of sensitivity, specificity, and accuracy are measured on the test sets. The results are 0.935 (sensitivity), 0.972 (specificity), and 0.963 (accuracy) for the 2D Mask R-CNN based method, and 0.947 (sensitivity), 0.968 (specificity), and 0.971 (accuracy) for the 3DConvNet method, respectively. In regard to efficiency, for 3D brain tumor segmentation, the program takes around ten and a half hours for training with 300 epochs on BraTS 2018 dataset and takes only around 50s for testing of a typical image with a size of 160×216×176. For 2D Mask R-CNN based tumor grading, the program takes around 4h for training with around 60000 iterations, and around 1s for testing of a 2D slice image with size of 128×128. For 3DConvNet based tumor grading, the program takes around 2h for training with 10000 iterations, and 0.25s for testing of a 3D cropped image with size of 64×64×64, using a DELL PRECISION Tower T7910, with two NVIDIA Titan Xp GPUs. Two effective glioma grading methods on conventional MRI images using deep convolutional neural networks have been developed. Our methods are fully automated without manual specification of region-of-interests and selection of slices for model training, which are common in traditional machine learning based brain tumor grading methods. This methodology may play a crucial role in selecting effective treatment options and survival predictions without the need for surgical biopsy.

A diffusion‐based compensation approach for intensity inhomogeneity correction in MRI

AbstractIntensity inhomogeneity is considered as an inherent artifact in magnetic resonance images and is prominent in high‐field strength scanners. An effective and conceptually simple retrospective correction technique is introduced in this article that implements a compensation function based on spatially constrained fuzzy c‐means clustering to reduce the effect of intensity inhomogeneity. Intensity compensation functions are estimated on each clustered region and are subsequently processed with an anisotropic diffusion strategy. The proposed approach does not require any parametric models or prior knowledge on the acquisition process for the intensity inhomogeneity correction. The proposed diffusion based technique was evaluated on simulated and real data sets and the results were compared with some of the prominent correction methods. The quantitative analyses in terms of coefficient of variation and coefficient of joint variation ensure the effectiveness of the proposed methodology. The experimental analyses of the results show that the proposed methodology outperforms the state‐of‐the‐art approaches.

Fully automated lesion segmentation and visualization in automated whole breast ultrasound (ABUS) images.

The number of breast cancer patients has increased each year, and the demand for breast cancer detection has become quite large. There are many common breast cancer diagnostic tools. The latest automated whole breast ultrasound (ABUS) technology can obtain a complete breast tissue structure, which improves breast cancer detection technology. However, due to the large amount of ABUS image data, manual interpretation is time-consuming and labor-intensive. If there are lesions in multiple images, there may be some omissions. In addition, if further volume information or the three-dimensional shape of the lesion is needed for therapy, it is necessary to manually segment each lesion, which is inefficient for diagnosis. Therefore, automatic lesion segmentation for ABUS is an important issue for guiding therapy. Due to the amount of speckle noise in an ultrasonic image and the low contrast of the lesion boundary, it is quite difficult to automatically segment the lesion. To address the above challenges, this study proposes an automated lesion segmentation algorithm. The architecture of the proposed algorithm can be divided into four parts: (I) volume of interest selection, (II) preprocessing, (III) segmentation, and (IV) visualization. A volume of interest (VOI) is automatically selected first via a three-dimensional level-set, and then the method uses anisotropic diffusion to address the speckled noise and intensity inhomogeneity correction to eliminate shadowing artifacts before the adaptive distance regularization level set method (DRLSE) conducts segmentation. Finally, the two-dimensional segmented images are reconstructed for visualization in the three-dimensional space. The ground truth is delineated by two radiologists with more than 10 years of experience in breast sonography. In this study, three performance assessments are carried out to evaluate the effectiveness of the proposed algorithm. The first assessment is the similarity measurement. The second assessment is the comparison of the results of the proposed algorithm and the Chan-Vese level set method. The third assessment is the volume estimation of phantom cases. In this study, in the 2D validation of the first assessment, the area Dice similarity coefficients of the real cases named cases A, real cases B and phantoms are 0.84±0.02, 0.86±0.03 and 0.92±0.02, respectively. The overlap fraction (OF) and overlap value (OV) of the real cases A are 0.84±0.06 and 0.78±0.04, real case B are 0.91±0.04 and 0.82±0.05, respectively. The overlap fraction (OF) and overlap value (OV) of the phantoms are 0.95±0.02 and 0.92±0.03, respectively. In the 3D validation, the volume Dice similarity coefficients of the real cases A, real cases B and phantoms are 0.85±0.02, 0.89±0.04 and 0.94±0.02, respectively. The overlap fraction (OF) and overlap value (OV) of the real cases A are 0.82±0.06 and 0.79±0.04, real cases B are 0.92±0.04 and 0.85±0.07, respectively. The overlap fraction (OF) and overlap value (OV) of the phantoms are 0.95±0.01 and 0.93±0.04, respectively. Therefore, the proposed algorithm is highly reliable in most cases. In the second assessment, compared with Chan-Vese level set method, the Dice of the proposed algorithm in real cases A, real cases B and phantoms are 0.84±0.02, 0.86±0.03 and 0.92±0.02, respectively. The Dice of Chan-Vese level set in real cases A, real cases B and phantoms are 0.65±0.23, 0.69±0.14 and 0.76±0.14, respectively. The Dice performance of different methods on segmentation shows a highly significant impact (P<0.01). The results show that the proposed algorithm is more accurate than Chan-Vese level set method. In the third assessment, the Spearman's correlation coefficient between the segmented volumes and the corresponding ground truth volumes is ρ=0.929 (P=0.01). In summary, the proposed method can batch process ABUS images, segment lesions, calculate their volumes and visualize lesions to facilitate observation by radiologists and physicians.

Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma

To investigate the effect of image preprocessing, in respect to intensity inhomogeneity correction and noise filtering, on the robustness and reproducibility of the radiomics features extracted from the Glioblastoma (GBM) tumor in multimodal MR images (mMRI). In this study, for each patient 1461 radiomics features were extracted from GBM subregions (i.e., edema, necrosis, enhancement, and tumor) of mMRI (i.e., FLAIR, T1, T1C, and T2) volumes for five preprocessing combinations (in total 116 880 radiomics features). The robustness and reproducibility of the radiomics features were assessed under four comparisons: (a) Baseline versus modified bias field; (b) Baseline versus modified bias field followed by noise filtering; (c) Baseline versus modified noise, and (d) Baseline versus modified noise followed bias field correction. The concordance correlation coefficient (CCC), dynamic range (DR), and interclass correlation coefficient (ICC) were used as metrics. Shape features and subsequently, local binary pattern (LBP) filtered images were highly stable and reproducible against bias field correction and noise filtering in all measurements. In all MRI modalities, necrosis regions (NC: n ® ~449/1461, 30%) had the highest number of highly robust features, with CCC and DR >= 0.9, in comparison with edema (ED: n ® ~296/1461, 20%), enhanced (EN: n ® ~ 281/1461, 19%) and active‐tumor regions (TM: n ® ~254/1461, 17%). The necrosis regions (NC: n¯ ~ 449/1461, 30%) had a higher number of highly robust features (CCC and DR >= 0.9) than edema (ED: n¯ ~ 296/1461, 20%), enhanced (EN: n¯ ~ 281/1461, 19%) and active‐tumor (TM: n¯ ~ 254/1461, 17%) regions across all modalities. Furthermore, our results identified that the percentage of high reproducible features with ICC >= 0.9 after bias field correction (23.2%), and bias field correction followed by noise filtering (22.4%) were higher in contrast with noise smoothing and also noise smoothing follow by bias correction. These preliminary findings imply that preprocessing sequences can also have a significant impact on the robustness and reproducibility of mMRI‐based radiomics features and identification of generalizable and consistent preprocessing algorithms is a pivotal step before imposing radiomics biomarkers into the clinic for GBM patients.

Influence of Artifact Corrections on MRI Signal Intensity Ratios for Assessment of Gadolinium Brain Retention

Differences in brain signal intensity ratios (SIRs) of deep brain nuclei in T1-weighted (T1w) magnetic resonance images were reported as an indicator of gadolinium brain retention. Variable methods of image reconstruction and inhomogeneity correction for T1w images exist, which might affect the accuracy of SIRs. The aim of our prospective study was to investigate the effect of flow artifact compensation (FAC) and intensity inhomogeneity correction (IIC) on the dentate nucleus-to-pons and globus pallidus-to-thalamus SIRs in study participants who had previously received multiple doses of gadobutrol. This study included 76 participants who received five or more gadobutrol-enhanced scans between 2007 and 2017. A control group of 25 participants without gadolinium-based contrast agent application in their patient history was included for comparison. Unenhanced brain magnetic resonance imaging including two T1w spin-echo sequences with and without FAC was performed in all participants. Both sequences were reconstructed with and without IIC. Images were assessed for flow artifacts and SIRs were calculated. Using FAC, a lower proportion of participants had to be excluded from the final analysis of dentate nucleus-to-pons SIR due to flow artifacts (15% versus 46%, p < 0.001). Without IIC, a difference was found between the study and the control group for the dentate nucleus-to-pons ratio (p = 0.004), but not for the same sequence reconstructed with IIC (p = 0.29). For the globus pallidus-to-thalamus ratio, no difference was found between the study and control group. The application of an IIC algorithm has significant impact on brain nuclei SIRs for the assessment of gadolinium brain retention.

Automated Estimation of Acute Infarct Volume from Noncontrast Head CT Using Image Intensity Inhomogeneity Correction.

Identification of early ischemic changes (EIC) on noncontrast head CT scans performed within the first few hours of stroke onset may have important implications for subsequent treatment, though early stroke is poorly delimited on these studies. Lack of sharp lesion boundary delineation in early infarcts precludes manual volume measures, as well as measures using edge-detection or region-filling algorithms. We wished to test a hypothesis that image intensity inhomogeneity correction may provide a sensitive method for identifying the subtle regional hypodensity which is characteristic of early ischemic infarcts. A digital image analysis algorithm was developed using image intensity inhomogeneity correction (IIC) and intensity thresholding. Two different IIC algorithms (FSL and ITK) were compared. The method was evaluated using simulated infarcts and clinical cases. For synthetic infarcts, measured infarct volumes demonstrated strong correlation to the true lesion volume (for 20% decreased density “infarcts,” Pearson r = 0.998 for both algorithms); both algorithms demonstrated improved accuracy with increasing lesion size and decreasing lesion density. In clinical cases (41 acute infarcts in 30 patients), calculated infarct volumes using FSL IIC correlated with the ASPECTS scores (Pearson r = 0.680) and the admission NIHSS (Pearson r = 0.544). Calculated infarct volumes were highly correlated with the clinical decision to treat with IV-tPA. Image intensity inhomogeneity correction, when applied to noncontrast head CT, provides a tool for image analysis to aid in detection of EIC, as well as to evaluate and guide improvements in scan quality for optimal detection of EIC.

Retrospective correction of intensity inhomogeneity with sparsity constraints in transform-domain: Application to brain MRI

An effective retrospective correction method is introduced in this paper for intensity inhomogeneity which is an inherent artifact in MR images. Intensity inhomogeneity problem is formulated as the decomposition of acquired image into true image and bias field which are expected to have sparse approximation in suitable transform domains based on their known properties. Piecewise constant nature of the true image lends itself to have a sparse approximation in framelet domain. While spatially smooth property of the bias field supports a sparse representation in Fourier domain. The algorithm attains optimal results by seeking the sparsest solutions for the unknown variables in the search space through L1 norm minimization. The objective function associated with defined problem is convex and is efficiently solved by the linearized alternating direction method. Thus, the method estimates the optimal true image and bias field simultaneously in an L1 norm minimization framework by promoting sparsity of the solutions in suitable transform domains. Furthermore, the methodology doesn't require any preprocessing, any predefined specifications or parametric models that are critically controlled by user-defined parameters. The qualitative and quantitative validation of the proposed methodology in simulated and real human brain MR images demonstrates the efficacy and superiority in performance compared to some of the distinguished algorithms for intensity inhomogeneity correction.

A deep learning framework for efficient analysis of breast volume and fibroglandular tissue using MR data with strong artifacts.

The main purpose of this work is to develop, apply, and evaluate an efficient approach for breast density estimation in magnetic resonance imaging data, which contain strong artifacts including intensity inhomogeneities. We present a pipeline for breast density estimation, which consists of intensity inhomogeneity correction, breast volume segmentation, nipple extraction, and fibroglandular tissue segmentation. For the segmentation steps, a well-known deep learning architecture is employed. The average Dice coefficient for the breast parenchyma is [Formula: see text], which outperforms the classical state-of-the-art approach by a margin of [Formula: see text]. The proposed solution is accurate and highly efficient and has potential to be applied for big epidemiological data with thousands of participants.

Brain Tissue Segmentation and Bias Field Correction of MR Image Based on Spatially Coherent FCM with Nonlocal Constraints.

Influenced by poor radio frequency field uniformity and gradient-driven eddy currents, intensity inhomogeneity (or bias field) and noise appear in brain magnetic resonance (MR) image. However, some traditional fuzzy c-means clustering algorithms with local spatial constraints often cannot obtain satisfactory segmentation performance. Therefore, an objective function based on spatial coherence for brain MR image segmentation and intensity inhomogeneity correction simultaneously is constructed in this paper. First, a novel similarity measure including local neighboring information is designed to improve the separability of MR data in Gaussian kernel mapping space without image smoothing, and the similarity measure incorporates the spatial distance and grayscale difference between cluster centroid and its neighborhood pixels. Second, the objective function with an adaptive nonlocal spatial regularization term is drawn upon to compensate the drawback of the local spatial information. Meanwhile, bias field information is also embedded into the similarity measure of clustering algorithm. From the comparison between the proposed algorithm and the state-of-the-art methods, our model is more robust to noise in the brain magnetic resonance image, and the bias field is also effectively estimated.

Enhanced Homomorphic Unsharp Masking method for intensity inhomogeneity correction in brain MR images

ABSTRACTMRI is a powerful diagnostic tool providing excellent soft tissue contrast and high spatial resolution. However, imperfections arising in the radio frequency field and scanner-related intensity artefacts in MRI produce intensity inhomogeneity. These intensity variations pose major challenges for subsequent image processing and analysis techniques. Therefore, a robust means of correcting intensity inhomogeneity is essential for any accurate and efficient processing technique. Homomorphic filtering based techniques are commonly used for intensity correction in brain MR images, but the halo effect induced by these methods limit their performance in the presence of a tumour. To mitigate the halo effect, a novel Enhanced Homomorphic Unsharp Masking (EHUM) intensity correction algorithm is proposed in this paper. The proposed method first determines the ROI to overcome the halo effect between foreground and background regions. Then, the intensity correction is carried out using homomorphic filtering and linear grey scale mapping. The quantitative and qualitative evaluation results show the efficiency of the proposed method in overcoming the intensity inhomogeneity in both normal and abnormal brain MR images.

Context Dependent Fuzzy Associated Statistical Model for Intensity Inhomogeneity Correction From Magnetic Resonance Images.

In this paper, a novel context-dependent fuzzy set associated statistical model-based intensity inhomogeneity correction technique for magnetic resonance image (MRI) is proposed. The observed MRI is considered to be affected by intensity inhomogeneity and it is assumed to be a multiplicative quantity. In the proposed scheme the intensity inhomogeneity correction and MRI segmentation is considered as a combined task. The maximum a posteriori probability (MAP) estimation principle is explored to solve this problem. A fuzzy set associated Gibbs’ Markov random field (MRF) is considered to model the spatio-contextual information of an MRI. It is observed that the MAP estimate of the MRF model does not yield good results with any local searching strategy, as it gets trapped to local optimum. Hence, we have exploited the advantage of variable neighborhood searching (VNS)-based iterative global convergence criterion for MRF-MAP estimation. The effectiveness of the proposed scheme is established by testing it on different MRIs. Three performance evaluation measures are considered to evaluate the performance of the proposed scheme against existing state-of-the-art techniques. The simulation results establish the effectiveness of the proposed technique.

Is Intensity Inhomogeneity Correction Useful for Classification of Breast Cancer in Sonograms Using Deep Neural Network?

The sonogram is currently an effective cancer screening and diagnosis way due to the convenience and harmlessness in humans. Traditionally, lesion boundary segmentation is first adopted and then classification is conducted, to reach the judgment of benign or malignant tumor. In addition, sonograms often contain much speckle noise and intensity inhomogeneity. This study proposes a novel benign or malignant tumor classification system, which comprises intensity inhomogeneity correction and stacked denoising autoencoder (SDAE), and it is suitable for small-size dataset. A classifier is established by extracting features in the multilayer training of SDAE; automatic analysis of imaging features by the deep learning algorithm is applied on image classification, thus allowing the system to have high efficiency and robust distinguishing. In this study, two kinds of dataset (private data and public data) are used for deep learning models training. For each dataset, two groups of test images are compared: the original images and the images after intensity inhomogeneity correction, respectively. The results show that when deep learning algorithm is applied on the sonograms after intensity inhomogeneity correction, there is a significant increase of the tumor distinguishing accuracy. This study demonstrated that it is important to use preprocessing to highlight the image features and further give these features for deep learning models. In this way, the classification accuracy will be better to just use the original images for deep learning.

A Multi-Scale Framework for Bias Field Estimation in MRI Brain Images

Intensity inhomogeneity is an artifact in MR brain images and causes intensity variation of same tissues on the basis of location of the tissue within the image. It is crucial to minimize this phenomenon to improve the accuracy of the computer-aided diagnosis. Unlike the several methods proposed in the past to minimize intensity inhomogeneity, this proposed method uses a pyramidal decomposition strategy to estimate the bias field in MR brain images. The bias field estimated from the proposed multi-scale framework can be effectively used for intensity inhomogeneity correction of the acquired MR data. The proposed methodology has been tested on simulated database and quantitative analyses in terms of coefficient of variation in grey matter and white matter tissue regions separately and combined coefficient of joint variation are assessed. The qualitative and quantitative analyses on the corrected data indicate that the method is effective for intensity inhomogeneity on brain MR images.

Original intensity preserved inhomogeneity correction and segmentation for liver magnetic resonance imaging

Abstract Intensity inhomogeneity (IIH), also named as bias field, is an undesired phenomenon of liver magnetic resonance imaging (MRI) which severely affects the quantitative analysis of medical image and decreases the performance of subsequent computer aided diagnosis (CAD) of liver cirrhosis. Many algorithms have been proposed to reduce or eliminate IIH of MRI, and some notable achievements for brain MRI have been obtained. However, IIH correction of abdominal MRI receives less attention and is challenging because of the irregular structure and the wide intensity range of different tissues. In this paper, an automatic method based on the global intensity, the local intensity and the spatial continuity information is presented for reducing IIH of liver MRI. What should be noted is that the gray level should be preserved after correction since it is important for subsequent quantitative image analysis. Therefore, a constraint term is introduced based on the information of bias field intensity for appropriate IIH correction. In addition, the objective function introduces a fuzzy membership mask to remove the background noise and avoid misclassification. Our method is successfully applied to the clinical liver MRI and acquires desirable results. Compared with other approaches, our method obtains the best segmentation with Jaccard similarity (JS) = 0.88 ± 0.06, Dice index (DI) = 0.94 ± 0.03, and accuracy (ACC) = 0.99 ± 0.01.

3D Deep Learning for Automatic Brain MR Tumor Segmentation with T-Spline Intensity Inhomogeneity Correction

Automatic segmentation of brain tumor data is a herculean task for medical applications, particularly in cancer diagnosis. This paper emulates some challenging issues such as noise sensitivity, partial volume averaging, intensity inhomogeneity, inter-slice intensity variations, and intensity non-standardization. This paper intends a novel N3T-spline intensity inhomogeneity correction for bias field correction and the three dimension convolutional neural network (3DCNN) for automatic segmentation. The proposed work consists of four stages (i) pre-processing, (ii) feature extraction (iii) automatic segmentation and (iv) post-processing. In the pre-processing step, novel nonparametric non-uniformity normalization (N3) based T-spline approach is proposed to correct the bias field distortion, which recedes the noises and intensity variations. The extended gray level co-occurrence matrix (EGLCM) is a feature extraction technique, from which the texture patches more suitable for brain tumor segmentation can be extracted. The proposed 3DCNN automatically segments the brain tumor and divides the discrete abnormal tissues from the raw data and EGLCM features. Finally, a simple threshold scheme is adapted on the segmented result to correct the false labels and eliminate the 3D connected small regions. The simulation results in the proposed segmentation procedure could acquire competitive performance as compared with the existing procedure for the BRATS 2015 dataset.

Application of Color Transformation Techniques in Pediatric Spinal Cord MR Images: Typically Developing and Spinal Cord Injury Population.

The purpose of this study was to evaluate an improved and reliable visualization method for pediatric spinal cord MR images in healthy subjects and patients with spinal cord injury (SCI). A total of 15 pediatric volunteers (10 healthy subjects and 5 subjects with cervical SCI) with a mean age of 11.41years (range 8-16years) were recruited and scanned using a 3.0T Siemens Verio MR scanner. T2-weighted axial images were acquired covering entire cervical spinal cord level C1 to C7. These gray-scale images were then converted to color images by using five different techniques including hue-saturation-value (HSV), rainbow, red-green-blue (RGB), and two enhanced RGB techniques using automated contrast stretching and intensity inhomogeneity correction. Performance of these techniques was scored visually by two neuroradiologists within three selected cervical spinal cord intervertebral disk levels (C2-C3, C4-C5, and C6-C7) and quantified using signal to noise ratio (SNR) and contrast to noise ratio (CNR). Qualitative and quantitative evaluation of the color images shows consistent improvement across all the healthy and SCI subjects over conventional gray-scale T2-weighted gradient echo (GRE) images. Inter-observer reliability test showed moderate to strong intra-class correlation (ICC) coefficients in the proposed techniques (ICC > 0.73). The results suggest that the color images could be used for quantification and enhanced visualization of the spinal cord structures in addition to the conventional gray-scale images. This would immensely help towards improved delineation of the gray/white and CSF structures and further aid towards accurate manual or automatic drawings of region of interests (ROIs).

Segmentation of MR Images of the Brain to Detect WM, GM, and CSF Tissues in the Presence of Noise and Intensity Inhomogeneity

ABSTRACTSegmentation of brain MR images for the detection of various healthy brain tissues such as white matter, gray matter, and cerebrospinal fluid is of immense interest to detect and to diagnose different brain-related disorders at the primitive level. MR image segmentation becomes a difficult task owing to the presence of intensity inhomogeneity (IIH), noise, partial volume effects, and intrinsic nature of the MR images. This paper proposes an efficient, region-based, energy minimization technique named as anisotropic multiplicative intrinsic component optimization (AMICO) to segment the brain image in the presence of IIH and noise and to detect different healthy brain tissues. The proposed algorithm utilizes a powerful anisotropic diffusion filter to denoise the image. The MICO algorithm segment the denoised image after correcting IIH. In the proposed technique, MR brain image is decomposed into two multiplicative and intrinsic components, such as the true image component and the bias field component. Brain tissue physical properties are represented by the component of true image and the IIH is characterized by the bias field component. Optimization of these two multiplicative and intrinsic components by employing the proposed effective energy minimization process, result in IIH correction and tissue segmentation simultaneously. The pursuance of the proposed technique is compared with some other existing techniques using the parameters, dice similarity coefficient, sensitivity, specificity, and segmentation accuracy. The results validated the excellent performance of the AMICO in detecting various brain tissues consisting of various levels of IIH and noise.