Segmentation Of Abnormal Tissues Research Articles

Texture Estimation for Abnormal Tissue Segmentation in Brain MRI.

This chapter discusses multifractal texture estimation and characterization of brain lesions (necrosis, edema, enhanced tumor, nonenhanced tumor, etc.) in magnetic resonance (MR) images. This work formulates the complex texture of tumor in MR images using a stochastic model known as multifractional Brownian motion (mBm). Mathematical derivations of the mBm model and corresponding algorithm to extract the spatially varying multifractal texture feature are discussed. Extracted multifractal texture feature is fused with other effective features to enhance the tissue characteristics. Segmentation of the tissues is performed using a feature-based classification method. The efficacy of the mBm texture feature in segmenting different abnormal tissues is demonstrated using a large-scale publicly available clinical dataset. Experimental results and performance of the methods confirm the efficacy of the proposed technique in an automatic segmentation of abnormal tissues in multimodal (T1, T2, Flair, and T1contrast) brain MRIs.

Enhancing U-Net with Spatial-Channel Attention Gate for Abnormal Tissue Segmentation in Medical Imaging

In recent years, deep learning has dominated medical image segmentation. Encoder-decoder architectures, such as U-Net, can be used in state-of-the-art models with powerful designs that are achieved by implementing skip connections that propagate local information from an encoder path to a decoder path to retrieve detailed spatial information lost by pooling operations. Despite their effectiveness for segmentation, these naïve skip connections still have some disadvantages. First, multi-scale skip connections tend to use unnecessary information and computational sources, where likable low-level encoder features are repeatedly used at multiple scales. Second, the contextual information of the low-level encoder feature is insufficient, leading to poor performance for pixel-wise recognition when concatenating with the corresponding high-level decoder feature. In this study, we propose a novel spatial-channel attention gate that addresses the limitations of plain skip connections. This can be easily integrated into an encoder-decoder network to effectively improve the performance of the image segmentation task. Comprehensive results reveal that our spatial-channel attention gate remarkably enhances the segmentation capability of the U-Net architecture with a minimal computational overhead added. The experimental results show that our proposed method outperforms the conventional deep networks in term of Dice score, which achieves 71.72%.

A reliable ensemble-based classification framework for glioma brain tumor segmentation

Glioma is one of the most frequent primary brain tumors in adults that arise from glial cells. Automatic and accurate segmentation of glioma is critical for detecting all parts of tumor and its surrounding tissues in cancer detection and surgical planning. In this paper, we present a reliable classification framework for detection and segmentation of abnormal tissues including brain glioma tumor portions such as edemas and tumor core. This framework learns weighted features extracted from the 3D cubic neighborhoods regarding to gray-level differences that indicate the spatial relationships among voxels. In addition to intensity values in each slice, we consider sets of three consecutive slices to extract information from 3D neighbors. Classification procedure is defined based on combination of support vector machines regarding to an ensemble learning method. In order to regularize and improve the output of the classifier framework, we design a post-process procedure based on statistical concepts. The proposed framework is trained and tested with BRATS datasets, and comparative analysis is implemented. Experimental results indicate competitive performance compared to the state-of-the-art methods. The achieved accuracy is characterized by the overall mean Dice index of 88%.

MMTDNN: Multi-view Massive Training Deep Neural Network for Segmentation and Detection of Abnormal Tissues in Medical Images

Purpose: Automated segmentation of abnormal tissues in medical images is considered as an essential part of those computer-aided detection and diagnosis systems which analyze medical images. However, automated segmentation of abnormalities is a challenging task due to the limitations of imaging technologies and complex structure of abnormalities, including low contrast between normal and abnormal tissues, shape diversity, appearance inhomogeneity, and the vague boundaries of abnormalities. Therefore, more intelligent segmentation techniques are required to tackle these challenges. Materials and Methods: In this study, a method, which is called MMTDNN, is proposed to segment and detect medical image abnormalities. MMTDNN, as a multi-view learning machine, utilizes convolutional neural networks in a massive training strategy. Moreover, the proposed method has four phases of preprocessing, view generation, pixel-level segmentation, and post-processing. The International Symposium on Biomedical Imaging (ISBI)-2016 dataset is used for the evaluation of the proposed method. Results: The performance of the proposed method has been evaluated on the task of skin lesion segmentation as one of the challenging applications of abnormal tissue segmentation. Both qualitative and quantitative results demonstrate outstanding performance. Meanwhile, the accuracy of 0.973, the Jaccard index of 0.876, and the Dice similarity coefficient of 0.931 have been achieved. Conclusion: In conclusion, the experimental result demonstrates that the proposed method outperforms stateof-the-art methods of skin lesion segmentation.

Feature-Guided Deep Radiomics for Glioblastoma Patient Survival Prediction.

Glioblastoma is recognized as World Health Organization (WHO) grade IV glioma with an aggressive growth pattern. The current clinical practice in diagnosis and prognosis of Glioblastoma using MRI involves multiple steps including manual tumor sizing. Accurate identification and segmentation of multiple abnormal tissues within tumor volume in MRI is essential for precise survival prediction. Manual tumor and abnormal tissue detection and sizing are tedious, and subject to inter-observer variability. Consequently, this work proposes a fully automated MRI-based glioblastoma and abnormal tissue segmentation, and survival prediction framework. The framework includes radiomics feature-guided deep neural network methods for tumor tissue segmentation; followed by survival regression and classification using these abnormal tumor tissue segments and other relevant clinical features. The proposed multiple abnormal tumor tissue segmentation step effectively fuses feature-based and feature-guided deep radiomics information in structural MRI. The survival prediction step includes two representative survival prediction pipelines that combine different feature selection and regression approaches. The framework is evaluated using two recent widely used benchmark datasets from Brain Tumor Segmentation (BraTS) global challenges in 2017 and 2018. The best overall survival pipeline in the proposed framework achieves leave-one-out cross-validation (LOOCV) accuracy of 0.73 for training datasets and 0.68 for validation datasets, respectively. These training and validation accuracies for tumor patient survival prediction are among the highest reported in literature. Finally, a critical analysis of radiomics features and efficacy of these features in segmentation and survival prediction performance is presented as lessons learned.

Multi-view representation learning for segmentation of abnormal tissues in medical images applied to multiple sclerosis lesion delineation

Automated segmentation of abnormal tissues in medical images assists both physicians and medical researchers in the process of diseases diagnostic and research activities respectively. Intelligent techniques of automated segmentation are gaining more popularity in contrast to non-intelligent ones. In these techniques, quality representation of pixel/voxels by considering multiple natural and artificial views which exist in medical images increases segmentation accuracy. The proposed method for segmentation of abnormal tissues in medical images is based on multi-view representation with six phases of pre-processing, view generation, representation generation, classification, post-processing, and evaluation. In the representation phase, raw data of medical images are represented based on the modes of variation or clusters exist in the original multi-view feature space. Quantitative results of the experiment demonstrate representations generated via the proposed method are effective especially when the Random Forest classifier is employed. DSC of 0.72 for a subject shows that the results are promising. This study shows cluster based representation of raw pixel/voxels of multiple views are effective in supervised segmentation of abnormal tissues.

Automated Segmentation of Abnormal Tissues in Medical Images.

Nowadays, medical image modalities are almost available everywhere. These modalities are bases of diagnosis of various diseases sensitive to specific tissue type. Usually physicians look for abnormalities in these modalities in diagnostic procedures. Count and volume of abnormalities are very important for optimal treatment of patients. Segmentation is a preliminary step for these measurements and also further analysis. Manual segmentation of abnormalities is cumbersome, error prone, and subjective. As a result, automated segmentation of abnormal tissue is a need. In this study, representative techniques for segmentation of abnormal tissues are reviewed. Main focus is on the segmentation of multiple sclerosis lesions, breast cancer masses, lung nodules, and skin lesions. As experimental results demonstrate, the methods based on deep learning techniques perform better than other methods that are usually based on handy feature engineering techniques. Finally, the most common measures to evaluate automated abnormal tissue segmentation methods are reported

Quantitative MR Image Analysis for Brian Tumor.

This paper presents an integrated quantitative MR image analysis framework to include all necessary steps such as MRI inhomogeneity correction, feature extraction, multiclass feature selection and multimodality abnormal brain tissue segmentation respectively. We first obtain mathematical algorithm to compute a novel Generalized multifractional Brownian motion (GmBm) texture feature. We then demonstrate efficacy of multiple multiresolution texture features including regular fractal dimension (FD) texture, and stochastic texture such as multifractional Brownian motion (mBm) and GmBm features for robust tumor and other abnormal tissue segmentation in brain MRI. We evaluate these texture and associated intensity features to effectively delineate multiple abnormal tissues within and around the tumor core, and stroke lesions using large scale public and private datasets.

Segmentation of hyper-acute cerebral infarct based on random forest and sparse coding from diffusion weighted imaging.

Irreversible infarcts are critical for the assessment of potential risk and benefit pertaining to thrombolysis in hyper-acute ischemic stroke. It is a challenging work to segment infarct at hyper-acute stage due to the substantial variability. A general abnormal tissue segmentation method is proposed and applied to segment hyper-acute ischemic infarct in this paper. Multiple features are designed to train a random forest classifier for voxel classification. Sparse coding based bag-of-features is adopted to train a region classifier for infarct region recognition. The proposed method has been validated on 98 consecutive patients recruited within 6 hours from onset and achieved a higher Dice coefficient 0.774±0.117 than the other two existing methods (0.755±0.118; 0.597±0.204). It could provide a potential tool to quantify infarcts from diffusion weighted imaging at hyper-acute stage with accuracy to assist the decision making especially for thrombolytic therapy.

Image Segmentation Algorithms on MR Brain Images

Magnetic Resonance Image plays a major role in medical diagnostics. Image segmentation is done to divide an image into meaningful structures. Image segmentation is the initial step in image analysis and pattern recognition. It becomes more important while dealing with medical images where pre-surgery and post-surgery decisions are required for the purpose of initiating and speeding up the recovery process. Manual segmentation of abnormal tissues cannot be compared with modern day's high speed computing machines. Segmentation is done to extract the features of the image that are used for analysis, interpretation, and understanding of images. Accuracy of the extracted features decides the accuracy of the algorithm. Selection of a suitable algorithm is highly based on the application. This paper highlights the various image segmentation algorithms, used in medical images.