A novel Markov random field model based on region adjacency graph for T1 magnetic resonance imaging brain segmentation

Tissue segmentation in magnetic resonance brain scans is the most critical task in different aspects of brain analysis. Because manual segmentation of brain magnetic resonance imaging (MRI) images is a time‐consuming and labor‐intensive procedure, automatic image segmentation is widely used for this purpose. As Markov Random Field (MRF) model provides a powerful tool for segmentation of images with a high level of artifacts, it has been considered as a superior method. But because of the high computational cost of MRF, it is not appropriate for online processing. This article has proposed a novel method based on a proper combination of MRF model and watershed algorithm in order to alleviate the MRF's drawbacks. Results illustrate that the proposed method has a good ability in MRI image segmentation, and also decreases the computational time effectively, which is a valuable improvement in the online applications. © 2017 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 27, 78–88, 2017     

Bone segmentation and 3D visualization of CT images for traumatic pelvic injuries

Pelvic bone segmentation is a vital step in analyzing pelvic CT images, which assists physicians with diagnostic decision making in cases of traumatic pelvic injuries. Due to the limited resolution of the original CT images and the complexity of pelvic structures and their possible fractures, automatic pelvic bone segmentation in multiple CT slices is very difficult. In this study, an automatic pelvic bone segmentation approach is proposed using the combination of anatomical knowledge and computational techniques. It is developed for solving the problem of accurate and efficient bone segmentation using multiple consecutive pelvic CT slices obtained from each patient. Our proposed segmentation method is able to handle variation of bone shapes between slices there by making it less susceptible to inter‐personal variability between different patients' data. Moreover, the designed training models are validated using a cross‐validation process to demonstrate the effectiveness. The algorithm's capability is tested on a set of 20 CT data sets. Successful segmentation results and quantitative evaluations are present to demonstrate the effectiveness and robustness of proposed algorithm, well suited for pelvic bone segmentation purposes.     

Automated brain tumour segmentation techniques— A review

Automatic segmentation of brain tumour is the process of separating abnormal tissues from normal tissues, such as white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). The process of segmentation is still challenging due to the diversity of shape, location, and size of the tumour segmentation. The metabolic process, psychological process, and detailed information of the images, are obtained using positron emission tomography (PET) image, Computer Tomography (CT) image and Magnetic Resonance Image (MRI). Multimodal imaging techniques (such as PET/CT and PET/MRI) that combine the information from many imaging techniques contribute more for accurate brain tumour segmentation. In this article, a comprehensive overview of recent automatic brain tumour segmentation techniques of MRI, PET, CT, and multimodal imaging techniques has been provided. The methods, techniques, their working principle, advantages, their limitations, and their future challenges are discussed in this article. © 2017 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 27, 66–77, 2017     

Segmentation for brain magnetic resonance images using dual‐tree complex wavelet transform and spatial constrained self‐organizing tree map

In brain MR images, the noise and low‐contrast significantly deteriorate the segmentation results. In this paper, we introduce a novel application of dual‐tree complex wavelet transform (DT‐CWT), and propose an automatic unsupervised segmentation method integrating DT‐CWT with self‐organizing map for brain MR images. First, a multidimensional feature vector is constructed based on the intensity, low‐frequency subband of DT‐CWT, and spatial position information. Then, a spatial constrained self‐organizing tree map (SCSOTM) is presented as the segmentation system. It adaptively captures the complicated spatial layout of the individual tissues, and overcomes the problem of overlapping gray‐scale intensities for different tissues. SCSOTM applies a dual‐thresholding method for automatic growing of the tree map, which uses the information from the high‐frequency subbands of DT‐CWT. The proposed method is validated by extensive experiments using both simulated and real T1‐weighted MR images, and compared with the state‐of‐the‐art algorithms. © 2014 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 24, 208–214, 2014     

基于U-net的水位线检测

提出一种基于U-net水位线自动分割的新方法,并通过多种场景进行验证。首先标记出原始图像中的水和背景并对其灰度化;然后利用处理后的图像和原始图像制作出数据集,把数据集作为输入利用U-net对图像进行分割;最后将所有分割出来的图像进行边缘提取得到水位线。实验结果表明:U-net水位自动分割可以精确地标记出水位线,同时解决了在水位测量过程中图像背景所带来的影响,分割效果明显优于其它分割方法,识别率达到96%以上。     

Automatic Segmentation of Liver from Abdominal Computed Tomography Images Using Energy Feature

Liver Segmentation is one of the challenging tasks in detecting and classifying liver tumors from Computed Tomography (CT) images. The segmentation of hepatic organ is more intricate task, owing to the fact that it possesses a sizeable quantum of vascularization. This paper proposes an algorithm for automatic seed point selection using energy feature for use in level set algorithm for segmentation of liver region in CT scans. The effectiveness of the method can be determined when used in a model to classify the liver CT images as tumorous or not. This involves segmentation of the region of interest (ROI) from the segmented liver, extraction of the shape and texture features from the segmented ROI and classification of the ROIs as tumorous or not by using a classifier based on the extracted features. In this work, the proposed seed point selection technique has been used in level set algorithm for segmentation of liver region in CT scans and the ROIs have been extracted using Fuzzy C Means clustering (FCM) which is one of the algorithms to segment the images. The dataset used in this method has been collected from various repositories and scan centers. The outcome of this proposed segmentation model has reduced the area overlap error that could offer the intended accuracy and consistency. It gives better results when compared with other existing algorithms. Fast execution in short span of time is another advantage of this method which in turns helps the radiologist to ascertain the abnormalities instantly.     

Fetal brain extraction from magnetic resonance image (MRI) of human fetus

Study of a fetus is a rapidly growing field of research and it requires fetal brain segmentation. Automatic segmentation of the fetal brain from magnetic resonance imaging (MRI) is challenging, due to the highly variable size and shape of the developing brain, possible brain structure abnormalities, movement of the fetus and a poor resolution of fetal MRI scans. This is in contrast to adult brain segmentation, where the brain structure is stable and several established methods exist. This paper presents a fully automatic segmentation method to segment the fetal brain portion from MRI. The segmentation pipeline developed in this study includes contrast enhancement, region growing and hole filling. Twenty-five volumes of retrospective fetal MRI are used in this work. Experimental results show that this method can successfully segment the fetal brain from magnetic resonance images which are comparable to that of a semi-automatic method.     

Fully automatic method for segmentation of brain tumor from multimodal magnetic resonance images using wavelet transformation and clustering technique

Fully automatic brain tumor segmentation is one of the critical tasks in magnetic resonance imaging (MRI) images. This proposed work is aimed to develop an automatic method for brain tumor segmentation process by wavelet transformation and clustering technique. The proposed method using discrete wavelet transform (DWT) for pre‐ and post‐processing, fuzzy c‐means (FCM) for brain tissues segmentation. Initially, MRI images are preprocessed by DWT to sharpen the images and enhance the tumor region. It assists to quicken the FCM clustering technique and classified into four major classes: gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), and background (BG). Then check the abnormality detection using Fuzzy symmetric measure for GM, WM, and CSF classes. Finally, DWT method is applied in segmented abnormal region of images respectively and extracts the tumor portion. The proposed method used 30 multimodal MRI training datasets from BraTS2012 database. Several quantitative measures were calculated and compared with the existing. The proposed method yielded the mean value of similarity index as 0.73 for complete tumor, 0.53 for core tumor, and 0.35 for enhancing tumor. The proposed method gives better results than the existing challenging methods over the publicly available training dataset from MICCAI multimodal brain tumor segmentation challenge and a minimum processing time for tumor segmentation. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 305–314, 2016     

Enhancing breast pectoral muscle segmentation performance by using skip connections in fully convolutional network

The precise detection and segmentation of pectoral muscle areas in mediolateral oblique (MLO) views is an essential step in the development of a computer-aided diagnosis system to access breast malignant lesions or parenchyma. The goal of this article is to develop a robust and fully automatic algorithm for pectoral muscle segmentation from mammography images. This paper presents an image enhancement approach that improves the quality of mammogram scans and a convolutional neural network-based fully convolutional network architecture enhanced with residual connections for automatic segmentation of the pectoral muscle from the MLO views of a digital mammogram. For this purpose, the model is tested and trained on three different mammogram datasets named MIAS, INBREAST, and DDSM. The ground truth labels of the pectoral muscle were identified under the supervision of experienced radiologists. For training and testing, 10-fold cross-validation was used. The proposed model was compared with baseline U-Net-based architecture. Finally, we used a postprocessing step to find the actual boundary of the pectoral muscle. Our presented architecture generated a mean Intersection over Union (IoU) of 97%, dice similarity coefficient (DSC) of 96% and 98% accuracy on testing data. The proposed architecture for pectoral muscle segmentation from the MLO views of mammogram images with high accuracy and dice score can be quickly merged with the breast tumor segmentation problem.     

A comprehensive review: Segmentation of MRI images—brain tumor

Segmentation of tumors in human brain aims to classify different abnormal tissues (necrotic core, edema, active cells) from normal tissues (cerebrospinal fluid, gray matter, white matter) of the brain. In existence, detection of abnormal tissues is easy for studying brain tumor, but reproducibility, characterization of abnormalities and accuracy are complicated in the process of segmentation. The magnetic resonance imaging (MRI)‐based segmentation of tumors in brain images is more enhancing and attracting in current years of research studies. It is due to non‐invasive examination and good contrast prone to soft tissues of images obtained from MRI modality. Medical approval of different segmentation techniques depends on the benchmark and simplicity of the method. This article incorporates both fully‐automatic and semi‐automatic methods for segmentation. The outlook study of this article is to provide the summary of most significant segmentation methods of tumors in brain using MRI. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 295–304, 2016     

MRI brain segmentation in combination of clustering methods with Markov random field

Medical image segmentation is a preliminary stage of inclusion in identification tools. The correct segmentation of brain Magnetic Resonance Imaging (MRI) images is crucial for an accurate detection of the disease diagnosis. Due to in‐homogeneity, low distinction and noise the segmentation of the brain MRI images is treated as the most challenging task. In this article, we proposed hybrid segmentation, by combining the clustering methods with Hidden Markov Random Field (HMRF) technique. This aims to decrease the computational load and improves the runtime of segmentation method, as MRF methodology is used in post‐processing the images. Its evaluation has performed on real imaging data, resulting in the classification of brain tissues with dice similarity metric. These results indicate the improvement in performance of the proposed method with various noise levels, compared with existing algorithms. In implementation, selection of clustering method provides better results in the segmentation of MRI brain images.     

Research on the magnetic resonance imaging brain tumor segmentation algorithm based on DO-UNet

With the social and economic development and the improvement of people's living standards, smart medical care is booming, and medical image processing is becoming more and more popular in research, of which brain tumor segmentation is an important branch of medical image processing. However, the manual segmentation method of brain tumors requires a lot of time and effort from the doctor and has a great impact on the treatment of patients. In order to solve this problem, we propose a DO-UNet model for magnetic resonance imaging brain tumor image segmentation based on attention mechanism and multi-scale feature fusion to realize fully automatic segmentation of brain tumors. Firstly, we replace the convolution blocks in the original U-Net model with the residual modules to prevent the gradient disappearing. Secondly, the multi-scale feature fusion is added to the skip connection of U-Net to fuse the low-level features and high-level features more effectively. In addition, in the decoding stage, we add an attention mechanism to increase the weight of effective information and avoid information redundancy. Finally, we replace the traditional convolution in the model with DO-Conv to speed up the network training and improve the segmentation accuracy. In order to evaluate the model, we used the BraTS2018, BraTS2019, and BraTS2020 datasets to train the improved model and validate it online, respectively. Experimental results show that the DO-UNet model can effectively improve the accuracy of brain tumor segmentation and has good segmentation performance.     

LSS-net: 3-dimensional segmentation of the spinal canal for the diagnosis of lumbar spinal stenosis

Lumbar Spinal Stenosis (LSS) is one of the main causes of chronic low back pain. Chronic low back pain not only reduces the quality of life of people but also can be an important expense item in the country's economy due to the inability of the person to participate in working life and treatment costs. As in other diseases, rapid diagnosis and early treatment of LSS significantly affect the quality of life of the person. Magnetic Resonance (MR) imaging is one of the methods used to diagnose LSS. Diagnosis by interpreting MR images requires serious expertise, and it has been frequently studied by academics in recent years because it is a system that assists the doctor with an objective approach. This field of study is machine learning, which we can call the sub-branch of Artificial Intelligence. Deep learning-based machine learning is very successful in processing biomedical images such as MR. In this study, a model that performs 3-dimensional automatic segmentation on T2 sequence Lumbar MR Images is proposed for the diagnosis of LSS. This 3D LSS segmentation study, according to our knowledge, has the feature of being the first in its field and will be an important resource for those who work in this field. In addition, with the proposed model, parts that cannot be fully opened in LSS surgical operations, especially in the nerve roots, can be fully determined beforehand which will ensure that the patient's complaints are completely eliminated after the operation. In MR images, a total of 6 classes were created and segmentation was carried out, including the spinal disc, canal, thecal sac, posterior element, and other regions and background in the image, which are important for LSS. To measure the success of segmentation, the Intersection over Union (IoU) metric was calculated for each class. 3D segmentation success for the validation set in the dataset; Background (IoU = 0.83), Canal (IoU = 0.61), Disc (IoU = 0.91), Other (IoU = 0.97), Posterior element (IoU = 0.82), and Thecal Sac (IoU = 0.81). The 3D automatic segmentation success rates obtained are quite high and show that a Computer Aided Diagnosis system can be created in LSS diagnosis.     

Brain tumor severity analysis using modified multi‐texton histogram and hybrid kernel SVM

Magnetic resonance image (MRI) segmentation refers to a process of assigning labels to set of pixels or multiple regions. It plays a major role in the field of biomedical applications as it is widely used by the radiologists to segment the medical images input into meaningful regions. In recent years, various brain tumor detection techniques are presented in the literature. In this article, we have developed an approach to brain tumor detection and severity analysis is done using the various measures. The proposed approach comprises of preprocessing, segmentation, feature extraction, and classification. In preprocessing steps, we need to perform skull stripping and then, anisotropic filtering is applied to make image suitable for extracting features. In feature extraction, we have modified the multi‐texton histogram (MTH) technique to improve the feature extraction. In the classification stage, the hybrid kernel is designed and applied to training of support vector machine to perform automatic detection of tumor region in MRI images. For comparison analysis, our proposed approach is compared with the existing works using K‐cross fold validation method. From the results, we can conclude that the modified multi‐texton histogram with non‐linear kernels has shown the accuracy of 86% but the MTH with non‐linear kernels shows the accuracy of 83.8%.     

A fast and robust segmentation of magnetic resonance brain images using a combination of the pyramidal approach and level set method

We propose in this article an approach to optimize the processing time and to improve the quality of brain magnetic resonance images segmentation. Level set method (LSM) was adopted with a periodic reinitialization process to prevent the LS function from being too steep or too flat near the interface. Although it is used to maintain the stability of the interface evolution and gives interesting results, it requires a longer processing time. To overcome this disadvantage and reduce the processing time, we propose a hybridization with a regular Gaussian pyramid, which reduces the resolution of the initial image and prevents the possibility of local minima. To compare the different segmentation algorithms, we used six types of quality measurements: specificity, sensitivity, Dice similarity, the Jaccard index, and the correctly and incorrectly marked pixels. A comparison between the results obtained by LSM, LSM with reinitialization, the approach of Barman et al., An International Journal 1 (2011), particle swarm optimization based on the Chan and Vese model (Mandal et al., Engineering Applications of Artificial Intelligence 35 (2014), 199‐214) and by our hybrid approach reveals a clear efficiency of our hybridization strategy. The processing time was significantly reduced, and the quality of segmentation was improved. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 243–253, 2016     

Enhancing level set brain tumor segmentation using fuzzy shape prior information and deep learning

Magnetic resonance imaging (MRI) brain tumor segmentation is a crucial task for clinical treatment. However, it is challenging owing to variations in type, size, and location of tumors. In addition, anatomical variation in individuals, intensity non-uniformity, and noises adversely affect brain tumor segmentation. To address these challenges, an automatic region-based brain tumor segmentation approach is presented in this paper which combines fuzzy shape prior term and deep learning. We define a new energy function in which an Adaptively Regularized Kernel-Based Fuzzy C-Means (ARKFCM) Clustering algorithm is utilized for inferring the shape of the tumor to be embedded into the level set method. In this way, some shortcomings of traditional level set methods such as contour leakage and shrinkage have been eliminated. Moreover, a fully automated method is achieved by using U-Net to obtain the initial contour, reducing sensitivity to initial contour selection. The proposed method is validated on the BraTS 2017 benchmark dataset for brain tumor segmentation. Average values of Dice, Jaccard, Sensitivity and specificity are 0.93 ± 0.03, 0.86 ± 0.06, 0.95 ± 0.04, and 0.99 ± 0.003, respectively. Experimental results indicate that the proposed method outperforms the other state-of-the-art methods in brain tumor segmentation.     

Boundary-based object segmentation in X-ray imaging using spiral search

In this paper, we propose a boundary-based method for object segmentation by using only the edge information. The proposed method is especially applied to object segmentation of dangerous firearms and knives in the X-ray images of baggage, where no colour or texture features are available to describe the target object. The Canny edge detector is used to extract edge points from the X-ray image. These edges have cluttered backgrounds and may be discontinuous. A fast spiral search is proposed to connect neighbouring points, either continuous or discontinuous, and form closed contours for individual objects. The distance and direction angle of an edge point in the search process can be obtained from a pre-constructed spiral look-up-table. No computation of the geometric features is required. Thus, the search of the coherent neighbouring points for edge connection is very fast. The experimental results have shown that the proposed method can effectively and efficiently segment a variety of firearms and knives of different shapes and sizes in the X-ray images of baggage.     

Hybrid fully convolutional networks-based skin lesion segmentation and melanoma detection using deep feature

Fully convolutional networks (FCNs) take the input of arbitrary size and produce correspondingly sized output with efficient inference and learning. The automatic diagnosis of melanoma is very essential for reducing the mortality rate by identifying the disease in earlier stages. A two-stage framework is used for implementing the melanoma detection, segmentation of skin lesion, and identification of melanoma lesions. Two FCNs based on VGG-16 and GoogLeNet are incorporated for improving the segmentation accuracy. A hybrid framework is used for incorporating these two FCNs. The classification is done by extracting the feature from segmented lesion by using deep residual network and a hand-crafted feature. Classification is done by support vector machine. The performance analysis of our framework gives a promising accuracy, that is, 0.8892 for classification in ISBI 2016 dataset and 0.853 for ISIC 2017 dataset.     

SABOS-Net: Self-supervised attention based network for automatic organ segmentation of head and neck CT images

The segmentation of Organs At Risk (OAR) in Computed Tomography (CT) images is an essential part of the planning phase of radiation treatment to avoid the adverse effects of cancer radiotherapy treatment. Accurate segmentation is a tedious task in the head and neck region due to a large number of small and sensitive organs and the low contrast of CT images. Deep learning-based automatic contouring algorithms can ease this task even when the organs have irregular shapes and size variations. This paper proposes a fully automatic deep learning-based self-supervised 3D Residual UNet architecture with CBAM(Convolution Block Attention Mechanism) for the organ segmentation in head and neck CT images. The Model Genesis structure and image context restoration techniques are used for self-supervision, which can help the network learn image features from unlabeled data, hence solving the annotated medical data scarcity problem in deep networks. A new loss function is applied for training by integrating Focal loss, Tversky loss, and Cross-entropy loss. The proposed model outperforms the state-of-the-art methods in terms of dice similarity coefficient in segmenting the organs. Our self-supervised model could achieve a 4% increase in the dice score of Chiasm, which is a small organ that is present only in a very few CT slices. The proposed model exhibited better accuracy for 5 out of 7 OARs than the recent state-of-the-art models. The proposed model could simultaneously segment all seven organs in an average time of 0.02 s. The source code of this work is made available at https://github.com/seeniafrancis/SABOSNet .     

Image Processing of Manganese Nodules Based on Background Gray Value Calculation

To troubleshoot two problems arising from the segmentation of manganese nodule images-uneven illumination and morphological defects caused by white sand coverage, we propose, with reference to features of manganese nodules, a method called “background gray value calculation”. As the result of the image procession with the aid this method, the two problems above are solved eventually, together with acquisition of a segmentable image of manganese nodules. As a result, its comparison with other segmentation methods justifies its feasibility and stability. Judging from simulation results, it is indicated that this method is applicable to repair the target shape in the image, and segment the manganese nodule image in a short time. Also, it could be used to synchronously process a large number of manganese nodules on different conditions in an image, laying a good foundation for automatic underwater manganese nodule survey. Even if the target in the image is slightly distorted, the statistical data of manganese nodules are still accurate. Moreover, other methods cannot be fully applied to the segmentation of manganese nodule images; in another word, the effectiveness and stability of this method are proved.