Brain Tumor Segmentation in Multimodal MRI Using U-Net Layered Structure

The brain tumour is the mass where some tissues become old or damaged, but they do not die or not leave their space. Mainly brain tumour masses occur due to malignant masses. These tissues must die so that new tissues are allowed to be born and take their place. Tumour segmentation is a complex and time-taking problem due to the tumour’s size, shape, and appearance variation. Manually finding such masses in the brain by analyzing Magnetic Resonance Images (MRI) is a crucial task for experts and radiologists. Radiologists could not work for large volume images simultaneously, and many errors occurred due to overwhelming image analysis. The main objective of this research study is the segmentation of tumors in brain MRI images with the help of digital image processing and deep learning approaches. This research study proposed an automatic model for tumor segmentation in MRI images. The proposed model has a few significant steps, which first apply the pre-processing method for the whole dataset to convert Neuroimaging Informatics Technology Initiative (NIFTI) volumes into the 3D NumPy array. In the second step, the proposed model adopts U-Net deep learning segmentation algorithm with an improved layered structure and sets the updated parameters. In the third step, the proposed model uses state-of-the-art Medical Image Computing and Computer-Assisted Intervention (MICCAI) BRATS 2018 dataset with MRI modalities such as T1, T1Gd, T2, and Fluid-attenuated inversion recovery (FLAIR). Tumour types in MRI images are classified according to the tumour masses. Labelling of these masses carried by state-of-the-art approaches such that the first is enhancing tumour (label 4), edema (label 2), necrotic and non-enhancing tumour core (label 1), and the remaining region is label 0 such that edema (whole tumour), necrosis and active. The proposed model is evaluated and gets the Dice Coefficient (DSC) value for High-grade glioma (HGG) volumes for their test set-a, test set-b, and test set-c 0.9795, 0.9855 and 0.9793, respectively. DSC value for the Low-grade glioma (LGG) volumes for the test set is 0.9950, which shows the proposed model has achieved significant results in segmenting the tumour in MRI using deep learning approaches. The proposed model is fully automatic that can implement in clinics where human experts consume maximum time to identify the tumorous region of the brain MRI. The proposed model can help in a way it can proceed rapidly by treating the tumor segmentation in MRI.     

A Hybrid Attention-Based Residual Unet for Semantic Segmentation of Brain Tumor

Segmenting brain tumors in Magnetic Resonance Imaging (MRI) volumes is challenging due to their diffuse and irregular shapes. Recently, 2D and 3D deep neural networks have become famous for medical image segmentation because of the availability of labelled datasets. However, 3D networks can be computationally expensive and require significant training resources. This research proposes a 3D deep learning model for brain tumor segmentation that uses lightweight feature extraction modules to improve performance without compromising contextual information or accuracy. The proposed model, called Hybrid Attention-Based Residual Unet (HA-RUnet), is based on the Unet architecture and utilizes residual blocks to extract low- and high-level features from MRI volumes. Attention and Squeeze-Excitation (SE) modules are also integrated at different levels to learn attention-aware features adaptively within local and global receptive fields. The proposed model was trained on the BraTS-2020 dataset and achieved a dice score of 0.867, 0.813, and 0.787, as well as a sensitivity of 0.93, 0.88, and 0.83 for Whole Tumor, Tumor Core, and Enhancing Tumor, on test dataset respectively. Experimental results show that the proposed HA-RUnet model outperforms the ResUnet and AResUnet base models while having a smaller number of parameters than other state-of-the-art models. Overall, the proposed HA-RUnet model can improve brain tumor segmentation accuracy and facilitate appropriate diagnosis and treatment planning for medical practitioners.     

Modified UNet Model for Brain Stroke Lesion Segmentation on Computed Tomography Images

The task of segmentation of brain regions affected by ischemic stroke is help to tackle important challenges of modern stroke imaging analysis. Unfortunately, at the moment, the models for solving this problem using machine learning methods are far from ideal. In this paper, we consider a modified 3D UNet architecture to improve the quality of stroke segmentation based on 3D computed tomography images. We use the ISLES 2018 (Ischemic Stroke Lesion Segmentation Challenge 2018) open dataset to train and test the proposed model. Interpretation of the obtained results, as well as the ideas for further experiments are included in the paper. Our evaluation is performed using the Dice or f1 score coefficient and the Jaccard index. Our architecture may simply be extended to ischemia segmentation and computed tomography image identification by selecting relevant hyperparameters. The Dice/f1 score similarity coefficient of our model shown 58% and results close to ground truth which is higher than the standard 3D UNet model, demonstrating that our model can accurately segment ischemic stroke. The modified 3D UNet model proposed by us uses an efficient averaging method inside a neural network. Since this set of ISLES is limited in number, using the data augmentation method and neural network regularization methods to prevent overfitting gave the best result. In addition, one of the advantages is the use of the Intersection over Union loss function, which is based on the assessment of the coincidence of the shapes of the recognized zones.     

Residual learning based CNN for breast cancer histopathological image classification

Biopsy is one of the most commonly used modality to identify breast cancer in women, where tissue is removed and studied by the pathologist under the microscope to look for abnormalities in tissue. This technique can be time-consuming, error-prone, and provides variable results depending on the expertise level of the pathologist. An automated and efficient approach not only aids in the diagnosis of breast cancer but also reduces human effort. In this paper, we develop an automated approach for the diagnosis of breast cancer tumors using histopathological images. In the proposed approach, we design a residual learning-based 152-layered convolutional neural network, named as ResHist for breast cancer histopathological image classification. ResHist model learns rich and discriminative features from the histopathological images and classifies histopathological images into benign and malignant classes. In addition, to enhance the performance of the developed model, we design a data augmentation technique, which is based on stain normalization, image patches generation, and affine transformation. The performance of the proposed approach is evaluated on publicly available BreaKHis dataset. The proposed ResHist model achieves an accuracy of 84.34% and an F1-score of 90.49% for the classification of histopathological images. Also, this approach achieves an accuracy of 92.52% and F1-score of 93.45% when data augmentation is employed. The proposed approach outperforms the existing methodologies in the classification of benign and malignant histopathological images. Furthermore, our experimental results demonstrate the superiority of our approach over the pre-trained networks, namely AlexNet, VGG16, VGG19, GoogleNet, Inception-v3, ResNet50, and ResNet152 for the classification of histopathological images.     

Breast cancer diagnosis from mammographic images using optimized feature selection and neural network architecture

Breast cancer is one of the deadly diseases in women that have raised the mortality rate of women. An accurate and early detection of breast cancer using mammogram images is still a complex task. Hence, this article proposes a novel breast cancer detection model, which included five major phases: (a) preprocessing, (b) segmentation, (c) feature extraction, (d) feature selection, and (e) classification. The input mammogram image is initially preprocessed using contrast limited adaptive histogram equalization (CLAHE) and median filtering. The preprocessed image is then subjected to segmentation via the region growing algorithm. Subsequently, geometric features, texture features and gradient features are extracted from the segmented image. Since the length of the feature vector is large, it is essential to select the optimal features. Here, the selection of optimal features is done by a hybrid optimization algorithm. Once the optimal features are selected, they are subjected to the classification process involving the neural network (NN) classifier. As a novelty, the weight of NN is selected optimally to enhance the accuracy of diagnosis (benign and malignant). The optimal feature selection as well as the weight optimization of NN is accomplished by merging the Lion algorithm (LA) and particle swarm optimization (PSO), named as velocity updated lion algorithm (VU‐LA). Finally, a performance‐based evaluation is carried out between VU‐LA and the existing models like, whale optimization algorithm (WOA), gray wolf optimization (GWO), firefly (FF), PSO, and LA.     

A Noise-Resistant Superpixel Segmentation Algorithm for Hyperspectral Images

The superpixel segmentation has been widely applied in many computer vision and image process applications. In recent years, amount of superpixel segmentation algorithms have been proposed. However, most of the current algorithms are designed for natural images with little noise corrupted. In order to apply the superpixel algorithms to hyperspectral images which are always seriously polluted by noise, we propose a noise-resistant superpixel segmentation (NRSS) algorithm in this paper. In the proposed NRSS, the spectral signatures are first transformed into frequency domain to enhance the noise robustness; then the two widely spectral similarity measures-spectral angle mapper (SAM) and spectral information divergence (SID) are combined to enhance the discriminability of the spectral similarity; finally, the superpixels are generated with the proposed frequency-based spectral similarity. Both qualitative and quantitative experimental results demonstrate the effectiveness of the proposed superpixel segmentation algorithm when dealing with hyperspectral images with various noise levels. Moreover, the proposed NRSS is compared with the most widely used superpixel segmentation algorithm-simple linear iterative clustering (SLIC), where the comparison results prove the superiority of the proposed superpixel segmentation algorithm     

面向乳腺诊断的时域扩散光学层析图像重建方法

为了克服传统的X射线乳腺成像术在灵敏度、特异性、安全性和舒适性等方面存在的重大缺陷，提出了一种面向乳腺成像的时域扩散光学层析（diffuse optical tomography，DOT）图像重建技术．该技术以拉普拉斯变换时域扩散方程的有限元（finite element method，FEM）数值解作为正向模型，采用基于牛顿-拉夫逊迭代格式的逆模型框架．通过对锥形压缩乳房光学层析模式的模拟实验研究表明，该方法可有效重构出乳腺肿瘤组织的吸收系数μa和约化散射系数μs′的层析图像，且成像目标的空间位置准确，具有较高的图像质量．     

电视制导序列图像快速分割及目标特征提取

针对电视制导系统需从包含多个干扰目标的序列图像中快速识别和跟踪导弹目标的要求,提出了一种基于二值图像索引图的序列图像快速分割及目标特征提取算法,在序列图像二值化后,只需由FPGA对其遍历一次就可得到一张含有目标信息的索引图表,再由DSP对该索引图表边遍历边计算就可得到图像所含目标的数量.面积,质心坐标,二阶矩不变量等特征.实验结果表明,该算法并行处理效率高,实时性好,完全可满足电视制导系统的要求.     

Construction of pH-Sensitive Nanovaccines Encapsulating Tumor Cell Lysates and Immune Adjuvants for Breast Cancer Therapy

The current immunotherapy strategies for triple negative breast cancer (TNBC) are greatly limited due to the immunosuppressive tumor microenvironment (TME). Immunization with cancer vaccines composed of tumor cell lysates (TCL) can induce an effective antitumor immune response. However, this approach also has the disadvantages of inefficient antigen delivery to the tumor tissues and the limited immune response elicited by single-antigen vaccines. To overcome these limitations, a pH-sensitive nanocalcium carbonate (CaCO₃) carrier loaded with TCL and immune adjuvant CpG (CpG oligodeoxynucleotide 1826) is herein constructed for TNBC immunotherapy. This tailor-made nanovaccine, termed CaCO₃@TCL/CpG, not only neutralizes the acidic TME through the consumption of lactate by CaCO₃, which increases the proportion of the M1/M2 macrophages and promotes infiltration of effector immune cells but also activates the dendritic cells in the tumor tissues and recruits cytotoxic T cells to further kill the tumor cells. In vivo fluorescence imaging study shows that the pegylated nanovaccine could stay longer in the blood circulation and extravasate preferentially into tumor site. Besides, the nanovaccine exhibits high cytotoxicity in 4T1 cells and significantly inhibits tumor growth of tumor-bearing mice. Overall, this pH-sensitive nanovaccine is a promising nanoplatform for enhanced immunotherapy of TNBC.     

一种改进的MRI图像刚性平移运动伪影的校正

在磁共振成像过程中由于患者的运动会在图像中造成运动伪影,从而造成图像的退化,严重影响临床诊断．本文对MRI图像刚性平移运动伪影提出了一个改进的后处理方法：首先用谱平移理论消除频率编码方向平移运动;然后建立模糊模型表示图像的背景并对其进行抑制,用数学形态学的方法确定图像的支撑域;最后以能量熵为收敛准则,用相位恢复算法对频率编码方向残余的子像素移动造成的伪影和相位编码方向的伪影进行消除．实验表明,应用本研究提出的方法能够明显地消除图像空间运动造成的伪影．     

Hybrid Models for Breast Cancer Detection via Transfer Learning Technique

Currently, breast cancer has been a major cause of deaths in women worldwide and the World Health Organization (WHO) has confirmed this. The severity of this disease can be minimized to the large extend, if it is diagnosed properly at an early stage of the disease. Therefore, the proper treatment of a patient having cancer can be processed in better way, if it can be diagnosed properly as early as possible using the better algorithms. Moreover, it has been currently observed that the deep neural networks have delivered remarkable performance for detecting cancer in histopathological images of breast tissues. To address the above said issues, this paper presents a hybrid model using the transfer learning to study the histopathological images, which help in detection and rectification of the disease at a low cost. Extensive dataset experiments were carried out to validate the suggested hybrid model in this paper. The experimental results show that the proposed model outperformed the baseline methods, with F-scores of 0.81 for DenseNet + Logistic Regression hybrid model, (F-score: 0.73) for Visual Geometry Group (VGG) + Logistic Regression hybrid model, (F-score: 0.74) for VGG + Random Forest, (F-score: 0.79) for DenseNet + Random Forest, and (F-score: 0.79) for VGG + Densenet + Logistic Regression hybrid model on the dataset of histopathological images.     

Surface Functionalization of Single Superparamagnetic Iron Oxide Nanoparticles for Targeted Magnetic Resonance Imaging

Magnetic resonance imaging (MRI), a non‐invasive, non‐radiative technique, is thought to lead to cellular or even molecular resolution if optimized targeted MR contrast agents are introduced. This would allow diagnosing progressive diseases in early stages. Here, it is shown that the high binding affinity of poly(ethylene glycol)‐gallol (PEG‐gallol) allows freeze drying and re‐dispersion of 9 ± 2‐nm iron oxide cores individually stabilized with ≈9‐nm‐thick stealth coatings, yielding particle stability for at least 20 months. Particle size, stability, and magnetic properties of PEGylated particles are compared to Feridex, a commercially available untargeted negative MR contrast agent. Biotin‐PEG(3400)‐gallol/methoxy‐PEG(550)‐gallol stabilized nanoparticles are further functionalized with biotinylated human anti‐VCAM‐1 antibodies using the biotin–neutravidin linkage. Binding kinetics and excellent specificity of these nanoparticles are demonstrated using quartz crystal microbalance with dissipation monitoring (QCM‐D). These MR contrast agents can be functionalized with any biotinylated ligand at controlled ligand surface density, rendering them a versatile research tool.     

Residual Magnetic Flux Leakage: A Possible Tool for Studying Pipeline Defects

Simulated defects of different shapes and sizes were created in a section of API X70 steel line pipe and were investigated using a residual magnetic flux leakage (MFL) technique. The MFL patterns reflected the actual shape and size of the defects, although there was a slight shift in their position. The defect features were apparent even at high stresses of 220 MPa when the samples were magnetized at those particular stresses. However, unlike the active flux technique, the residual MFL needs a sensitive flux detector to detect the comparatively weaker flux signals.     

A New Hybrid Model for Segmentation of the Skin Lesion Based on Residual Attention U-Net

Skin segmentation participates significantly in various biomedical applications, such as skin cancer identification and skin lesion detection. This paper presents a novel framework for segmenting the skin. The framework contains two main stages: The first stage is for removing different types of noises from the dermoscopic images, such as hair, speckle, and impulse noise, and the second stage is for segmentation of the dermoscopic images using an attention residual U-shaped Network (U-Net). The framework uses variational Autoencoders (VAEs) for removing the hair noises, the Generative Adversarial Denoising Network (DGAN-Net), the Denoising U-shaped U-Net (D-U-NET), and Batch Renormalization U-Net (Br-U-NET) for removing the speckle noise, and the Laplacian Vector Median Filter (MLVMF) for removing the impulse noise. In the second main stage, the residual attention u-net was used for segmentation. The framework achieves (35.11, 31.26, 27.01, and 26.16), (36.34, 33.23, 31.32, and 28.65), and (36.33, 32.21, 28.54, and 27.11) for removing hair, speckle, and impulse noise, respectively, based on Peak Signal Noise Ratio (PSNR) at the level of (0.1, 0.25, 0.5, and 0.75) of noise. The framework also achieves an accuracy of nearly 94.26 in the dice score in the process of segmentation before removing noise and 95.22 after removing different types of noise. The experiments have shown the efficiency of the used model in removing noise according to the structural similarity index measure (SSIM) and PSNR and in the segmentation process as well.     

An Improved Jellyfish Algorithm for Multilevel Thresholding of Magnetic Resonance Brain Image Segmentations

Image segmentation is vital when analyzing medical images, especially magnetic resonance (MR) images of the brain. Recently, several image segmentation techniques based on multilevel thresholding have been proposed for medical image segmentation; however, the algorithms become trapped in local minima and have low convergence speeds, particularly as the number of threshold levels increases. Consequently, in this paper, we develop a new multilevel thresholding image segmentation technique based on the jellyfish search algorithm (JSA) (an optimizer). We modify the JSA to prevent descents into local minima, and we accelerate convergence toward optimal solutions. The improvement is achieved by applying two novel strategies: Ranking-based updating and an adaptive method. Ranking-based updating is used to replace undesirable solutions with other solutions generated by a novel updating scheme that improves the qualities of the removed solutions. We develop a new adaptive strategy to exploit the ability of the JSA to find a best-so-far solution; we allow a small amount of exploration to avoid descents into local minima. The two strategies are integrated with the JSA to produce an improved JSA (IJSA) that optimally thresholds brain MR images. To compare the performances of the IJSA and JSA, seven brain MR images were segmented at threshold levels of 3, 4, 5, 6, 7, 8, 10, 15, 20, 25, and 30. IJSA was compared with several other recent image segmentation algorithms, including the improved and standard marine predator algorithms, the modified salp and standard salp swarm algorithms, the equilibrium optimizer, and the standard JSA in terms of fitness, the Structured Similarity Index Metric (SSIM), the peak signal-to-noise ratio (PSNR), the standard deviation (SD), and the Features Similarity Index Metric (FSIM). The experimental outcomes and the Wilcoxon rank-sum test demonstrate the superiority of the proposed algorithm in terms of the FSIM, the PSNR, the objective values, and the SD; in terms of the SSIM, IJSA was competitive with the others.     

A Novel Hybrid Machine Learning Approach for Classification of Brain Tumor Images

Abnormal growth of brain tissues is the real cause of brain tumor. Strategy for the diagnosis of brain tumor at initial stages is one of the key step for saving the life of a patient. The manual segmentation of brain tumor magnetic resonance images (MRIs) takes time and results vary significantly in low-level features. To address this issue, we have proposed a ResNet-50 feature extractor depended on multilevel deep convolutional neural network (CNN) for reliable images segmentation by considering the low-level features of MRI. In this model, we have extracted features through ResNet-50 architecture and fed these feature maps to multi-level CNN model. To handle the classification process, we have collected a total number of 2043 MRI patients of normal, benign, and malignant tumor. Three model CNN, multi-level CNN, and ResNet-50 based multi-level CNN have been used for detection and classification of brain tumors. All the model results are calculated in terms of various numerical values identified as precision (P), recall (R), accuracy (Acc) and f1-score (F1-S). The obtained average results are much better as compared to already existing methods. This modified transfer learning architecture might help the radiologists and doctors as a better significant system for tumor diagnosis.     

Efficient Polysulfide‐Based Nanotheranostics for Triple‐Negative Breast Cancer: Ratiometric Photoacoustics Monitored Tumor Microenvironment‐Initiated H2S Therapy

The incidence of triple‐negative breast cancer (TNBC) is difficult to predict, and TNBC has a high mortality rate among women worldwide. In this study, a theranostics approach is developed for TNBC with ratiometric photoacoustic monitored thiol‐initiated hydrogen sulfide (H₂S) therapy. The ratiometric photoacoustic (PA) probe (CY) with a thiol‐initiated H₂S donor (PSD) to form a nanosystem (CY‐PSD nanoparticles) is integrated. In this theranostics approach, H₂S generated from PSD is sensed by CY based on ratiometric PA signals, which simultaneously pinpoints the tumor region. Additionally, H₂S is cytotoxic toward TNBC cells (MDA‐MB 231), showing a tumor inhibition rate of 63%. To further verify its pharmacological mechanism, proteomics analysis is performed on tumors treated with CY‐PSD nanoparticles. Cells are killed by the significant mitochondrial dysfunction via supressed energy supply and apoptosis initiation. Besides, the observed inhibition of oxidative stress also generates the cytotoxicity. Significant Kyoto Encyclopedia of Genes Genomes pathways related to TNBC are found to be inhibited. This H₂S theranostics approach updates the current anticancer therapies which brings promise for women suffering malignant breast cancer.     

Nanotentacle‐Structured Magnetic Particles for Efficient Capture of Circulating Tumor Cells

Circulating tumor cells (CTCs) have attracted considerable attention as promising markers for diagnosing and monitoring the cancer status. Despite many technological advances in isolating CTCs, the capture efficiency and purity still remain challenges that limit clinical practice. Here, the construction of “nanotentacle”‐structured magnetic particles using M13‐bacteriophage and their application for the efficient capturing of CTCs is demonstrated. The M13‐bacteriophage to magnetic particles followed by modification with PEG is conjugated, and further tethered monoclonal antibodies against the epidermal receptor 2 (HER2). The use of nanotentacle‐structured magnetic particles results in a high capture purity (>45%) and efficiency (>90%), even for a smaller number of cancer cells (≈25 cells) in whole blood. Furthermore, the cancer cells captured are shown to maintain a viability of greater than 84%. The approach can be effectively used for capturing CTCs with high efficiency and purity for the diagnosis and monitoring of cancer status.     

Applicability of the Magnetic Barkhausen Noise Method for Nondestructive Measurement of Residual Stresses in the Carburized and Tempered 19CrNi5H Steels

There exist no materials and/or structures of technical importance without residual stresses. The residual stress management concept has gained importance in industrial applications aiming to improve service performance and useful life of the product. Thus, the industry requests rapid, reliable, and nondestructive methods to determine residual stress state. The aim of this article is to investigate the applicability of the Magnetic Barkhausen Noise (MBN) method to measurement of surface residual stresses in the carburized steels. To comprehend the differences in the surface residual stress state, 19CrNi5H steel samples were carburized at 900°C for 8 and 13 hours, and then, tempered in the range of 180°C and 600°C. The MBN measurement results were correlated with those obtained by the X-ray diffraction (XRD) measurements. Microstructural investigations and hardness measurements were also conducted. For this particular study, it was concluded that both techniques give similar qualitative results for monitoring of the residual stress variations in the carburized and tempered steels. Since the MBN method is much faster than the XRD method, from the industrial point of view it is a very strong candidate for qualitative monitoring of residual stress variations. With an appropriate pre-calibration by considering the effect of microstructure, the MBN method may give reliable quantitative results for residual stress.