A review on brain tumor diagnosis from MRI images: Practical implications, key achievements, and lessons learned

Artificial Intelligence Algorithm-Based Analysis of Ultrasonic Imaging Features for Diagnosis of Pregnancy Complicated with Brain Tumor

This research was to explore the accuracy of ultrasonic diagnosis based on artificial intelligence algorithm in the diagnosis of pregnancy complicated with brain tumors. In this study, 18 patients with pregnancy complicated with brain tumor confirmed by pathology were selected as the research object. Ultrasound contrast based on artificial bee colony algorithm was performed and diagnosed by experienced clinicians. Ultrasonic image will be reconstructed by artificial bee colony algorithm to improve its image display ability. The pathological diagnosis will be handed over to the physiological pathology laboratory of the hospital for diagnosis. The doctor's ultrasonic diagnosis results were compared with the pathological diagnosis stage results of patients, and the results were analyzed by statistical analysis to evaluate its diagnostic value. The comparison results showed that the number and classification of benign tumors were the same, while in malignant tumors, the number diagnosis was the same, but there was one patient with diagnostic error in classification. One case of mixed glial neuron tumor was diagnosed as glial neuron tumor, and the diagnostic accuracy was 94.44% and the K value was 0.988. The diagnostic results of the two were in excellent agreement. The results show that, in the ultrasonic image diagnosis of patients with brain tumors during pregnancy based on artificial intelligence algorithm, most of them are benign and have obvious symptoms. Ultrasound has a good diagnostic accuracy and can be popularized in clinical diagnosis. The results can provide experimental data for the clinical application of ultrasonic image feature analysis based on artificial intelligence as the diagnosis of pregnancy complicated with brain tumors.

MRI-based machine learning for determining quantitative and qualitative characteristics affecting the survival of glioblastoma multiforme

PURPOSE

Our current study aims to consider the image biomarkers extracted from the MRI images for exploring their effects on glioblastoma multiforme (GBM) patients' survival. Determining its biomarker helps better manage the disease and evaluate treatments. It has been proven that imaging features could be used as a biomarker. The purpose of this study is to investigate the features in MRI and clinical features as the biomarker association of survival of GBM.

METHODS

55 patients were considered with five clinical features, 10 qualities pre-operative MRI image features, and six quantitative features obtained using BraTumIA software. It was run ANN, C5, Bayesian, and Cox models in two phases for determining important variables. In the first phase, we selected the quality features that occur at least in three models and quantitative in two models. In the second phase, models were run with the extracted features, and then the probability value of variables in each model was calculated.

RESULTS

The mean of accuracy, sensitivity, specificity, and area under curve (AUC) after running four machine learning techniques were 80.47, 82.54, 79.78, and 0.85, respectively. In the second step, the mean of accuracy, sensitivity, specificity, and AUC were 79.55, 78.71, 79.83, and 0.87, respectively.

CONCLUSION

We found the largest size of the width, the largest size of length, radiotherapy, volume of enhancement, volume of nCET, satellites, enhancing margin, and age feature are important features.

Artificial Intelligence in Brain Tumour Surgery-An Emerging Paradigm

Artificial intelligence (AI) platforms have the potential to cause a paradigm shift in brain tumour surgery. Brain tumour surgery augmented with AI can result in safer and more effective treatment. In this review article, we explore the current and future role of AI in patients undergoing brain tumour surgery, including aiding diagnosis, optimising the surgical plan, providing support during the operation, and better predicting the prognosis. Finally, we discuss barriers to the successful clinical implementation, the ethical concerns, and we provide our perspective on how the field could be advanced.

Automatic brain tumour diagnostic method based on a back propagation neural network and an extended set-membership filter

BACKGROUND

Diagnosing brain tumours remains a challenging task in clinical practice. Despite their questionable accuracy, magnetic resonance image (MRI) scans are presently considered the optimal facility for assessing the growth of tumours. However, the efficiency of manual diagnosis is low, and high computational cost and poor convergence restrict the application of machine learning methods. This study aims to design a method that can reliably diagnose brain tumours from MRI scans.

METHODS

First, image pre-processing (which includes background removal, size standardization, noise removal, and contrast enhancement) is utilized to normalize the images. Then, grey level co-occurrence matrix features are selected as texture features of the brain MRI scans. Finally, a method combining a back propagation neural network (BPNN) and an extended set-membership filter (ESMF) is proposed to classify features and perform image classification.

RESULTS

A total of 304 patient MRI series (247 images of brains with tumours and 57 images of normal brains) were included and assessed in this study. The results revealed that our proposed method can achieve an accuracy of 95.40% and has classification accuracies of 97.14% and 88.24% for brain tumour and normal brain, respectively.

CONCLUSION

This study proposes an automatic brain tumour detection model constructed using a combination of BPNN and ESMF. The model is found to be able to accurately classify brain MRI scans as normal or tumour images.

Accuracy of Machine Learning Algorithms for the Classification of Molecular Features of Gliomas on MRI: A Systematic Literature Review and Meta-Analysis

Simple Summary

Glioma prognosis and treatment are based on histopathological characteristics and molecular profile. Following the World Health Organization (WHO) guidelines (2016), the most important molecular diagnostic markers include IDH1/2-genotype and 1p/19q codeletion status, although more recent publications also include ARTX genotype and TERT- and MGMT promoter methylation. Machine learning algorithms (MLAs), however, were described to successfully determine these molecular characteristics non-invasively by using magnetic resonance imaging (MRI) data. The aim of this review and meta-analysis was to define the diagnostic accuracy of MLAs with regard to these different molecular markers. We found high accuracies of MLAs to predict each individual molecular marker, with IDH1/2-genotype being the most investigated and the most accurate. Radiogenomics could therefore be a promising tool for discriminating genetically determined gliomas in a non-invasive fashion. Although encouraging results are presented here, large-scale, prospective trials with external validation groups are warranted.

Abstract

Treatment planning and prognosis in glioma treatment are based on the classification into low- and high-grade oligodendroglioma or astrocytoma, which is mainly based on molecular characteristics (IDH1/2- and 1p/19q codeletion status). It would be of great value if this classification could be made reliably before surgery, without biopsy. Machine learning algorithms (MLAs) could play a role in achieving this by enabling glioma characterization on magnetic resonance imaging (MRI) data without invasive tissue sampling. The aim of this study is to provide a performance evaluation and meta-analysis of various MLAs for glioma characterization. Systematic literature search and meta-analysis were performed on the aggregated data, after which subgroup analyses for several target conditions were conducted. This study is registered with PROSPERO, CRD42020191033. We identified 724 studies; 60 and 17 studies were eligible to be included in the systematic review and meta-analysis, respectively. Meta-analysis showed excellent accuracy for all subgroups, with the classification of 1p/19q codeletion status scoring significantly poorer than other subgroups (AUC: 0.748, p = 0.132). There was considerable heterogeneity among some of the included studies. Although promising results were found with regard to the ability of MLA-tools to be used for the non-invasive classification of gliomas, large-scale, prospective trials with external validation are warranted in the future.

Role of deep learning in brain tumor detection and classification (2015 to 2020): A review

During the last decade, computer vision and machine learning have revolutionized the world in every way possible. Deep Learning is a sub field of machine learning that has shown remarkable results in every field especially biomedical field due to its ability of handling huge amount of data. Its potential and ability have also been applied and tested in the detection of brain tumor using MRI images for effective prognosis and has shown remarkable performance. The main objective of this research work is to present a detailed critical analysis of the research and findings already done to detect and classify brain tumor through MRI images in the recent past. This analysis is specifically beneficial for the researchers who are experts of deep learning and are interested to apply their expertise for brain tumor detection and classification. As a first step, a brief review of the past research papers using Deep Learning for brain tumor classification and detection is carried out. Afterwards, a critical analysis of Deep Learning techniques proposed in these research papers (2015-2020) is being carried out in the form of a Table. Finally, the conclusion highlights the merits and demerits of deep neural networks. The results formulated in this paper will provide a thorough comparison of recent studies to the future researchers, along with the idea of the effectiveness of various deep learning approaches. We are confident that this study would greatly assist in advancement of brain tumor research.

Optical wireless communication performance enhancement using Hamming coding and an efficient adaptive equalizer with a deep-learning-based quality assessment

Optical wireless communication (OWC) technology is one of several alternative technologies for addressing the radio frequency limitations for applications in both indoor and outdoor architectures. Indoor optical wireless systems suffer from noise and intersymbol interference (ISI). These degradations are produced by the wireless channel multipath effect, which causes data rate limitation and hence overall system performance degradation. On the other hand, outdoor OWC suffers from several physical impairments that affect transmission quality. Channel coding can play a vital role in the performance enhancement of OWC systems to ensure that data transmission is robust against channel impairments. In this paper, an efficient framework for OWC in developing African countries is introduced. It is suitable for OWC in both indoor and outdoor environments. The outdoor scenario will be suitable to wild areas in Africa. A detailed study of the system stages is presented to guarantee the suitable modulation, coding, equalization, and quality assessment scenarios for the OWC process, especially for tasks such as image and video communication. Hamming and low-density parity check coding techniques are utilized with an asymmetrically clipped DC-offset optical orthogonal frequency-division multiplexing (ADO-OFDM) scenario. The performance versus the complexity of both utilized techniques for channel coding is studied, and both coding techniques are compared at different coding rates. Another task studied in this paper is how to perform efficient adaptive channel estimation and hence equalization on the OWC systems to combat the effect of ISI. The proposed schemes for this task are based on the adaptive recursive least-squares (RLS) and the adaptive least mean squares (LMS) algorithms with activity detection guidance and tap decoupling techniques at the receiver side. These adaptive channel estimators are compared with the adaptive estimators based on the standard LMS and RLS algorithms. Moreover, this paper presents a new scenario for quality assessment of optical communication systems based on the regular transmission of images over the system and quality evaluation of these images at the receiver based on a trained convolutional neural network. The proposed OWC framework is very useful for developing countries in Africa due to its simplicity of implementation with high performance.

Three-class brain tumor classification using deep dense inception residual network

Three-class brain tumor classification becomes a contemporary research task due to the distinct characteristics of tumors. The existing proposals employ deep neural networks for the three-class classification. However, achieving high accuracy is still an endless challenge in brain image classification. We have proposed a deep dense inception residual network for three-class brain tumor classification. We have customized the output layer of Inception ResNet v2 with a deep dense network and a softmax layer. The deep dense network has improved the classification accuracy of the proposed model. The proposed model has been evaluated using key performance metrics on a publicly available brain tumor image dataset having 3064 images. Our proposed model outperforms the existing model with a mean accuracy of 99.69%. Further, similar performance has been obtained on noisy data.

MhURI:A Supervised Segmentation Approach to Leverage Salient Brain Tissues in Magnetic Resonance Images

BACKGROUND AND OBJECTIVES

Accurate segmentation of critical tissues from a brain MRI is pivotal for characterization and quantitative pattern analysis of the human brain and thereby, identifies the earliest signs of various neurodegenerative diseases. To date, in most cases, it is done manually by the radiologists. The overwhelming workload in some of the thickly populated nations may cause exhaustion leading to interruption for the doctors, which may pose a continuing threat to patient safety. A novel fusion method called U-Net inception based on 3D convolutions and transition layers is proposed to address this issue.

METHODS

A 3D deep learning method called Multi headed U-Net with Residual Inception (MhURI) accompanied by Morphological Gradient channel for brain tissue segmentation is proposed, which incorporates Residual Inception 2-Residual (RI2R) module as the basic building block. The model exploits the benefits of morphological pre-processing for structural enhancement of MR images. A multi-path data encoding pipeline is introduced on top of the U-Net backbone, which encapsulates initial global features and captures the information from each MRI modality.

RESULTS

The proposed model has accomplished encouraging outcomes, which appreciates the adequacy in terms of some of the established quality metrices when compared with some of the state-of-the-art methods while evaluating with respect to two popular publicly available data sets.

CONCLUSION

The model is entirely automatic and able to segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) from brain MRI effectively with sufficient accuracy. Hence, it may be considered to be a potential computer-aided diagnostic (CAD) tool for radiologists and other medical practitioners in their clinical diagnosis workflow.

Recognition of brain tumors in MRI images using texture analysis

Objectives

Brain neoplasms or intracranial tumors, which are more common in older adults, can affect individuals of any age including pediatric and children. Exposure to carcinogenic agents including ionizing radiation and family history is one of the main causes of the disease. Early diagnosis is crucial to avoid prolonged. patients' suffering. The aim of the study was to efficiently recognize the brain tumors from the other brain tissues which include grey and white matter as well as cerebrospinal fluid (CSF).

Materials and methods

This study was performed using axial, sagittal and coronal views for fifty brain tumor patients randomly selected from a set of 200 patients, with a “control” set consisting of images showing no sign of disease; and the “test” brain MRI images for patients diagnosed with brain tumor. The study includes both genders with age ranging from 18 years to 83 years old, (56.5 ± 17.2). The brain images were acquired using a standard head coil Philips Intera 1.5 Tesla machine (USA). The thickness of each section in the entire sequence was 8 mm. Acquisition of T2-weighted and T1-weighted were performed. Interactive Data Language software was used to analyze the data.

Results

The results of this study showed that: the overall accuracy of classification process was 94.8%, and for the tumor; the sensitivity was 97.3%. White matter and grey matter showed a classification accuracy of 95.7% and 89.7% and for CSF the accuracy was 94.3%.

Conclusion

The results showed that brain tumor can be classified successfully and delineated using texture analysis with minimum efforts and with high accuracy for brain tumors.

Automatic detection and segmentation of multiple brain metastases on magnetic resonance image using asymmetric UNet architecture

Detection of brain metastases is a paramount task in cancer management due both to the number of high-risk patients and the difficulty of achieving consistent detection. In this study, we aim to improve the accuracy of automated brain metastasis (BM) detection methods using a novel asymmetric UNet (asym-UNet) architecture. An end-to-end asymmetric 3D-UNet architecture, with two down-sampling arms and one up-sampling arm, was constructed to capture the imaging features. The two down-sampling arms were trained using two different kernels (3 × 3 × 3 and 1 × 1 × 3, respectively) with the kernel (1 × 1 × 3) dominating the learning. As a comparison, vanilla single 3D UNets were trained with different kernels and evaluated using the same datasets. Voxel-based Dice similarity coefficient (DSCv), sensitivity (S v), precision (P v), BM-based sensitivity (S BM), and false detection rate (F BM) were used to evaluate model performance. Contrast-enhanced T1 MR images from 195 patients with a total of 1034 BMs were solicited from our institutional stereotactic radiosurgery database. The patient cohort was split into training (160 patients, 809 lesions), validation (20 patients, 136 lesions), and testing (15 patients, 89 lesions) datasets. The lesions in the testing dataset were further divided into two subgroups based on the diameters (small S = 1-10 mm, large L = 11-26 mm). In the testing dataset, there were 72 and 17 BMs in the S and L sub-groups, respectively. Among all trained networks, asym-UNet achieved the highest DSCv of 0.84 and lowest F BM of 0.24. Although vanilla 3D-UNet with a single 1 × 1 × 3 kernel achieved the highest sensitivities for the S group, it resulted in the lowest precision and highest false detection rate. Asym-UNet was shown to balance sensitivity and false detection rate as well as keep the segmentation accuracy high. The novel asym-UNet segmentation network showed overall competitive segmentation performance and more pronounced improvement in hard-to-detect small BMs comparing to the vanilla single 3D UNet.

Current landscape and future perspectives in preclinical MR and PET imaging of brain metastasis

Brain metastasis (BM) is a major cause of cancer patient morbidity. Clinical magnetic resonance imaging (MRI) and positron emission tomography (PET) represent important resources to assess tumor progression and treatment responses. In preclinical research, anatomical MRI and to some extent functional MRI have frequently been used to assess tumor progression. In contrast, PET has only to a limited extent been used in animal BM research. A considerable culprit is that results from most preclinical studies have shown little impact on the implementation of new treatment strategies in the clinic. This emphasizes the need for the development of robust, high-quality preclinical imaging strategies with potential for clinical translation. This review focuses on advanced preclinical MRI and PET imaging methods for BM, describing their applications in the context of what has been done in the clinic. The strengths and shortcomings of each technology are presented, and recommendations for future directions in the development of the individual imaging modalities are suggested. Finally, we highlight recent developments in quantitative MRI and PET, the use of radiomics and multimodal imaging, and the need for a standardization of imaging technologies and protocols between preclinical centers.

Two-Dimensional Stockwell Transform and Deep Convolutional Neural Network for Multi-Class Diagnosis of Pathological Brain

Since the brain lesion detection and classification is a vital diagnosis task, in this paper, the problem of brain magnetic resonance imaging (MRI) classification is investigated. Recent advantages in machine learning and deep learning allows the researchers to develop the robust computer-aided diagnosis (CAD) tools for classification of brain lesions. Feature extraction is an essential step in any machine learning scheme. Time-frequency analysis methods provide localized information that makes them more attractive for image classification applications. Owing to the advantages of two-dimensional discrete orthonormal Stockwell transform (2D DOST), we propose to use it to extract the efficient features from brain MRIs and obtain the feature matrix. Since there are some irrelevant features, two-directional two-dimensional principal component analysis ((2D)₂PCA) is used to reduce the dimension of the feature matrix. Finally, convolution neural networks (CNNs) are designed and trained for MRI classification. Simulation results indicate that the proposed CAD tool outperforms the recently introduced ones and can efficiently diagnose the MRI scans.

Hypoxia and Amino Acid Imaging of High-Grade Glioma: 18F-FAZA PET/CT and 11C-Methionine PET/MRI

In the present case, we report the first experience of a patient with high-grade glioma who underwent dual F-FAZA PET/CT imaging for intratumoral hypoxia assessment, before treatment, and for therapy monitoring in the suspicious of recurrence, as part of a clinical research protocol. In addition, despite the diagnosis of glioblastoma, the patient at 3 years from diagnosis was alive and underwent C-methionine simultaneous PET/MRI for disease monitoring after treatment, showing stability of disease. The multitracer capability of PET in assessing different and complementary metabolic features along with the use of a last-generation scanner as PET/MRI in brain oncology are here enlighten.

Chitosan-Based Non-viral Gene and Drug Delivery Systems for Brain Cancer

Central nervous system (CNS) tumors are a leading source of morbidity and mortality worldwide. Today, different strategies have been developed to allow targeted and controlled drug delivery into the brain. Gene therapy is a system based on the modification of patient's cells through the introduction of genetic material to exert a specific action. Administration of the foreign genetic material can be done through viral-mediated delivery or non-viral delivery via physical or mechanical systems. For brain cancer specifically, gene therapy can overcome the actual challenge of blood brain barrier penetration, the main reason for therapeutic failure. Chitosan (CS), a natural based biodegradable polymer obtained from the exoskeleton of crustaceans such as crab, shrimp, and lobster, has been used as a delivery vehicle in several non-viral modification strategies. This cationic polysaccharide is highly suitable for gene delivery mainly due to its chemical properties, its non-toxic nature, its capacity to protect nucleic acids through the formation of complexes with the genetic material, and its ease of degradation in organic environments. Recent evidence supports the use of CS as an alternative gene delivery system for cancer treatment. This review will describe multiple studies highlighting the advantages and challenges of CS-based delivery structures for the treatment of brain tumors. Furthermore, this review will provide insight on the translational potential of various CS based-strategies in current clinical cancer studies. Specifically, CS-based nanostructures including nanocapsules, nanospheres, solid-gel formulations, and nanoemulsions, also microshperes and micelles will be evaluated.

A new approach for brain tumor diagnosis system: Single image super resolution based maximum fuzzy entropy segmentation and convolutional neural network

Magnetic resonance imaging (MRI) images can be used to diagnose brain tumors. Thanks to these images, some methods have so far been proposed in order to distinguish between benign and malignant brain tumors. Many systems attempting to define these tumors are based on tissue analysis methods. However, various factors such as the quality of an MRI device, noisy images and low image resolution may decrease the quality of MRI images. To eliminate these problems, super resolution approaches are preferred as a complementary source for brain tumor images. The proposed method benefits from single image super resolution (SISR) and maximum fuzzy entropy segmentation (MFES) for brain tumor segmentation on an MRI image. Later, pre-trained ResNet architecture, which is a convolutional neural network (CNN) architecture, and support vector machine (SVM) are used to perform feature extraction and classification, respectively. It was observed in experimental studies that SISR displayed a higher performance in terms of brain tumor segmentation. Similarly, it displayed a higher performance in terms of classifying brain tumor regions as well as benign and malignant brain tumors. As a result, the present study indicated that SISR yielded an accuracy rate of 95% in the diagnosis of segmented brain tumors, which exceeds brain tumor segmentation using MFES without SISR by 7.5%.

The Molecular Effects of Ionizing Radiations on Brain Cells: Radiation Necrosis vs. Tumor Recurrence

The central nervous system (CNS) is generally resistant to the effects of radiation, but higher doses, such as those related to radiation therapy, can cause both acute and long-term brain damage. The most important results is a decline in cognitive function that follows, in most cases, cerebral radionecrosis. The essence of radio-induced brain damage is multifactorial, being linked to total administered dose, dose per fraction, tumor volume, duration of irradiation and dependent on complex interactions between multiple brain cell types. Cognitive impairment has been described following brain radiotherapy, but the mechanisms leading to this adverse event remain mostly unknown. In the event of a brain tumor, on follow-up radiological imaging often cannot clearly distinguish between recurrence and necrosis, while, especially in patients that underwent radiation therapy (RT) post-surgery, positron emission tomography (PET) functional imaging, is able to differentiate tumors from reactive phenomena. More recently, efforts have been done to combine both morphological and functional data in a single exam and acquisition thanks to the co-registration of PET/MRI. The future of PET imaging to differentiate between radionecrosis and tumor recurrence could be represented by a third-generation PET tracer already used to reveal the spatial extent of brain inflammation. The aim of the following review is to analyze the effect of ionizing radiations on CNS with specific regard to effect of radiotherapy, focusing the attention on the mechanism underling the radionecrosis and the brain damage, and show the role of nuclear medicine techniques to distinguish necrosis from recurrence and to early detect of cognitive decline after treatment.