China 
Africa 
Explore chapters and articles related to this topic
An Efficient System for Predictive Analysis on Brain Cancer Using Machine Learning and Deep Learning Techniques
Published in Teena Bagga, Kamal Upreti, Nishant Kumar, Amirul Hasan Ansari, Danish Nadeem, Designing Intelligent Healthcare Systems, Products, and Services Using Disruptive Technologies and Health Informatics, 2023
Akshita S. Chanchlani, Vilas M. Thakare, Vijay M. Wadhai, Dhanashri H. Gawali, Minakshee Patil
Brain cancer is caused by a malignant brain tumour. Not all brain tumours are malignant (cancerous). Some types of brain tumour are benign (non-cancerous). Tumour grade is the description of a tumour based on how abnormal the tumour cells and the tumour tissue look under a microscope [3]: Grade I: The tissue is benign. The cells look nearly like normal brain cells, and they grow slowly.Grade II: The tissue is malignant. The cells look less like normal cells than do the cells in a Grade I tumour.Grade III: The malignant tissue has cells that look very different from normal cells. The abnormal cells are actively growing (anaplastic).Grade IV: The malignant tissue has cells that look most abnormal and tend to grow quickly.
Artificial Intelligence and Machine Learning
Published in Archana Mire, Vinayak Elangovan, Shailaja Patil, Advances in Deep Learning for Medical Image Analysis, 2022
Kaushik Dehingia, Mdi B. Jeelani, Anusmita Das
When a brain tumor develops, most abnormal cells have poor contrast compared to neighboring cells. The majority of patients with brain tumors have a 5-year survival record. As a result, the most important job is to identify a brain tumor as soon as possible. Optical imaging and AI help to speed up and improve the identification and diagnosis of brain tumors. In medical imaging, AI in the application of DL methods is used to categorize and diagnose brain tumors. The most widely used MRI modality for brain tumor diagnosis is a painless technique that helps study tumors from different perspectives and viewpoints. The medical imaging method of brain tumor segmentation is used for tissue quantification, classification, surgical preparation, abnormality localization, and various medical assessments. Manual segmentation, semiautomatic segmentation, and fully automatic segmentation are the three forms of segmentation. Different AI and ML algorithms are used in MRI image processing to better view image segmentation and classification [Saba 2020]. In the segmentation of brain tumors, the CNN algorithm is widely used. With limited pre-processing, CNN extracts features from pixel images directly [Badža and Barjaktarovi 2020]. The best-known CNN architectures for brain tumor segmentation are given as fuzzy clustering, the form of k-clustering, and Otsu and threshold approaches, as well as U-Net architecture [Bhandarim et al. 2020]. LinkNet is a semantic segmentation-focused light DNN architecture. This network is faster and more accurate than SegNet [Sobhaninia et al. 2018, Saba 2020].
Swarm Optimization and Machine Learning to Improve the Detection of Brain Tumor
Published in Shikha Agrawal, Manish Gupta, Jitendra Agrawal, Dac-Nhuong Le, Kamlesh Kumar Gupta, Swarm Intelligence and Machine Learning, 2022
The exact causes of brain tumors are still unknown despite extensive research. Some of the causes and risk factors discussed in [3] are: Some of the brain tumors can be genetically inherited. The risk of developing a tumor increases if many family members have suffered from it in the past.Exposure to ionizing radiation increases the risk of tumors. The radiation may be due to X-rays or CT scans, nuclear plants, power lines and mobile phones. Similarly repeated exposure to harmful chemicals like nickel or cadmium compounds, tobacco smoke and arsenic compounds may put a person to the risk of developing a brain tumor.The risk of getting a brain tumor increases with age.Obesity or being overweight is also considered to be one of the risk factors in getting some types of brain tumors.
An efficient brain tumor classification using MRI images with hybrid deep intelligence model
Published in The Imaging Science Journal, 2023
Annapareddy V. N. Reddy, Pradeep Kumar Mallick, B. Srinivasa Rao, Phaneendra Kanakamedala
In a faster RCNN technique, the greatest Detection and Accuracy are attained but processing a large dataset is challenging. Evaluation with real clinical MR image analysis and high-dimension feature extraction is needed to finalize the efficiency of the TK method. Moreover, even in the deep architecture, there need for better optimization techniques for good decision-making. CNN is effective at classifying and identifying tumours but it needs large training data. The prognosis for a malignant brain tumour relies on factors like location in the brain, size, and grade. A brain tumour may occasionally be treatable if discovered early enough, but it usually returns and cannot always be removed. Hence, with the examination of the literature work, this work addresses the use of optimization tactics in training the system for better detection efficiency. This work seeks to develop a new classification model for brain tumours along the following steps: Preprocessing, segmentation, Feature extraction, and tumour classification. An architectural design of the recommended system for classifying brain tumours is shown in Figure 1.
Computational modeling and simulation of stenosis of the cerebral aqueduct due to brain tumor
Published in Engineering Applications of Computational Fluid Mechanics, 2022
Uzair Ul Haq, Ali Ahmed, Zartasha Mustansar, Arslan Shaukat, Sasa Cukovic, Faizan Nadeem, Saadia Talay, M. Junaid Iqbal Khan, Lee Margetts
Brain tumors can be benign or malignant. Compressive forces of the brain tumor may constrict the flow of cerebrospinal fluid (CSF), thereby causing stenosis of the cerebral aqueduct (CA). Likewise, during stenosis of the CA, obstructive hydrocephalus (which is a direct consequence of the constriction caused by brain tumor on the walls of the CA) can be seen as well. It is important to understand the core mechanisms of stenosis of the CA, and the nature, pathophysiology and biomechanics of the brain tumor and obstructive hydrocephalus, along with their relationship with each other. The study of stenosis of the CA primarily helps in understanding the increase in intracranial pressure (ICP) under particular circumstances. According to a survey conducted by CancerNet (2021), around 23,890 adults in the USA would be diagnosed with brain cancers in 2021; furthermore, every year about a million Americans are affected by hydrocephalus (Hydrocephalus Association, 2021). Stenosis of the CA is an important domain and a topical area for clinical discussion. Continuous monitoring of CSF pressure (and ICP) inside the cranium usually involves surgical interventions. The invasive mechanisms for clinically sensitive procedures are risky and cannot be performed as a matter of routine. However, a numerical model may overcome this clinical and practical limitation in a non-invasive manner. This would provide clinicians with better analytic methods to understand the interaction of the brain tumor with the walls of the CA and its effects, including stenosis, without surgical intervention.
Research perspective and review towards brain tumour segmentation and classification using different image modalities
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2022
A brain tumour is caused by the mass of abnormal tissues that are developed in the brain. These tissues in the brain affect the skull regions and force them to stop normal brain functions (Popuri et al. 2012). These tissues can be defined as intracranial lesions, and it leads to intracranial pressure in the skull regions. Brain tumours are categorised into two types namely, benign and malignant tumours (Nanthagopal and Rajamony 2012). The benign types are known to be non-cancerous that are curable but sometimes grow back. On the other hand, the malignant types are said to be cancerous, which causes other healthy tissue in the brain to be affected at a faster rate. So, it is most essential to identify and classify brain tumours as benign and malignant types to precede the treatment for recovering the health of the patients (Rajendran and Dhanasekaran 2012). These brain tumours can be detected through various medical image modalities such as MRI, Positron Emission Tomography (PET), Computed Tomography (CT), etc. Here, MRI is defined as a non-invasive method for diagnosing the brain tumour that utilises radiofrequency pulses and magnetic fields to show the internal body structure. These MRIs are divided into three types, namely, “T1 weighted, T2 weighted, and Fluid Attenuated Inversion Recovery (FLAIR)” for brain tumour detection (Xia et al. 2012a). Some other image modalities are also used in brain tumour detection models and produce satisfactory results for tumour detection (Giridhar et al. 2020).