China
Africa
Explore chapters and articles related to this topic
Computer-aided Diagnosis (CAD) System for Determining Histological Grading of Astrocytoma Based on Ki67 Counting
Published in Varun Bajaj, G.R. Sinha, Computer-aided Design and Diagnosis Methods for Biomedical Applications, 2021
Fahmi Akmal Dzulkifli, Maryam Ahmad Sharifuddin, Mohd Yusoff Mashor, Hasnan Jaafar
Generally, brain tumors can be divided into two categories. These categories are known as primary brain tumors and metastatic brain tumors [7]. The primary brain tumor is defined as a tumor originally derived from the neoplastic cells of the brain. A metastatic or also known as a secondary brain tumor is a tumor that begins to develop elsewhere in the body and then spreads to the brain to form a new tumor. A primary brain tumor can be divided into two types: glioma and non-glioma. A glioma tumor is a tumor that grows from a glial cell. Glial cells act as supportive tissues in the brain, and they are responsible for providing support and protection for the neurons. Astrocytes, oligodendrocytes, ependymal cells, Schwann cells, satellite cells, and microglia are examples of supporting tissues in the brain [1]. Examples of glioma tumors include astrocytoma, oligodendroglioma, ependymoma, and brain stem glioma. Non-glioma tumors are tumors that form and arise from cells within the brain that are not glial cells. Examples of types of non-glioma tumors are meningioma, medulloblastoma, craniopharyngioma, and pineal gland and pituitary gland tumors.
1
Published in Mara Cercignani, Nicholas G. Dowell, Paul S. Tofts, Quantitative MRI of the Brain: Principles of Physical Measurement, 2018
Another critical application for 1H MRS is the ability to predict survival. The majority of studies that have been performed to date have focused on patients with glioblastoma, which is the most common and most malignant type of glioma with a median overall survival of 15 months (Stupp et al., 2005). A series of studies have examined the predictive value of metabolic parameters from 3D long TE MRSI (Figure 12.15b) in patients with newly diagnosed glioblastoma at different time points (such as before and after receiving surgical resection or radiation therapy) and for different types of chemotherapy (such as temozolomide and anti-angiogenic agents) (Crawford et al., 2009; Li et al., 2013; Nelson et al., 2016a, 2016b; Saraswathy et al., 2009). Patients with high levels of lactate and lipid in the region with abnormal CNI (McKnight et al., 2001) had worse overall survival in these studies.
Nanobased Cns Delivery Systems
Published in Anil K. Sharma, Raj K. Keservani, Rajesh K. Kesharwani, Nanobiomaterials, 2018
Rahimeh Rasouli, Mahmood Alaei-Beirami, Farzaneh Zaaeri
Cancer is the most important cause of death all over the world. Brain cancers have significant stage in man death statistics. Glioma, as a brain cancer, is being treated with different technics include mix of surgery, radiotherapy, systematic chemotherapy and photodynamic therapy, despite all improving advances, patients survive for several months, only (Stupp et al., 2006). Cancer is not unique in CNS problems so, that increasing trend of neuro-degenerative disease, following increasing life expectancy besides aging of HIV infected patients, and CNS infections, especially hidden HIV in CNS acting like Trojan horse, is being considered in CNS drug delivery studies. BBB is first of the important obstacles in CNS therapy which could be leaved behind by potential nanosystems or automated drugs (Guarnieri et al., 2014).
An efficient glioma classification and grade detection using hybrid convolutional neural network-based SVM model
Published in The Imaging Science Journal, 2023
New imaging technologies [6, 7] are developed and met with ever-increasing quantities of data to diagnose and plan therapy. In such a circumstance, the employment of automated and intelligent technology is becoming increasingly important. Medical image processing techniques have become very familiar with efficient ML [8] with artificial and computer intelligence in recent years. The gold standard for brain tumor categorization is now histopathology analysis. ML techniques [9] combined with the extraction of essential characteristics from magnetic resonance imaging (MRI) may replace invasive tumor classification methods. Most diagnostic testing for brain cancers [10], particularly gliomas, has relied on MRI and histological studies. The typical way of diagnosis and prognosis has been histopathological examination. Following surgery, the histology findings are helpful to identify the adjuvant therapy options. But doing this study necessitates an intrusive biopsy process, which is one of the driving reasons for developing MRI-based diagnostic methods [11], mainly when the dangers of biopsy are great. Radiological imaging's diagnostic [12] and therapeutic are used for fast expansion. This has been aided by developing novel image capture modalities and sequences that enable recording more minor anatomical elements at better resolution. The burden of manual diagnostics has been reduced with automated techniques. ML techniques have been used to automate the analysis of each image characteristic.
Improving multi-scale attention networks: Bayesian optimization for segmenting medical images
Published in The Imaging Science Journal, 2023
Brain Magnetic Resonance Imaging (MRI) Dataset [28]: The Brain MRI dataset, as shown in Figures 6(b) and 6(c), contains Brain MRI images together with manual abnormality segmentation masks. This dataset is originally retrieved from The Cancer Genome Atlas Low Grade Glioma (TCGA-LGG). Glioma is a type of tumour that starts in the glial cells of the brain or the spine. The selected samples highlight the variety of colours and image sizes present in the dataset. It is arduous even for humans to exactly pinpoint or locate the origin of glioma in such images. On top of that many images do not have any segmentation masks, making the training of deep learning algorithms more challenging. The dataset contains about 3929 image mask pairs of dimensions .
Modified CNN Architecture for Efficient Classification of Glioma Brain Tumour
Published in IETE Journal of Research, 2022
J. Angelin Jeba, S. Nirmala Devi, M. Meena
Glioma is a type of brain tumour that is grouped based on its growth pattern, behaviour, and genetic mutations. These tumours can be categorized as benign or malignant [5]. It affects the functions of the brain and will become life-threatening to the person depending on its location and growth. The detection of the type of glioma is needed to determine the treatment method and prognosis. Some of the glioma treatment methods include surgery, radiation therapy, chemotherapy, targeted therapy and experimental clinical trials [5]. According to World Health Organization (WHO), glioma tumour grading includes two types, namely low-grade tumours and high-grade tumours. Our work is focused on low-grade brain tumours and high-grade brain tumours as shown in Figure 1.