What are brain tumors?

Answer from top 2 papers

Brain tumors are abnormal cell aggregations in brain tissue, which can be either cancerous or noncancerous (). The most common types include Gliomas, Meningiomas, and Pituitary tumors ( and ). These tumors are among the most fatal cancers, with various types classified based on location, texture, and shape, and their accurate classification is critical for determining the appropriate treatment ((Kumar et al., 2023) and (Richterová et al., 2014)).
Interestingly, while manual classification of brain tumors is time-consuming and prone to errors, advancements in artificial intelligence (AI), particularly deep learning methods like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), have shown high accuracy in tumor detection and classification from MRI images ( and (Kumar et al., 2023)). These automated methods can significantly aid in early detection, which is crucial for patient recovery ( and ).
In summary, brain tumors are a significant medical concern due to their complexity and the necessity for precise classification for treatment. The development of AI-based diagnostic tools, such as CNNs and RNNs, has improved the accuracy and speed of tumor classification from MRI images, offering a promising direction for enhancing patient outcomes ( and (Kumar et al., 2023)).

Source Papers

18
10.12694/scpe.v24i1.2088

Multi-class Brain Tumor Classification and Segmentation using Hybrid Deep Learning Network Model

Apr 19, 2023
Scalable Computing: Practice and Experience
Parasa Rishi Kumar + 4 more +4

Brain tumor classification is a significant task for evaluating tumors and selecting the type of treatment as per their classes. Brain tumors are diagnosed using multiple imaging techniques. However, MRI is frequently utilized since it provides greater image quality and uses non-ionizing radiation. Deep learning (DL) is a subfield of machine learning and recently displayed impressive performance, particularly in segmentation and classifying problems. Based on convolutional neural network (CNN), a Hybrid Deep Learning Network (HDLN) model is proposed in this research for classifying multiple types of brain tumors including glioma, meningioma, and pituitary tumors. The Mask RCNN is used for brain tumor classification. We used a squeeze-and-excitation residual network (SE-ResNet) for brain tumor segmentation, which is a residual network (ResNet) with a squeeze-and-excitation block. A publicly available research dataset is used for testing the proposed model for experiment analysis and it obtained an overall accuracy of 98.53%, 98.64% sensitivity and 98.91% specificity. In comparison to the most advanced classification models, the proposed model obtained the best accuracy. For multi-class brain tumor diseases, the proposed HDLN model demonstrated its superiority to the existing approaches.

11
10.4149/gpb_2014007

Most frequent molecular and immunohistochemical markers present in selected types of brain tumors.

Jan 01, 2014
General physiology and biophysics
Romana Richterová + 9 more +9

Tumors of brain tissue and meninges create a heterogeneous group with various biological behavior, therapy management and differing prognosis. Some of these do not require treatment, some can be cured by surgery and some are rapidly fatal despite treatment. Despite huge progress in tumor research, innovations in diagnostic tools and therapy, prognosis remains, in case of malignant tumor types, very serious. There has been an increased understanding of molecular abnormalities occurring in primary brain tumors. Genome-wide analyses of tumors have improved the knowledge in tumor biology. The aim of the research is to explain the oncogenesis features thus leading to the use of new therapeutic modalities in order to prolong survival rate of patients and at the same time providing satisfactory life quality. This article offers a short review of the basic genetic alterations present with some histological types of brain tumors.