ITDS | SPMS

Brain Tumor Identification Via CNN Approach

Project Description
Supervisor

Tumors of the brain develop from irregular cell multiplication within the brain tissue and represent the second primary contributor to cancer-related fatalities (Badran et al., 2010). Key categories include non-cancerous (benign), cancerous (malignant), hormone-related (pituitary), and support-cell-based (glioma) varieties (Choudhary et al., 2022). Non-cancerous growths consist of atypical cells that remain localized without spreading to adjacent areas or distant body parts. These typically expand at a gradual pace, feature distinct margins, and pose fewer risks compared to aggressive forms (Goyal et al., 2021). Pituitary growths form in the endocrine gland situated near the brain's foundation, which oversees hormonal balance. Although mostly non-spreading, they may trigger endocrine disruptions or exert force on nearby neural elements, resulting in symptoms such as migraines or sight disturbances. Management often involves operative removal, targeted radiation, or pharmacological interventions (Armstrong et al., 2004). Cancerous masses comprise aberrant cells capable of infiltrating surrounding structures and disseminating through circulatory or lymphatic pathways. Such formations tend to advance swiftly and may prove fatal without prompt care (Sharmila et al., 2022). Gliomas emerge from glial elements that assist and safeguard neural cells in the central nervous system, potentially exhibiting either non-aggressive or aggressive traits (Gupta et al., 2023). Aggressive brain growths carry elevated mortality risks owing to their position in a crucial bodily structure. Despite their scarcity comprising just 1.8% of worldwide cancer cases (Abdellatef et al., 2021) innovations in deep learning (DL) and machine learning (ML) have advanced the assessment of diagnostic scans (Rahman & Islam, 2021). Diverse scan enhancement strategies are applied in this domain. Computerized identification through magnetic resonance imaging (MRI) is vital, as it supplies details on irregular tissues essential for therapeutic strategies (Soundarya et al., 2023). With ongoing AI developments, healthcare providers increasingly rely on DL frameworks alongside MRI for identifying neural growths (Goyal et al., 2021). MRI employs intense magnetic forces and radiofrequency signals to generate comprehensive internal visualizations (Cho et al., 2020). Clinicians utilize these depictions to deliver effective care for affected individuals. Advanced DL architectures, such as convolutional neural networks (CNNs) a subset of neural networks are effective for recognizing neural malignancies (Brindha et al., 2023).

Machine Learning: Machine Learning (ML) research in Computer Science and Information Technology focuses on the development of algorithms and models that enable computers to learn from data and improve their performance over time without being explicitly programmed. It is a subset of Artificial Intelligence that uses statistical techniques to give machines the ability to learn patterns, make decisions, and predict outcomes based on data. Supervised learning, a key area of ML research, involves training models on labeled data, where the input-output relationships are predefined. This method is widely used for tasks such as classification (e.g., spam detection) and regression (e.g., predicting house prices). Unsupervised learning, on the other hand, involves finding hidden patterns in data without predefined labels, with clustering and association being typical applications in areas such as customer segmentation and anomaly detection. Reinforcement learning is another area of ML that focuses on teaching agents to make decisions by interacting with their environment and receiving feedback in the form of rewards or penalties. It is often applied in robotics, game playing, and autonomous systems, where continuous learning and adaptation are required.