Cerebral Neoplasm Detection from MRI using CNN

EasyChair Preprint 12428

Abstract

The effective treatment of cerebral carcinoma depends on the early and precise diagnosis of brain malignancies. Timely diagnosis not only facilitates the development of more effective treatments but also has the potential to save lives. In recent years, machine learning algorithms have gained prominence in the field of medical imaging and information processing, providing a powerful alternative to the labor-intensive and error-prone manual  diagnosis of brain tumors. One of the key methods applied in this context is the use of convolutional neural networks (CNNs), which have demonstrated remarkable capabilities in extracting meaningful features from medical imagery. These extracted features are then utilized in the classification of MRI scans to determine whether a neural tumor is present or not. The integration of deep neural networks, specifically CNN-based models, has demonstrated potential for improving brain tumor detection accuracyultimately improving patient outcomes. The proposed work presented in this abstract revolves around the utilization of a deep neural network, with a focus on a CNN-based model. This model is designed to classify MRI scans, enabling healthcare professionals to swiftly and correctly detect the existence of brain malignancies. By automating the diagnostic process and reducing the reliance on manual interpretation, this approach offers the potential to revolutionize the field of cerebral carcinoma diagnosis, making it more efficient and less susceptible to human error.

Keyphrases: Brain Tumor Detection, Convolutional Neural Networks, MRI(magnetic resonance imaging)

@booklet{EasyChair:12428,
  author    = {Anup Dange and Satyajit Bahir and Rajshri Lomate and Tanuja Thakar},
  title     = {Cerebral Neoplasm Detection from MRI using CNN},
  howpublished = {EasyChair Preprint 12428},
  year      = {EasyChair, 2024}}