METHOD FOR DETECTING BRAIN TUMOURS IN MAGNETIC RESONANCE IMAGES (MRIS)

Abstract

ABSTRACT A method (100) for detecting brain tumours in magnetic resonance images (MRIs). Further, the method comprising acquiring a set of magnetic resonance images of a patient's brain. Further, the method (100) comprising the steps of pre-processing the acquired images to enhance image quality and reduce noise. Further, the method (100) comprising the steps of utilizing a deep learning model, specifically a convolutional neural network (CNN), to analyze the pre-processed images and classify regions of interest as either tumorous or non-tumorous. Further, the method (100) comprising the steps of outputting the classification results, including the location, size, and shape of any detected tumours, for clinical diagnosis and treatment planning.

Specification

Description:
FIELD OF THE DISCLOSURE
[0001] This invention generally relates to the field of medical imaging and, in particular, to a method for detecting brain tumours using magnetic resonance images through advanced deep learning techniques that enhance diagnostic accuracy while minimizing reliance on human interpretation.
BACKGROUND
[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
[0003] Brain tumours represent a significant health challenge, with increasing incidence rates globally. Traditional diagnostic methods, such as manual analysis , Claims:1. A method (100) for detecting brain tumours in magnetic resonance images (MRIs), the method comprising the steps of:
acquiring a set of magnetic resonance images of a patient's brain;
pre-processing the acquired images to enhance image quality and reduce noise;
utilizing a deep learning model, specifically a convolutional neural network (CNN), to analyze the pre-processed images and classify regions of interest as either tumorous or non-tumorous; and
outputting the classification results, including the location, size, and shape of any detected tumours, for clinical diagnosis and treatment planning.

2. The method (100) as claimed in claim 1, further comprising the step of employing data augmentation techniques during the training of the convolutional neural network to improve classification accuracy by increasing the diversity of the training dataset.

Documents