MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641090001 A) filed by Mrs. T Aruna Jacintha; Mrs. Ch V Nagajyothi; Mr. Gopinath K; Mrs. Sumitha V; Mrs. Kumudashree H S; and Mr. Rakesh D S on July 24, 2026, for Brain Tumor Detection Using Deep Learning.
Inventors include Mrs. T Aruna Jacintha; Mrs. Ch V Nagajyothi; Mr. Gopinath K; Mrs. Sumitha V; Mrs. Kumudashree H S; and Mr. Rakesh D S.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: Magnetic resonance imaging is extensively employed for the assessment of tumours. Nonetheless, MRI produces vast amounts of data, rendering manual segmentation challenging within a practical timeframe, hence constraining the application of precise measurements in clinical settings. Brain tumours are among the most perilous neoplasms, as they may arise from the proliferation of cells within or next to the brain. A brain tumour is defined as any abnormal aggregation of cells within or adjacent to the brain that may become malignant. A tumour is propelled by swift and unregulated cellular proliferation in the brain. If not addressed in the early stages, it may become lethal. Notwithstanding various substantial endeavours and promising results, precise segmentation and classification remain problematic. The identification of brain tumours is considerably hindered by variations in tumour location, morphology, and size. Recent advancements in Deep Learning (DL) methodologies have gained traction in creating automated systems that can efficiently diagnose or categorise brain tumours with enhanced accuracy and reduced time. Deep learning facilitates a pre-trained Convolutional Neural Network (CNN) model tailored for medical imaging, particularly for the classification of brain tumours. The identification of a brain tumour is a protracted process that significantly depends on the radiologist's expertise and proficiency. The volume of data requiring management has surged significantly due to the rise in patient numbers, rendering previous methods both expensive and inefficient. Numerous scholars examined an array of algorithms for the detection and classification of brain tumours that were both precise and rapid. The integration of advanced prediction, automated feature extraction, and enhanced predictability establishes the model as a significant application of neural network methodologies for brain tumour classification, with considerable promise for advancing medical imaging and clinical decision-making.
Disclaimer: Curated by HT Syndication.
