TY - GEN
T1 - Brain Tumor Identification and Classification using a Novel Extraction Method based on Adapted Alexnet Architecture
AU - Guru, Prasad M.S.
AU - Praveen, Gujjar J.
AU - Dodmane, Radhakrishna
AU - Sardar, Tanvir H.
AU - Ashwitha, A.
AU - Yeole, Ashwini N.
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Brain tumours are caused by the aberrant development of cells, which is what leads to their formation. It is one of the primary factors contributing to death in adults all over the world. Millions of lives could be saved via earlier detection of brain tumours. An increased survival rate may be possible if brain tumours are detected by MRI at an earlier stage. MRI aids in the treatment process by providing a clearer image of the tumour. It is of utmost importance to detect, segment, and extract contaminated tumour areas from MRI scans, but this is a massive and time-consuming task that requires the skill of radiologists or clinical professionals. In this article, a modified version of the Alexnet architecture is provided for the purpose of identifying and classifying brain tumours through the use of a productive segmentation strategy. The efficacy of the proposed approach is illustrated by numerical results showing almost 87.38% accuracy in recognising aberrant and normal tissue from brain MRI images. The goal of this work is to detect tumours at an earlier stage than is currently possible, and the given strategy performed better than competing methods. .
AB - Brain tumours are caused by the aberrant development of cells, which is what leads to their formation. It is one of the primary factors contributing to death in adults all over the world. Millions of lives could be saved via earlier detection of brain tumours. An increased survival rate may be possible if brain tumours are detected by MRI at an earlier stage. MRI aids in the treatment process by providing a clearer image of the tumour. It is of utmost importance to detect, segment, and extract contaminated tumour areas from MRI scans, but this is a massive and time-consuming task that requires the skill of radiologists or clinical professionals. In this article, a modified version of the Alexnet architecture is provided for the purpose of identifying and classifying brain tumours through the use of a productive segmentation strategy. The efficacy of the proposed approach is illustrated by numerical results showing almost 87.38% accuracy in recognising aberrant and normal tissue from brain MRI images. The goal of this work is to detect tumours at an earlier stage than is currently possible, and the given strategy performed better than competing methods. .
UR - http://www.scopus.com/inward/record.url?scp=85159474312&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85159474312&partnerID=8YFLogxK
U2 - 10.1109/ISCON57294.2023.10112075
DO - 10.1109/ISCON57294.2023.10112075
M3 - Conference contribution
AN - SCOPUS:85159474312
T3 - 2023 6th International Conference on Information Systems and Computer Networks, ISCON 2023
BT - 2023 6th International Conference on Information Systems and Computer Networks, ISCON 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th International Conference on Information Systems and Computer Networks, ISCON 2023
Y2 - 3 March 2023 through 4 March 2023
ER -