%0 Journal Article %1 noauthororeditor %A Regin, Steffi. R | Shynu T | S. Suman Rajest | R. %D 2023 %J CENTRAL ASIAN JOURNAL OF MEDICAL AND NATURAL SCIENCE %K Activation Convolutional FCNN, Network, Neural Segmentation, Sigmoid U-Net %N 6 %P 1326-1343 %T A Convolutional Neural Network with a U-Net for Brain Tumor Segmentation and Classification %U https://cajmns.centralasianstudies.org/index.php/CAJMNS/article/view/2234/2270 %V 4 %X An aberrant proliferation of live brain cells is known as a brain tumour. The development of this tumour within the skull disrupts regular brain function. Early detection is key when it comes to brain tumours; else, they can be fatal. The intricate anatomy of the brain, which can differ from one individual to another, makes tumour detection a difficult undertaking. One possible use of magnetic resonance (MR) imaging is the detection of brain tumours. It can be a tedious and time-consuming operation to accurately segregate tumour areas, though. Accurate tumour segmentation from a given brain MR picture is achieved by our programme using PyTorch, an AI and computer vision library for Python, in conjunction with a CNN (Convolutional Neural Network) based on U-nets. A second Fully Convolutional Neural Network is employed to categorise the tumour into one of its three main types meningioma, glioma, and pituitary tumor—based on the measured tumour area, intensity, form, and location.

@article{noauthororeditor, abstract = {An aberrant proliferation of live brain cells is known as a brain tumour. The development of this tumour within the skull disrupts regular brain function. Early detection is key when it comes to brain tumours; else, they can be fatal. The intricate anatomy of the brain, which can differ from one individual to another, makes tumour detection a difficult undertaking. One possible use of magnetic resonance (MR) imaging is the detection of brain tumours. It can be a tedious and time-consuming operation to accurately segregate tumour areas, though. Accurate tumour segmentation from a given brain MR picture is achieved by our programme using PyTorch, an AI and computer vision library for Python, in conjunction with a CNN (Convolutional Neural Network) based on U-nets. A second Fully Convolutional Neural Network is employed to categorise the tumour into one of its three main types meningioma, glioma, and pituitary tumor—based on the measured tumour area, intensity, form, and location.}, added-at = {2024-02-17T13:21:08.000+0100}, author = {Regin, Steffi. R | Shynu T | S. Suman Rajest | R.}, biburl = {https://www.bibsonomy.org/bibtex/2c6c71afd131130d4541a110056f1170d/centralasian_20}, interhash = {162dd23bc596a152b0a88ae9fb6cdb39}, intrahash = {c6c71afd131130d4541a110056f1170d}, issn = {2660-4159}, journal = {CENTRAL ASIAN JOURNAL OF MEDICAL AND NATURAL SCIENCE}, keywords = {Activation Convolutional FCNN, Network, Neural Segmentation, Sigmoid U-Net}, language = {english}, month = dec, number = 6, pages = {1326-1343}, timestamp = {2024-02-17T13:21:08.000+0100}, title = {A Convolutional Neural Network with a U-Net for Brain Tumor Segmentation and Classification}, url = {https://cajmns.centralasianstudies.org/index.php/CAJMNS/article/view/2234/2270}, volume = 4, year = 2023 }