The objective concerning this study is to improve the veracity of brain Cancer diagnosis and segmentation, accompanying the aim of aiding physicians in recognizing specific brain tumors. Brain tumors are continuous neoplasms within the brain. These tumors are caused by uncontrolled progress of abnormal containers. Classification of brain tumors is divided established the location of the lump, the type of tissue produced, and either the tumor is diseased (malignant) or benign (mild) and several additional considerations. In addition, a surgical biopsy of the doubtful tissue (carcinoma) is required to obtain more news about the type of tumor. Biopsy takes 10 to 15 days for lab testing. With the advantages of machine intelligence algorithms, especially the CNN design in classifying brain tumors and contour discovery, this research was conducted on the conduct of machine learning on MRI image results for cases with mind tumor using transfer education EfficientNet-B7 and U-Net.
Author(s) Details:
Antonius Fajar Adinegoro,
Department of Physics, Udayana University, Bali, Indonesia.
Gusti Ngurah Sutapa,
Department of Physics, Udayana University, Bali, Indonesia.
Anak Agung Ngurah Gunawan,
Department of Physics, Udayana University, Bali, Indonesia.
Ni Kadek Nova Anggarani,
Department of Physics, Udayana University, Bali, Indonesia.
Putu Suardana,
Department of Physics, Udayana University, Bali, Indonesia.
I. Gde Antha Kasmawan,
Department of Physics, Udayana University, Bali, Indonesia.
Please see the link here: https://stm.bookpi.org/RATMCS-V1/article/view/10689
Keywords: Convolutional neural network, U-Net, EfficientNet-B7, machine learningbrain tumor