Multi-class segmentation of brain tumor using Convolution Neural Network
MetadataShow full item record
In this report a fully Convolution Neural Network (CNN) architecture is used to segment multi-modal Brain Tumors from Magnetic Resonance (MR) images. Due to the challenges in manual segmentation, computerized brain tumor segmentation is one of the most important challenges in medical imaging. The fully convolutional structure of the network makes it faster than any network with a dense fully connected layer. The two phase training and entropy sampling of data makes it easier to learn tumor boundaries and overcome the data imbalance problem.
Showing items related by title, author, creator and subject.
Cerebellar tumor location as a predictor of neurocognitive functioning among survivors of pediatric brain tumors Mitchell Von Buttlar, Ashlee Beth (2016-12)The literature has clearly demonstrated that the cerebellum serves as a major processing center in the brain for many complex functional pathways ranging from attention and learning to emotions and affect. Research is now ...
Jnk2 Effects on Tumor Development, Genetic Instability and Replicative Stress in an Oncogene-Driven Mouse Mammary Tumor Model Chen, Peila; O'Neal, Jamye F.; Ebelt, Nancy D.; Cantrell, Michael A.; Mitra, Shreya; Nasrazadani, Azadeh; Vandenbroek, Tracy L.; Heasley, Lynn E.; Van Den Berg, Carla L. (Public Library of Science, 2010-05-03)Oncogenes induce cell proliferation leading to replicative stress, DNA damage and genomic instability. A wide variety of cellular stresses activate c-Jun N-terminal kinase (JNK) proteins, but few studies have directly ...
Huang, Yu-Yen, active 21st century (2013-12)Circulating tumor cells (CTCs) are known to escape from the primary tumor site and may settle down at the distant organ to grow a second tumor. CTCs are one of causes initiating carcinoma metastasis. Detection of CTCs has ...