TY - JOUR
T1 - Cerebral micro-bleeding detection based on densely connected neural network
AU - Wang, Shuihua
AU - Tang, Chaosheng
AU - Sun, Junding
AU - Zhang, Yudong
N1 - Publisher Copyright:
© 2019 Wang, Tang, Sun and Zhang.
PY - 2019
Y1 - 2019
N2 - Cerebral micro-bleedings (CMBs) are small chronic brain hemorrhages that have many side effects. For example, CMBs can result in long-term disability, neurologic dysfunction, cognitive impairment and side effects from other medications and treatment. Therefore, it is important and essential to detect CMBs timely and in an early stage for prompt treatment. In this research, because of the limited labeled samples, it is hard to train a classifier to achieve high accuracy. Therefore, we proposed employing Densely connected neural network (DenseNet) as the basic algorithm for transfer learning to detect CMBs. To generate the subsamples for training and test, we used a sliding window to cover the whole original images from left to right and from top to bottom. Based on the central pixel of the subsamples, we could decide the target value. Considering the data imbalance, the cost matrix was also employed. Then, based on the new model, we tested the classification accuracy, and it achieved 97.71%, which provided better performance than the state of art methods.
AB - Cerebral micro-bleedings (CMBs) are small chronic brain hemorrhages that have many side effects. For example, CMBs can result in long-term disability, neurologic dysfunction, cognitive impairment and side effects from other medications and treatment. Therefore, it is important and essential to detect CMBs timely and in an early stage for prompt treatment. In this research, because of the limited labeled samples, it is hard to train a classifier to achieve high accuracy. Therefore, we proposed employing Densely connected neural network (DenseNet) as the basic algorithm for transfer learning to detect CMBs. To generate the subsamples for training and test, we used a sliding window to cover the whole original images from left to right and from top to bottom. Based on the central pixel of the subsamples, we could decide the target value. Considering the data imbalance, the cost matrix was also employed. Then, based on the new model, we tested the classification accuracy, and it achieved 97.71%, which provided better performance than the state of art methods.
KW - Cmb detection
KW - Cost matrix
KW - Deep learning
KW - Densenet
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85066241617&partnerID=8YFLogxK
U2 - 10.3389/fnins.2019.00422
DO - 10.3389/fnins.2019.00422
M3 - Article
AN - SCOPUS:85066241617
SN - 1662-4548
VL - 13
JO - Frontiers in Neuroscience
JF - Frontiers in Neuroscience
IS - MAY
M1 - 422
ER -