Detecting cerebral microbleeds with transfer learning

Brain Age Prediction of Children Using Routine Brain MR Images via Deep Learning

“…Of these, convolutional neural network (CNN) of deep learning has achieved great success with superior performance beyond human experts in many computer vision and speech recognition tasks since it was put forward (15)(16)(17)(18)(19)(20). In the field of medical image analysis, CNN-based method has been also proposed for disease diagnosis and lesion detection with high performance in accuracy, such as the classification and detection of lung nodules (21,22), the recognition of melanoma (23), the detection of cerebral microbleeds (24)(25)(26), as well as the classification of Alzheimer's disease (27,28). In addition, brain age prediction based CNN model has been proved to be a reliable and heritale biomarker of brain aging and can be used to indicate the risk of brain degenerative diseases (29,30), whereas it has not been reported in young children up to now.…”

Automated detection of cerebral microbleeds in MR images: A two-stage deep learning approach

“…Hence, similar processing time per subject of 0.69 s for YOLO was recorded for both LR and HR data. In addition, the quite high performances in terms of sensitivity and precision achieved by ( Wang et al, 2019 , Hong et al, 2019 ) could be due to the very huge number of the utilized microbleeds compared to other studies. ( Wang et al, 2019 ) extracted 68,847 CMBs and over 56 million Non-CMBs from 20 patients, while ( Hong et al, 2019 ) extracted 4287 CMBs from 10 subjects.…”

“…In addition, the quite high performances in terms of sensitivity and precision achieved by ( Wang et al, 2019 , Hong et al, 2019 ) could be due to the very huge number of the utilized microbleeds compared to other studies. ( Wang et al, 2019 ) extracted 68,847 CMBs and over 56 million Non-CMBs from 20 patients, while ( Hong et al, 2019 ) extracted 4287 CMBs from 10 subjects. In the FPs reduction stage, the execution time per subject was computed as a multiplication of the processing time of each 3D input patch via the 3D-CNN by the total number of false positives per subject (i.e., 155.5 in case of LR and 52.18 in case of HR).…”

“…They dispensed the candidate detection stage by using a sliding window over the entire MR image and achieved higher performance with overall sensitivity of 97.78% and classification accuracy of 97.71%. Similarly, Hong et al adapted the 2D-ResNet-50 for distinguishing the 2D CMBs patches retrieved by the sliding window from the non-CMBs, achieving a sensitivity of 95.71% and an accuracy of 97.46% ( Hong et al, 2019 ). However, utilizing a 2D sliding window strategy over the whole 3D MR volume per subject requires high computational burden and large execution time.…”

Teeth Category Classification by Fractional Fourier Entropy and Improved Hybrid Genetic Algorithm

“…Although back propagation is a good choice for training algorithm, it cannot guarantee to converge at the global best solution, because back propagation belongs to a greedy algorithm which depends on gradient descent. Therefore, we try to solve the training problem using optimization methods [ 23 – 28 ].…”