AdaptAhead Optimization Algorithm for Learning Deep CNN Applied to MRI Segmentation

Hoseini, Farnaz; Shahbahrami, Asadollah; Bayat, Peyman

doi:10.1007/s10278-018-0107-6

Cited by 49 publications

(33 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adaptive gradient descent in optimization provides adaptation to the previous gradient. Acceleration by Nesterov's momentum has been combined with the adaptive gradient descent because momentum helps to improve the convergence of adaptive gradient methods . The momentum term (ie,

{‖δ_{i}‖}_{s_{i *}}^{2}

in Equation ) accelerates convergence of deterministic components, while adaptive gradient concentrates over the stochastic components.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Acceleration by Nesterov's momentum has been combined with the adaptive gradient descent because momentum helps to improve the convergence of adaptive gradient methods. 30,64 The momentum term (ie, δ i k k 2 s i* in Equation 3) accelerates convergence of deterministic components, while adaptive gradient concentrates over the stochastic components. Also, momentum leads to low complexity on the bound of deterministic part compared with the bound of adaptive gradient.…”

Section: Optimization In the 3d Cnnmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosis of Alzheimer's disease with Sobolev gradient‐based optimization and 3D convolutional neural network

Göçeri

2019

Numer Methods Biomed Eng

View full text Add to dashboard Cite

Alzheimer's disease is a neuropsychiatric, progressive, also an irreversible disease. There is not an effective cure for the disease. However, early diagnosis has an important role for treatment planning to delay its progression since the treatments have the most impact at the early stage of the disease. Neuroimages obtained by different imaging techniques (for example, diffusion tensor‐based and magnetic resonance‐based imaging) provide powerful information and help to diagnose the disease. In this work, a deeply supervised and robust method has been developed using three dimensional features to provide objective and accurate diagnosis from magnetic resonance images. The main contributions are (a) a new three dimensional convolutional neural network topology; (b) a new Sobolev gradient‐based optimization with weight values for each decision parameters; (c) application of the proposed topology and optimizer to diagnose Alzheimer's disease; (d) comparisons of the results obtained from the recent techniques that have been implemented for Alzheimer's disease diagnosis. Experimental results and quantitative evaluations indicated that the proposed network model is able to achieve to extract desired features from images and provides automated diagnosis with 98.06% accuracy.

show abstract

{‖δ_{i}‖}_{s_{i *}}^{2}

in Equation ) accelerates convergence of deterministic components, while adaptive gradient concentrates over the stochastic components.…”

Section: Proposed Methodsmentioning

confidence: 99%

Section: Optimization In the 3d Cnnmentioning

confidence: 99%

Diagnosis of Alzheimer's disease with Sobolev gradient‐based optimization and 3D convolutional neural network

Göçeri

2019

Numer Methods Biomed Eng

View full text Add to dashboard Cite

show abstract

“…Specically, a number of historical data is input to iteratively update parameters until convergence, and learning method utilized here is the RMSProp. 48 Due to the limitation of textual length, detailed iterative process is le out. Aer that, a complete prediction mechanism is established for outlet indexes.…”

Section: Decodingmentioning

confidence: 99%

Data-driven prediction and control of wastewater treatment process through the combination of convolutional neural network and recurrent neural network

Guo

Wang

et al. 2020

RSC Adv.

View full text Add to dashboard Cite

show abstract

“…After deep learning, especially the emergence of convolutional neural networks, this method of auto-learning features using convolutional neural networks has driven the rapid development of many visual tasks, including segmentation algorithms of medical exercise rehabilitation image. Hoseini et al [10] applied the study of deep learning algorithms to the segmentation of neural cell images. Xiao et al [11] applied the deep learning algorithm to the benign and malignant discrimination of breast tumors.…”

Section: Related Workmentioning

confidence: 99%

Segmentation Algorithm of Medical Exercise Rehabilitation Image Based on HFCNN and IoT

Ding

Ren

2019

IEEE Access

View full text Add to dashboard Cite

Deep learning has achieved great success in the field of computer vision, and the precision in image classification and image detection has surpassed humans. Therefore, this paper combines deep learning and medical image segmentation, focusing on how to improve the accuracy and speed of segmentation algorithm of medical exercise rehabilitation image. Aiming at the shortcomings of traditional medical image recognition methods, a medical exercise rehabilitation image segmentation algorithm based on hierarchical features of convolutional neural networks is proposed, this paper calls it as hierarchical features of convolutional neural networks (HFCNN). The algorithm firstly samples the convolution output of multiple layers in the convolutional neural network to a unified scale and combines them to construct a hierarchical feature. This hierarchical feature combines the structural information of objects contained in the shallow layer of the network with the semantic information of objects contained in the deep layers of the network, so it has a strong ability to express. Secondly, the image can be segmented into multiple super pixels by the super pixel segmentation algorithm. The classifier is trained using the hierarchical features of the super pixel, and then the classification result is mapped back to the pixel. Finally, a fully connected conditional random field algorithm including one-potential potential energy and paired potential energy is constructed. The corresponding energy function is used to smooth the classification result of the pixel, and the regional consistency and continuity of the pixel mark are improved. Compared with many classical convolutional neural network algorithms, this algorithm not only accelerates the network convergence speed, shortens the training time, but also significantly improves the accuracy of segmentation algorithm of medical exercise rehabilitation image, showing good practical value.

show abstract

AdaptAhead Optimization Algorithm for Learning Deep CNN Applied to MRI Segmentation

Cited by 49 publications

References 16 publications

Diagnosis of Alzheimer's disease with Sobolev gradient‐based optimization and 3D convolutional neural network

Diagnosis of Alzheimer's disease with Sobolev gradient‐based optimization and 3D convolutional neural network

Data-driven prediction and control of wastewater treatment process through the combination of convolutional neural network and recurrent neural network

Segmentation Algorithm of Medical Exercise Rehabilitation Image Based on HFCNN and IoT

Contact Info

Product

Resources

About