TY  - JOUR
T1  - A New Deep Learning Method to Reconstruct and Estimate High
Complex Features from the Presented MR Image
AU - Saeed Alotaibi, Nouf 
JO  - Journal of Engineering and Applied Sciences
VL  - 15
IS  - 6
SP  - 1589
EP  - 1597
PY  - 2020
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2020.1589.1597
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2020.1589.1597
KW  - Fine-tuned deep learning
KW  -visualization
KW  -dynamic MR image reconstruction
KW  -MR image synthesis
KW  -framework
AB  - This study shows an effective deformable complex 3D image reconstruction and image synthesis
technique by consolidating needed high-level features from Convolutional Neural Network (CNN) system. By
recognize inherent deep feature representations in image patches for morphological changes in medicinal
imaging information discovery. Utilizing the ADNI and LONI imaging datasets, image reconstruction and
synthesis performance was verified with two existing design. Various performance measurements, High
Frequency Error Norm (HFEN), Mean Squared Error (MSE), peak Signal-to-Noise Ratio (PSNR), Structural
Similarity Index (SSI) are utilized to inspect different dataset. A deformable image reconstruction and synthesis
strategy that uses conventional features has low value of MSE and HFEN. Likewise, to reveal the adaptability
of the proposed image reconstruction and synthesis system, synthesis and reconstruction experiments were
directed on 7T cerebrum MR image. As presented in the paper outcomes, the proposed method can accomplish
predominant performance compared with other cutting-edge techniques with either low or high-level features
in terms of the synthesis and reconstruction rate. In all investigations, the outcome shows that the proposed
image synthesis and reconstruction framework reliably exhibited progressively precise outcomes when
contrasted with best in class. Hence, it can be used for possible precise image reconstruction and synthesis
related applications.
ER  -