High Frequency Coefficient Effect on Image Based on Contourlet Transformation

Oleiwi, Zahraa Ch.; Thanoon, Kifaa Hadi; Alsaif, Khalil I.

doi:10.1109/iccista.2019.8830649

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This could then be saved as a detector and applied to the test image datasets for validation and testing. Set the maximum number of epochs for training to 20, and use a mini-batch with 16 observations at each iteration [17], [18].…”

Section: Methodsmentioning

confidence: 99%

Alzheimer’s diseases classification using YOLOv2 object detection technique

Al-jabar

Basheer

Alsaif

2022

IJRES

View full text Add to dashboard Cite

Early diagnosis and treatment of Alzheimer's disease (AD) is necessary for the patient safety. Computer-aided diagnosis (CAD) is a useful tool for early diagnosis of Alzheimer's disease (AD). We make two contributions to the solution of this problem in this study. To begin with, we are the first to propose an Alzheimer's disease diagnosis solution based on the MATLAB that does not require any magnetic resonance imaging (MRI) pre-processing. Second, we apply recent deep learning object detection architectures like YOLOv2 to the diagnosis of Alzheimer's disease. A new reference data set containing 300 raw data points for Alzheimer's disease detection/normal control and severe stage (MCI/AD/NC) deep learning is presented. Primary screening cases for each category from the Alzheimer's disease neuroimaging initiative (ADNI) dataset. The T1-weighted Dicom MRI slice in the MP-Rage series in 32-bit DICOM image format and 32-bit PNG are included in this dataset. By using MATLAB’s image label tool, the test data were marked with their appropriate class label and bounding box. It was possible to achieve a detection accuracy of 0.98 for YOLOv2 in this trial without the usage of any MRI preprocessing technology.

show abstract

Section: Methodsmentioning

confidence: 99%