Hidayat, Eka Putra Syarif
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Bahasa Inggris Nurbaiti, Nurbaiti; Hidayat, Eka Putra Syarif; Anwar, Khairil; Hermawan, Dudung; Izzuddin, Salman
Generation Journal Vol 8 No 1 (2024): Generation Journal
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/gj.v8i1.21601

Abstract

Early detection of breast cancer with computer assistance has developed since two decades ago. Artificial intelligence using the convolutional neural network (CNN) method has successfully predicted mammography images with a high level of accuracy similar to human brain learning. The potential of AI models provides opportunities to spot breast cancer cases better. This research aims to develop AI models with CNN using the public DDSM dataset with a sample size of 1871, consisting of 1546 images for training and 325 images for testing. These AI models provided prediction results with different accuracy rate. Increasing the accuracy of the AI model can be done by improving the image quality before the modeling process, increasing the number of datasets, or carrying out a more profound iteration process so that the AI model with CNN can have a better level of accuracy.
Analisis Variasi Nilai Time Inversion (TI) Terhadap Infromasi Citra MRI Knee Joint Potongan Sagital Sekuen PDW SPAIR Widiatmoko, Mahfud Edy; Sabina, Asy Syifa; Supriyaningsih, Eny; Rizqi, Muhammad; Hidayat, Eka Putra Syarif
Jurnal Imejing Diagnostik (JImeD) Vol 11, No 2 (2025): JULY 2025
Publisher : Poltekkes Kemenkes Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31983/jimed.v11i2.13326

Abstract

Background: Magnetic Resonance Imaging (MRI) is a non-invasive imaging modality essential for evaluating complex anatomical structures such as the knee joint. MRI allows multiplanar imaging with high soft tissue contrast resolution. In knee imaging, the sagittal plane is particularly effective in assessing pathologies and visualizing structures like cartilage, menisci, bones, and ligaments (ACL and PCL). Proton Density Weighted (PDW) sequences combined with Spectral Adiabatic Inversion Recovery (SPAIR) fat suppression are commonly used to enhance soft tissue visualization. The image quality in SPAIR sequences is significantly influenced by the Time Inversion (TI) parameter. This study aimed to analyze the impact of varying TI values on the image quality of sagittal PDW SPAIR MRI of the knee joint, focusing on anatomical detail and contrast resolution.Methods: This research used a quantitative analytical method with an experimental approach. The study was conducted at the Radiology Department of Pertamina Central Hospital from March to April 2025. Ten knee MRI examinations were selected as samples. Image quality was assessed by three radiologists using a structured scoring questionnaire. The data were analyzed using non-parametric statistical tests, including Friedman and Wilcoxon Signed-Rank tests.Results: The Friedman test revealed statistically significant differences in anatomical detail (χ²(2) = 15.000, p = 0.001) and contrast resolution (χ²(2) = 17.882, p = 0.000) across the three TI values (100 ms, 160 ms, and 200 ms). Post-hoc Wilcoxon analysis showed that both TI 160 ms and 200 ms provided significantly higher image quality than 100 ms (p 0.017) in both parameters. However, no significant differences were found between TI 160 ms and 200 ms (p = 0.506 for anatomical detail, p = 0.273 for contrast resolution). Among the values tested, TI 160 ms demonstrated consistent and optimal scores for both image clarity and contrast.Conclusions: A TI value of 160 ms in the PDW SPAIR sequence is recommended as the optimal parameter for producing superior sagittal MRI images of the knee joint, particularly in terms of anatomical clarity and contrast resolution.