Back to the list
Congress: ECR25
Poster Number: C-18751
Type: Poster: EPOS Radiographer (scientific)
DOI: 10.26044/ecr2025/C-18751
Authorblock: H. Hirata; Sapporo/JP
Disclosures:
Hideki Hirata: Nothing to disclose
Keywords: Radiographers, MR, Imaging sequences, Artifacts
Purpose Recently, novel MRI reconstruction techniques based on deep learning (deep learning reconstruction: DLR) have been introduced, revolutionizing the trade-off between reducing scan time and maintaining image quality [1,2]. The first stage of super-resolution deep learning-based reconstruction (SR-DLR) acquires high-SNR images with denoising. The second stage of super-resolution processing generates high-resolution images by zero-fill interpolation processing (ZIP) of the acquired high-SNR images. Super-resolution processing is performed by learning and constructing a preset of high-resolution input images after ZIP processing and high-resolution...
Read more Methods and materials In July 2024, 81 patients underwent brain MRI (DWI, T2, FLAIR, T2*) using a 3-tesla MRI with SR-DLR were prospectively studied.For each sequence, C-R images were compared with images created from C-R images by SR-DLR (spatial resolution: double or three times, denoising level: level 1 Weak, level 2, level 3 Medium, level 4, level 5 Strong). Imaging conditions are shown in Figure 2. Two radiographers evaluated the overall image quality, noise, sharpness, contrast, and artifacts of each image on a...
Read more Results C-R image and the SR-DLR image are shown in Figures 3 and 4. The results of image evaluation are shown in Figure 5. For all sequences, overall image quality, noise, and sharpness scores were significantly higher for the SR-DLR image than for the C-R image (p<0.05). Even for clinical images, a high-resolution, low-noise image can be obtained from a low-resolution, high-noise image, demonstrating the usefulness of SR-DLR. There was no significant difference in scores for T2 and FLAIR for contrast....
Read more Conclusion Using SR-DLR, it is useful to obtain high-resolution, low-noise images from low-resolution, high-noise images. Furthermore, it can reduce imaging time while ensuring image quality.The SR-DLR is a technology that will bring about a major revolution in clinical and management.
Read more References [1] Sebastian Gassenmaier, Saif Afat, Marcel Dominik Nickel, et al. Accelerated T2-Weighted TSE Imaging of the Prostate Using Deep Learning Image Reconstruction: A Prospective Comparison with Standard T2-Weighted TSE Imaging. Cancers; 2021; 13(14): 3593. DOI: 10.3390/cancers13143593[2] Martin Jurka, Iva Macova, Monika Wagnerova, et al. Deep-learning-based reconstruction of T2-weighted magnetic resonance imaging of the prostate accelerated by compressed sensing provides improved image quality at half the acquisition time. Quantitative Imaging in Medicine and Surgery; 2024; 14(5): 3535. DOI: 10.21037/qims-23-1488
Read more
GALLERY