This study assessed the influence of deep learning reconstruction (DLR) on the quality of diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) using an ice-water phantom. An ice-water phantom with known diffusion properties (true ADC = 1.1 × 10 mm/s at 0 °C) was imaged at various b-values (0, 1000, 2000, and 4000 s/mm) using a 3 T magnetic resonance imaging scanner with slice thicknesses of 1.5 and 3.0 mm. All DWIs were reconstructed with or without DLR. ADC maps were generated using combinations of b-values 0 and 1000, 0 and 2000, and 0 and 4000 s/mm. Based on the quantitative imaging biomarker alliance profile, the signal-to-noise ratio (SNRs) in DWIs was calculated, and the accuracy, precision, and within-subject parameter variance (wCV) of the ADCs were evaluated. DLR improved the SNR in DWIs with b-values ranging from 0 to 2000s/mm; however, its effectiveness was diminished at 4000 s/mm. There was no noticeable difference in the ADCs of images generated with or without implementing DLR. For a slice thickness of 1.5 mm and combined b-values of 0 and 4000 s/mm, the ADC values were 0.97 × 10and 0.98 × 10mm/s with and without DLR, respectively, both being lower than the true ADC value. Furthermore, DLR enhanced the precision and wCV of the ADC measurements. DLR can enhance the SNR, repeatability, and precision of ADC measurements; however, it does not improve their accuracies.

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12194-023-00765-8DOI Listing

Publication Analysis

Top Keywords

ice-water phantom
12
deep learning
8
learning reconstruction
8
apparent diffusion
8
diffusion coefficient
8
b-values 1000
8
1000 2000
8
2000 4000 s/mm
8
adc measurements
8
dlr
7

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!