Clinical Evaluation of a Combined Deep Learning-Reconstructed Readout-Segmented Echo-Planar Imaging and Water-Excitation Spectral Fat-Saturation Protocol for Breast Diffusion-Weighted Imaging at 3T Breast MRI.
Authors
Affiliations (5)
Affiliations (5)
- Department of Radiology, Ulsan University Hospital, University of Ulsan College of Medicine, Ulsan 44033, Republic of Korea.
- Department of Radiology, Jeonbuk National University Medical School, Jeonju 54907, Republic of Korea.
- Research Institute of Clinical Medicine, Jeonbuk National University-Biomedical Research Institute, Jeonbuk National University Hospital, Jeonju 54907, Republic of Korea.
- Siemens Healthineers Ltd., Seoul 06620, Republic of Korea.
- Siemens Healthineers AG, 91052 Erlangen, Germany.
Abstract
<b>Objectives</b>: This study evaluates the protocol-level image quality and quantitative diffusion metrics of a clinically implemented deep-learning-reconstructed readout-segmented echo-planar imaging protocol with water-excitation spectral fat saturation (DL-rs-EPI with WEXfs) compared with conventional rs-EPI using spectral attenuated inversion recovery (SPAIR) at 3 T. <b>Methods</b>: Overall, 80 patients underwent breast magnetic resonance imaging (MRI) with both conventional rs-EPI with SPAIR and DL-rs-EPI with WEXfs protocols (b-values: 0, 800, and 1200 s/mm<sup>2</sup>). ROI-based relative image-quality metrics, including signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and lesion contrast, were assessed at b = 800 and b = 1200 s/mm<sup>2</sup>; apparent diffusion coefficient (ADC) values were calculated using multi-b-value data. Fat suppression, background diffusion signal, lesion conspicuity, and artifact severity were qualitatively evaluated. A temperature-controlled diffusion phantom (CaliberMRI) was scanned; ADC values were compared with reference values at 24 °C. <b>Results</b>: DL-rs-EPI with WEXfs demonstrated higher ROI-based relative SNR estimates (b800: 5.79 vs. 5.28; b1200: 5.41 vs. 4.94; <i>p</i> < 0.001) and CNR estimates (b800: 3.35 vs. 3.12, <i>p</i> = 0.024; b1200: 3.67 vs. 3.37, <i>p</i> = 0.001), with unchanged lesion contrast. Tumor ADC values were comparable between protocols, whereas normal fibroglandular tissue ADC values were slightly higher, and ADC contrast increased with DL-rs-EPI with WEXfs. Phantom ADC values from both protocols closely matched reference values at 24 °C, without significant differences. DL-rs-EPI with WEXfs demonstrated more homogeneous fat suppression and reduced background diffusion signal, with comparable lesion conspicuity and artifact severity. <b>Conclusions</b>: The combined DL-rs-EPI with WEXfs protocol demonstrated improved qualitative and relative quantitative image quality while preserving tumor ADC measurements. As a protocol-level evaluation, these composite improvements support its clinical feasibility for high-quality breast DWI without implying the isolated effect of DL reconstruction alone.