深度学习矫正脑DWI畸变的前瞻性对比研究
本前瞻性单中心研究纳入100例脑MRI患者,比较深度学习矫正的ss-EPI DWI(DL DWI)、未矫正ss-EPI DWI与RESOLVE DWI。结果显示DL DWI的图像质量与几何精度优于ss-EPI DWI,病灶可检测性与RESOLVE DWI相当,扫描时间仅为其一半以下。
要点
- DL DWI病灶可检测性与RESOLVE DWI相当,而采集时间不到RESOLVE DWI的一半。
- DL DWI在图像质量、几何畸变、诊断信心中位数均显著高于未矫正ss-EPI DWI。
- 三个观察参数中RESOLVE DWI的中位数评分最高(5.0),DL DWI为4.0。
核心结论
- DL DWI图像质量与几何精度优于未矫正ss-EPI DWI,病灶可检测性主观评分与RESOLVE DWI相似,且采集时间少于RESOLVE DWI的一半。
- 研究结论支持DL畸变矫正作为脑扩散加权成像中省时有效的方法,但需在预设非劣效设计中进一步确认。
研究设计与样本
- 前瞻性单中心研究,时间为2025年4月至2025年8月,入组100例临床指征脑MRI患者并签署知情同意。
- 所有患者均行DL矫正ss-EPI DWI(DL DWI,采集1分29秒)与RESOLVE DWI(3分17秒),ss-EPI DWI通过关闭DL矫正重建获得。
- 定性分析由3名认证放射科医师以5分Likert量表评价图像质量、病灶可检测性、畸变与诊断信心。
- 定量畸变评估包括与解剖3D T1加权数据配准的几何一致性,以及易感区域(颞叶、小脑、脑干)兴趣区内灰阶分布。
关键影像表现/征象
- DL DWI在所有定性参数上显著优于未矫正ss-EPI DWI,包括诊断信心中位数4.0对3.0(P<0.001)和整体图像质量4.0对3.0(P<0.001)。
- DL DWI在易感区(颞叶、小脑、脑干)灰阶分布归一化及配准代价函数值上均显示优于ss-EPI DWI的几何精度。
- 病灶可检测性中位数DL DWI与RESOLVE DWI均为4.0(P>0.08),二者均显著高于ss-EPI DWI(P<0.001)。
诊断标准与关键数值
- 几何畸变定性评分中位数:DL DWI为4.0,ss-EPI DWI为3.0,P<0.001;RESOLVE DWI总体评分最高,中位数5.0。
- 病灶可检测性:DL DWI与RESOLVE DWI中位数均4.0,未矫正ss-EPI DWI显著低于二者(P<0.001)。
- 诊断信心中位数:DL DWI为4.0,ss-EPI DWI为3.0,P<0.001。
- DL DWI采集时间1分29秒,RESOLVE DWI采集时间3分17秒,DL DWI不足RESOLVE DWI的一半。
临床应用与阅片要点
- DL矫正后的ss-EPI DWI可在显著缩短扫描时间的前提下改善近气-组织界面区域的几何畸变。
- 在临床工作中对颞叶、小脑、脑干等易感伪影区域,DL DWI可提供与RESOLVE DWI相当的病灶显示,可作为时间受限条件下的替代方案。
- 阅读DL DWI图像时仍需结合解剖T1加权像评估配准一致性及残余畸变对病灶定位的影响。
局限性
- 单中心前瞻性研究,样本量为100例,研究时间跨度较短为2025年4月至8月。
- 病灶可检测性与诊断信心以主观Likert量表评价,缺乏病理或随访金标准的独立验证。
- 作者指出结果需在预设的非劣效性研究设计中进一步确认。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Single-shot echo-planar imaging DWI (ss-EPI DWI) is susceptible to geometric distortions near air-tissue interfaces, limiting diagnostic accuracy. Multishot readout-segmented DWI (RESOLVE DWI) mitigates these artifacts but requires longer acquisition times. This study evaluated whether ss-EPI DWI with a deep learning-enabled correction of static field inhomogeneities (DL DWI) can achieve effective distortion correction while preserving diagnostic reliability and reducing scan time.
OBJECTIVES: To compare image quality, geometric distortion, lesion detectability, and diagnostic confidence of ss-EPI DWI with DL-enabled correction of static field inhomogeneities (DL DWI) against conventional ss-EPI DWI (without correction) and RESOLVE DWI.
MATERIALS AND METHODS: In this prospective single-center study (April 2025 to August 2025), 100 patients undergoing clinically indicated brain MRI were enrolled following written informed consent. All patients underwent DL ss-EPI DWI with DL correction (1 min 29 s) and RESOLVE DWI (3 min 17 s); ss-EPI DWI was reconstructed by disabling DL correction for all patients. Qualitative and quantitative analyses were performed. Three board-certified radiologists rated image quality, lesion detectability, distortion, and diagnostic confidence on a 5-point Likert Scale. Two quantitative measures of distortion were applied: geometric conformity with anatomic 3D T1-weighted data through coregistration methods and gray-value distributions within volumes of interest in susceptibility-affected regions (temporal lobe, cerebellum, and brainstem).
RESULTS: DL DWI significantly outperformed ss-EPI DWI across all qualitative parameters, including diagnostic confidence (median, 4.0 vs. 3.0; P < 0.001), overall image quality (median, 4.0 vs. 3.0; P < 0.001), and geometric distortion (median, 4.0 vs. 3.0; P < 0.001). RESOLVE DWI achieved the highest ratings overall (median, 5.0). Lesion detectability was comparable between DL DWI and RESOLVE DWI (median, 4.0 for both; P > 0.08), while both significantly outperformed ss-EPI DWI (P < 0.001). Quantitative analysis confirmed superior geometric accuracy of DL DWI over ss-EPI DWI, with lower coregistration cost-function values and normalization of gray-value distributions in susceptibility-affected regions.
CONCLUSION: DL DWI improved image quality and geometric accuracy compared with uncorrected ss-EPI DWI. Subjective lesion-detectability ratings were similar between DL DWI and RESOLVE DWI, while DL DWI required less than half the acquisition time. These findings support DL-based distortion correction as a promising, time-efficient approach for brain diffusion-weighted imaging that warrants confirmation in a predefined noninferiority design.
引用
- Khalaf, Altmann, Kronfeld, et al. Deep Learning-Based Distortion Correction for Brain Diffusion-weighted Imaging: A Prospective Comparison With Single-shot and Readout-segmented Echo-planar Imaging. Invest Radiol. 2026. PMID: 42712163. doi:10.1097/RLI.0000000000001311
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。