Scholarlink

Objectives <p>Deep learning (DL)–based image reconstruction (DLBIR) techniques promise accelerated MRI acquisitions with enhanced image quality. Herein, we compare the image quality of a DLBIR-based 3D FLAIR (3D-FLAIR<sub>DL</sub>) with conventional 3D FLAIR (3D-FLAIR<sub>SOC</sub>) in a cohort of multiple sclerosis (MS) patients.</p> Materials and methods <p>Our prospective, reader-blinded study, included 26 MS patients who underwent both sequences on a 3T scanner during the same study session over three months. Two neuroradiologists assessed noise, artifacts, sharpness, overall image quality, and diagnostic confidence using 4-point Likert-like scales. Lesion conspicuity was graded for lesions &lt; 3&#xa0;mm and ≥ 3&#xa0;mm. Quantitative metrics included lesion count, apparent signal-to-noise ratio (aSNR), and contrast-to-noise ratio (aCNR). A composite gold standard was used to calculate sensitivity and precision.</p> Results <p>3D-FLAIR<sub>DL</sub> showed significantly better qualitative scores (<i>p</i> &lt; 0.001) with high inter-reader agreement. Lesion conspicuity and diagnostic confidence improved, especially for &lt; 3&#xa0;mm lesions. DLBIR images detected 29 additional lesions (10 ≥ 3&#xa0;mm-sized lesions and 19 &lt; 3&#xa0;mm lesions), yielding higher sensitivity (99.5% vs. 88.8% for &lt; 3&#xa0;mm; 100% vs. 97.9% for ≥ 3&#xa0;mm) without false positives. aSNR and aCNR were significantly higher for DLBIR images (<i>p</i> &lt; 0.001). Acquisition time was reduced by 32% (3:54 vs. 5:44&#xa0;min).</p> Conclusion <p>DLBIR 3D FLAIR significantly improves lesion detection and image quality in MS, supporting its potential integration into standard imaging protocols. As DLBIR algorithms evolve, further validation in larger, diverse cohorts will be essential.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning–accelerated 3D flair for white matter lesion detection in multiple sclerosis: a feasibility study

  • 期刊论文

  • 发表日期：

    2026年1月22日

查看全文
  • Pranjal Rai,
  • Vincent Ern Yao Chan,
  • Marcel Dominik Nickel,
  • Cem Bilgin,
  • Peter Kollasch,
  • Kara Dueker,
  • Theodore J. Passe,
  • Steven A. Messina,
  • Victoria M. Silvera,
  • Amit Agarwal,
  • Girish Bathla

摘要

Objectives

Deep learning (DL)–based image reconstruction (DLBIR) techniques promise accelerated MRI acquisitions with enhanced image quality. Herein, we compare the image quality of a DLBIR-based 3D FLAIR (3D-FLAIRDL) with conventional 3D FLAIR (3D-FLAIRSOC) in a cohort of multiple sclerosis (MS) patients.

Materials and methods

Our prospective, reader-blinded study, included 26 MS patients who underwent both sequences on a 3T scanner during the same study session over three months. Two neuroradiologists assessed noise, artifacts, sharpness, overall image quality, and diagnostic confidence using 4-point Likert-like scales. Lesion conspicuity was graded for lesions < 3 mm and ≥ 3 mm. Quantitative metrics included lesion count, apparent signal-to-noise ratio (aSNR), and contrast-to-noise ratio (aCNR). A composite gold standard was used to calculate sensitivity and precision.

Results

3D-FLAIRDL showed significantly better qualitative scores (p < 0.001) with high inter-reader agreement. Lesion conspicuity and diagnostic confidence improved, especially for < 3 mm lesions. DLBIR images detected 29 additional lesions (10 ≥ 3 mm-sized lesions and 19 < 3 mm lesions), yielding higher sensitivity (99.5% vs. 88.8% for < 3 mm; 100% vs. 97.9% for ≥ 3 mm) without false positives. aSNR and aCNR were significantly higher for DLBIR images (p < 0.001). Acquisition time was reduced by 32% (3:54 vs. 5:44 min).

Conclusion

DLBIR 3D FLAIR significantly improves lesion detection and image quality in MS, supporting its potential integration into standard imaging protocols. As DLBIR algorithms evolve, further validation in larger, diverse cohorts will be essential.