Scholarlink

Background <p>Maximum intensity projections (MIPs) facilitate rapid lesion detection both for contrast-enhanced (CE) and diffusion-weighted imaging (DWI) breast magnetic resonance imaging (MRI). We evaluated the feasibility of AI-based virtual CE subtraction MIPs as a reading approach.</p> Materials and methods <p>This Institutional Review Board-approved retrospective study includes 540 multi-parametric breast MRI examinations (performed from 2017 to 2020), including multi-<i>b</i>-value DWI (50, 750, and 1,500 s/mm²). A 2D U-Net was trained using unenhanced (UnE) images as inputs to generate virtual abbreviated CE (VAbCE) subtractions. Two radiologists evaluated lesion suspicion, image quality, and artifacts for UnE, VACE, and abbreviated CE (AbCE) images. Lesion conspicuity was compared between VAbCE and AbCE MIPs.</p> Results <p>Cancer detection rates for UE, VAbCE, and AbCE MIPs were 90.0%, 91.4%, and 94.3%, respectively. Single-slice reading demonstrated sensitivities of 88.6% (UnE), 91.4% (VAbCE), and 94.3% (AbCE). Inter-rater agreement (Cohen κ) for lesion suspicion scores was higher for VAbCE (0.53) than UnE alone (0.39) and comparable to AbCE (0.58). No significant difference in mean lesion conspicuity was observed for VACE MIPs compared to ACE (<i>p</i> ≥ 0.670). No significant difference could be observed for quality (<i>p</i> ≥ 0.108), and reading time (<i>p</i> = 1.000) between methods. Fewer visually significant artifacts could be observed in VAbCE than in AbCE MIPs (<i>p</i> ≤ 0.001).</p> Conclusion <p>VAbCE breast MRI improved inter-rater agreement and allowed for slightly improved sensitivity compared to UnE images, while AbCE still provided the overall highest sensitivity. Further research is necessary to investigate the diagnostic potential of VAbCE breast MRI.</p> Relevance statement <p>VAbCE breast MRI generated by neural networks allowed the derivation of MIPs for rapid visual assessment, showing a way for screening applications.</p> Key Points <p><UnorderedList Mark="Bullet"> <ItemContent> <p>Virtual abbreviated contrast-enhanced (VAbCE) MIPs provided comparable sensitivity to MIPs of unenhanced high <i>b</i>-value DWI and were slightly lower than AbCE MIPs.</p> </ItemContent> <ItemContent> <p>Adding VAbCE to unenhanced high <i>b</i>-value DWI significantly improved interrater agreement for lesion suspicion scoring.</p> </ItemContent> <ItemContent> <p>Single-slice evaluation of VAbCE MIPs provided a sensitivity comparable to unenhanced high <i>b</i>-value DWI MIPs.</p> </ItemContent> </UnorderedList></p> Graphical Abstract <p></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

Virtual contrast-enhanced maximum intensity projections from high-b-value diffusion-weighted breast MRI: a feasibility study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月8日

查看全文
  • Andrzej Liebert,
  • Hannes Schreiter,
  • Dominique Hadler,
  • Lorenz A. Kapsner,
  • Sabine Ohlmeyer,
  • Jessica Eberle,
  • Ramona Erber,
  • Julius Emons,
  • Frederik B. Laun,
  • Michael Uder,
  • Evelyn Wenkel,
  • Sebastian Bickelhaupt

摘要

Background

Maximum intensity projections (MIPs) facilitate rapid lesion detection both for contrast-enhanced (CE) and diffusion-weighted imaging (DWI) breast magnetic resonance imaging (MRI). We evaluated the feasibility of AI-based virtual CE subtraction MIPs as a reading approach.

Materials and methods

This Institutional Review Board-approved retrospective study includes 540 multi-parametric breast MRI examinations (performed from 2017 to 2020), including multi-b-value DWI (50, 750, and 1,500 s/mm²). A 2D U-Net was trained using unenhanced (UnE) images as inputs to generate virtual abbreviated CE (VAbCE) subtractions. Two radiologists evaluated lesion suspicion, image quality, and artifacts for UnE, VACE, and abbreviated CE (AbCE) images. Lesion conspicuity was compared between VAbCE and AbCE MIPs.

Results

Cancer detection rates for UE, VAbCE, and AbCE MIPs were 90.0%, 91.4%, and 94.3%, respectively. Single-slice reading demonstrated sensitivities of 88.6% (UnE), 91.4% (VAbCE), and 94.3% (AbCE). Inter-rater agreement (Cohen κ) for lesion suspicion scores was higher for VAbCE (0.53) than UnE alone (0.39) and comparable to AbCE (0.58). No significant difference in mean lesion conspicuity was observed for VACE MIPs compared to ACE (p ≥ 0.670). No significant difference could be observed for quality (p ≥ 0.108), and reading time (p = 1.000) between methods. Fewer visually significant artifacts could be observed in VAbCE than in AbCE MIPs (p ≤ 0.001).

Conclusion

VAbCE breast MRI improved inter-rater agreement and allowed for slightly improved sensitivity compared to UnE images, while AbCE still provided the overall highest sensitivity. Further research is necessary to investigate the diagnostic potential of VAbCE breast MRI.

Relevance statement

VAbCE breast MRI generated by neural networks allowed the derivation of MIPs for rapid visual assessment, showing a way for screening applications.

Key Points

Virtual abbreviated contrast-enhanced (VAbCE) MIPs provided comparable sensitivity to MIPs of unenhanced high b-value DWI and were slightly lower than AbCE MIPs.

Adding VAbCE to unenhanced high b-value DWI significantly improved interrater agreement for lesion suspicion scoring.

Single-slice evaluation of VAbCE MIPs provided a sensitivity comparable to unenhanced high b-value DWI MIPs.

Graphical Abstract