Scholarlink

Background <p>Deep learning (DL) reconstruction shows potential in reducing MRI acquisition times while preserving image quality, but the impact of varying acceleration factors on knee MRI diagnostic accuracy remains undefined.</p> Purpose <p>Evaluate diagnostic performance of twofold, fourfold, and sixfold DL-accelerated knee MRI protocols versus standard protocols.</p> Materials/methods <p>In this prospective study, 71 consecutive patients underwent knee MRI with standard, DL2, DL4, and DL6 accelerated protocols. Four radiologists assessed ligament tears, meniscal lesions, bone marrow edema, chondropathy, and extensor abnormalities. Sensitivity, specificity, and interobserver agreement were calculated.</p> Results <p>DL2 and DL4 demonstrated high diagnostic accuracy. For ACL tears, DL2/DL4 achieved 98–100% sensitivity/specificity, while DL6 showed reduced sensitivity (91–96%). In meniscal evaluation, DL2 maintained 96–100% sensitivity and 98–100% specificity; DL4 showed 94–98% sensitivity and 97–99% specificity. DL6 exhibited decreased sensitivity (82–92%) for subtle lesions. Bone marrow edema detection remained excellent across acceleration factors. Interobserver agreement was excellent for DL2/DL4 (<i>W</i> = 0.91–0.97) and good for DL6 (<i>W</i> = 0.78–0.89).</p> Conclusion <p>DL2 protocols demonstrate performance nearly identical to standard protocols, while DL4 maintains acceptable diagnostic accuracy for most pathologies. DL6 shows reduced sensitivity for subtle abnormalities, particularly among less experienced readers. DL2 and DL4 protocols represent optimal balance between acquisition time reduction (50–75%) and diagnostic confidence.</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-driven abbreviated knee MRI protocols: diagnostic accuracy in clinical practice

  • 期刊论文

  • 发表日期：

    2025年7月4日

查看全文
  • Giovanni Foti,
  • Flavio Spoto,
  • Alessandro Spezia,
  • Luigi Romano,
  • Simone Caia,
  • Francesco Camerani,
  • Damiano Benedetti,
  • Thomas Mignolli

摘要

Background

Deep learning (DL) reconstruction shows potential in reducing MRI acquisition times while preserving image quality, but the impact of varying acceleration factors on knee MRI diagnostic accuracy remains undefined.

Purpose

Evaluate diagnostic performance of twofold, fourfold, and sixfold DL-accelerated knee MRI protocols versus standard protocols.

Materials/methods

In this prospective study, 71 consecutive patients underwent knee MRI with standard, DL2, DL4, and DL6 accelerated protocols. Four radiologists assessed ligament tears, meniscal lesions, bone marrow edema, chondropathy, and extensor abnormalities. Sensitivity, specificity, and interobserver agreement were calculated.

Results

DL2 and DL4 demonstrated high diagnostic accuracy. For ACL tears, DL2/DL4 achieved 98–100% sensitivity/specificity, while DL6 showed reduced sensitivity (91–96%). In meniscal evaluation, DL2 maintained 96–100% sensitivity and 98–100% specificity; DL4 showed 94–98% sensitivity and 97–99% specificity. DL6 exhibited decreased sensitivity (82–92%) for subtle lesions. Bone marrow edema detection remained excellent across acceleration factors. Interobserver agreement was excellent for DL2/DL4 (W = 0.91–0.97) and good for DL6 (W = 0.78–0.89).

Conclusion

DL2 protocols demonstrate performance nearly identical to standard protocols, while DL4 maintains acceptable diagnostic accuracy for most pathologies. DL6 shows reduced sensitivity for subtle abnormalities, particularly among less experienced readers. DL2 and DL4 protocols represent optimal balance between acquisition time reduction (50–75%) and diagnostic confidence.