Scholarlink

Purpose <p>To evaluate diagnostic accuracy and image quality of deep learning (DL) cine sequences for LV and RV parameters compared to conventional balanced steady-state free precession (bSSFP) cine sequences in cardiovascular magnetic resonance (CMR).</p> Material and methods <p>From January to April 2024, patients with clinically indicated CMR were prospectively included. LV and RV were segmented from short-axis bSSFP and DL cine sequences. LV and RV end-diastolic volume (EDV), end-systolic volume (EDV), stroke volume (SV), ejection fraction, and LV end-diastolic mass were calculated. The acquisition time of both sequences was registered. Results were compared with paired-samples t test or Wilcoxon signed-rank test. Agreement between DL cine and bSSFP was assessed using Bland–Altman plots. Image quality was graded by two readers based on blood-to-myocardium contrast, endocardial edge definition, and motion artifacts, using a 5-point Likert scale (1 = insufficient quality; 5 = excellent quality).</p> Results <p>Sixty-two patients were included (mean age: 47 ± 17&#xa0;years, 41 men). No significant differences between DL cine and bSSFP were found for all LV and RV parameters (<i>P</i> ≥ .176). DL cine was significantly faster (1.35 ± .55&#xa0;m vs 2.83 ± .79&#xa0;m; <i>P</i> &lt; .001). The agreement between DL cine and bSSFP was strong, with bias ranging from 45 to 1.75% for LV and from − 0.38 to 2.43% for RV. Among LV parameters, the highest agreement was obtained for ESV and SV, which fell within the acceptable limit of agreement (LOA) in 84% of cases. EDV obtained the highest agreement among RV parameters, falling within the acceptable LOA in 90% of cases. Overall image quality was comparable (median: 5, IQR: 4–5; <i>P</i> = .330), while endocardial edge definition of DL cine (median: 4, IQR: 4–5) was lower than bSSFP (median: 5, IQR: 4–5; <i>P</i> = .002).</p> Conclusion <p>DL cine allows fast and accurate quantification of LV and RV parameters and comparable image quality with conventional bSSFP.</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

Accelerated deep learning-based function assessment in cardiovascular magnetic resonance

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月17日

查看全文
  • Domenico De Santis,
  • Federica Fanelli,
  • Luca Pugliese,
  • Giovanna Grazia Bona,
  • Tiziano Polidori,
  • Curzio Santangeli,
  • Michela Polici,
  • Antonella Del Gaudio,
  • Giuseppe Tremamunno,
  • Marta Zerunian,
  • Andrea Laghi,
  • Damiano Caruso

摘要

Purpose

To evaluate diagnostic accuracy and image quality of deep learning (DL) cine sequences for LV and RV parameters compared to conventional balanced steady-state free precession (bSSFP) cine sequences in cardiovascular magnetic resonance (CMR).

Material and methods

From January to April 2024, patients with clinically indicated CMR were prospectively included. LV and RV were segmented from short-axis bSSFP and DL cine sequences. LV and RV end-diastolic volume (EDV), end-systolic volume (EDV), stroke volume (SV), ejection fraction, and LV end-diastolic mass were calculated. The acquisition time of both sequences was registered. Results were compared with paired-samples t test or Wilcoxon signed-rank test. Agreement between DL cine and bSSFP was assessed using Bland–Altman plots. Image quality was graded by two readers based on blood-to-myocardium contrast, endocardial edge definition, and motion artifacts, using a 5-point Likert scale (1 = insufficient quality; 5 = excellent quality).

Results

Sixty-two patients were included (mean age: 47 ± 17 years, 41 men). No significant differences between DL cine and bSSFP were found for all LV and RV parameters (P ≥ .176). DL cine was significantly faster (1.35 ± .55 m vs 2.83 ± .79 m; P < .001). The agreement between DL cine and bSSFP was strong, with bias ranging from 45 to 1.75% for LV and from − 0.38 to 2.43% for RV. Among LV parameters, the highest agreement was obtained for ESV and SV, which fell within the acceptable limit of agreement (LOA) in 84% of cases. EDV obtained the highest agreement among RV parameters, falling within the acceptable LOA in 90% of cases. Overall image quality was comparable (median: 5, IQR: 4–5; P = .330), while endocardial edge definition of DL cine (median: 4, IQR: 4–5) was lower than bSSFP (median: 5, IQR: 4–5; P = .002).

Conclusion

DL cine allows fast and accurate quantification of LV and RV parameters and comparable image quality with conventional bSSFP.