Scholarlink

Background <p>Several software programs have specifically been developed to analyse cardiac computed tomography prior to transcatheter aortic valve implantation (TAVI). However, they are not able to perform a complete analysis independently. We report the performance of a fully automated, deep learning-based algorithm for pre-procedural CT analysis as compared to the current clinical standard.</p> Methods <p>Patients with symptomatic severe aortic stenosis undergoing TAVI were retrospectively enrolled. The pre-procedural dataset was analysed by both a standard TAVI CT-analysis software and by a fully automated CT analysis platform with a deep learning-based algorithm.</p> Results <p>Ninety-eight patients were included in the analysis. The mean annulus diameter was 24.4 ± 2.4&#xa0;mm (conventional = 3mensio, Pie Medical Imaging, 3&#xa0;M) vs. 24.0 ± 2.4&#xa0;mm (artificial intelligence = AI), mean absolute error (MAE): 0.64&#xa0;mm, mean absolute percentage error (MAPE): 2.6%. The mean annulus perimeter was measured at 77.7 ± 7.4&#xa0;mm (3&#xa0;M) vs. 76.1 ± 7.5&#xa0;mm (AI), MAE: 2.26&#xa0;mm, MAPE: 2.9%. The mean annulus area was calculated at 468.9 ± 92.1 mm<sup>2</sup> (3&#xa0;M) vs. 455.6 ± 91.0 mm<sup>2</sup> (AI), MAE: 22.4 mm<sup>2</sup>, MAPE: 4.8%. The intraclass correlation coefficients (ICCs) of all abovementioned parameter were &gt; 0.95 showing an excellent correlation between the two methods. The distance from the annulus to the left coronary artery depicted to 14.0 ± 3.2&#xa0;mm (3&#xa0;M) vs. 12.6 ± 2.8&#xa0;mm (AI), MAE: 2.1&#xa0;mm, MAPE: 14.3%. The distance to the right coronary artery was 17.1 ± 2.7&#xa0;mm (3&#xa0;M) vs. 16.5 ± 3.2&#xa0;mm (AI), MAE: 1.7 mm, MAPE: 10.1%. The ICCs of the distances to the coronary ostia showed good correlation between both methods.</p> Conclusion <p>In this retrospective analysis, a deep learning-based analysis of pre-procedural CT datasets showed good to excellent correlation with conventional assessment for the preprocedural TAVI CT measurements. AI-based fully automated CT analysis could emerge to a valuable alternative to conventional CT assessment in the pre-procedural-planning for TAVI.</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

AI-assisted computed tomography analysis for pre-procedural planning prior to TAVI

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月12日

查看全文
  • Mani Arsalan,
  • Hanna Schneider,
  • Kerstin Piayda,
  • Philipp Christian Seppelt,
  • Arnaud Van Linden,
  • Stephan Fichtlscherer,
  • Florian Hecker,
  • David Leistner,
  • Thomas Walther

摘要

Background

Several software programs have specifically been developed to analyse cardiac computed tomography prior to transcatheter aortic valve implantation (TAVI). However, they are not able to perform a complete analysis independently. We report the performance of a fully automated, deep learning-based algorithm for pre-procedural CT analysis as compared to the current clinical standard.

Methods

Patients with symptomatic severe aortic stenosis undergoing TAVI were retrospectively enrolled. The pre-procedural dataset was analysed by both a standard TAVI CT-analysis software and by a fully automated CT analysis platform with a deep learning-based algorithm.

Results

Ninety-eight patients were included in the analysis. The mean annulus diameter was 24.4 ± 2.4 mm (conventional = 3mensio, Pie Medical Imaging, 3 M) vs. 24.0 ± 2.4 mm (artificial intelligence = AI), mean absolute error (MAE): 0.64 mm, mean absolute percentage error (MAPE): 2.6%. The mean annulus perimeter was measured at 77.7 ± 7.4 mm (3 M) vs. 76.1 ± 7.5 mm (AI), MAE: 2.26 mm, MAPE: 2.9%. The mean annulus area was calculated at 468.9 ± 92.1 mm2 (3 M) vs. 455.6 ± 91.0 mm2 (AI), MAE: 22.4 mm2, MAPE: 4.8%. The intraclass correlation coefficients (ICCs) of all abovementioned parameter were > 0.95 showing an excellent correlation between the two methods. The distance from the annulus to the left coronary artery depicted to 14.0 ± 3.2 mm (3 M) vs. 12.6 ± 2.8 mm (AI), MAE: 2.1 mm, MAPE: 14.3%. The distance to the right coronary artery was 17.1 ± 2.7 mm (3 M) vs. 16.5 ± 3.2 mm (AI), MAE: 1.7 mm, MAPE: 10.1%. The ICCs of the distances to the coronary ostia showed good correlation between both methods.

Conclusion

In this retrospective analysis, a deep learning-based analysis of pre-procedural CT datasets showed good to excellent correlation with conventional assessment for the preprocedural TAVI CT measurements. AI-based fully automated CT analysis could emerge to a valuable alternative to conventional CT assessment in the pre-procedural-planning for TAVI.

Graphical Abstract