Automatic aortic root segmentation and anatomical landmarks detection for TAVI procedure planning

Florent Lalys (1) , Simon Esneault (1) , Miguel Castro (2) , Lucas Royer (1) , Pascal Haigron (2) , Vincent Auffret (3, 2) , Jacques Tomasi (2, 4)

1 Therenva SAS
2 LTSI - Laboratoire Traitement du Signal et de l'Image
3 Service de cardiologie et maladies vasculaires [Rennes] = Cardiac, Thoracic, and Vascular Surgery [Rennes]
4 Service de chirurgie thoracique cardiaque et vasculaire [Rennes] = Thoracic and Cardiovascular Surgery [Rennes]

Purpose - Minimally invasive trans-catheter aortic valve implantation (TAVI) has emerged as a treatment of choice for high-risk patients with severe aortic stenosis. However, the planning of TAVI procedures would greatly benefit from automation to speed up, secure and guide the deployment of the prosthetic valve. We propose a hybrid approach allowing the computation of relevant anatomical measurements along with an enhanced visualization. Material and methods - After an initial step of centerline detection and aorta segmentation, model-based and statistical-based methods are used in combination with 3 D active contour models to exploit the complementary aspects of these methods and automatically detect aortic leaflets and coronary ostia locations. Important anatomical measurements are then derived from these landmarks. Results - A validation on 50 patients showed good precision with respect to expert sizing for the ascending aorta diameter calculation (2.2 ± 2.1 mm), the annulus diameter (1.31 ± 0.75 mm), and both the right and left coronary ostia detection (1.96 ± 0.87 mm and 1.80 ± 0.74 mm, respectively). The visualization is enhanced thanks to the aorta and aortic root segmentation, the latter showing good agreement with manual expert delineation (Jaccard index: 0.96 ± 0.03). Conclusion - This pipeline is promising and could greatly facilitate TAVI planning.

Mots clés: TAVI; active contour models; endovascular procedures; statistical-based methods

Domaines: Traitement du signal et de l'image [eess.SP]; Ingénierie biomédicale

Florent Lalys, Simon Esneault, Miguel Castro, Lucas Royer, Pascal Haigron, et al.. Automatic aortic root segmentation and anatomical landmarks detection for TAVI procedure planning. Minimally Invasive Therapy and Allied Technologies, 2019, 28 (3), pp.157-164. ⟨10.1080/13645706.2018.1488734⟩. ⟨hal-01862531⟩