Trajectory Grouping with Curvature Regularization for Tubular Structure Tracking

Laurent D. Cohen (1) , Li Liu (2) , Da Chen (3) , Minglei Shu (3) , Baosheng Li , Huazhong Shu (4) , Michel Paques (5)

1 CEREMADE - CEntre de REcherches en MAthématiques de la DEcision
2 Donghua University [Shanghai]
3 Shandong Artificial Intelligence Institute
4 SEU - Nanjing Southeast University
5 CHNO - Centre Hospitalier National d'Ophtalmologie des Quinze-Vingts

Tubular structure tracking is an important task in the fields of computer vision and medical image analysis. The minimal paths-based approaches have exhibited their powerful ability in tracing tubular structures, by which a tubular structure can be naturally treated as a minimal geodesic path computed with a suitable geodesic metric. However, existing minimal paths-based tracing approaches still suffer from difficulty, for instances the shortcuts and short branches combination problems, especially when dealing with the images involving complicated tubular tree structures or background. In this paper, we introduce a new minimal paths-based model for minimally interactive tubular structure centerline extraction in conjunction with a perceptual grouping scheme. Basically, we take into account the prescribed tubular trajectories and curvature-penalized geodesic paths to seek favourable shortest paths. The proposed approach can benefit from the local smoothness prior on tubular structures and the global optimality of the used graph-based path searching scheme. Experimental results on both synthetic and real images prove that the proposed model indeed obtains outperformance comparing with the state-of-the-art minimal path-based tubular structure tracing algorithms.

Mots clés: Tubular structure tracking; minimal path; perceptual grouping; curvature penalization; fast marching algorithm; graph optimization

Domaines: Traitement des images [eess.IV]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Equations aux dérivées partielles [math.AP]

Laurent D. Cohen, Li Liu, Da Chen, Minglei Shu, Baosheng Li, et al.. Trajectory Grouping with Curvature Regularization for Tubular Structure Tracking. IEEE Transactions on Image Processing, 2021, 31, pp.405 - 418. ⟨10.1109/TIP.2021.3131940⟩. ⟨hal-02996874⟩