Automated anatomical labeling of a topologically variant abdominal arterial system via probabilistic hypergraph matching

• Published in: Medical image analysis Vol. 75; p. 102249
• Main Authors: Liu, Yue, Wang, Xingce, Wu, Zhongke, López-Linares, Karen, Macía, Iván, Ru, Xudong, Zhao, Haichuan, González Ballester, Miguel A., Zhang, Chong
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2022; Elsevier BV
• Subjects: Abdomen; Abdomen - diagnostic imaging; Abdominal aorta; Algorithms; Anatomical labeling; Arteries; Automation; Blood vessels; Branches; Convexity; Epidemiology; Family trees; Graph matching; Graph theory; Graphs; Hidden Markov model; Humans; Hypergraph model; Image processing; Image Processing, Computer-Assisted; Labeling; Markov analysis; Markov chains; Mathematical models; Medical imaging; Multiclass classification; Optimization; Probabilistic graph matching; Probability; Probability distribution; Statistical analysis; Topological constraints; Topology; Abdominal aorta; Topological constraints; Anatomical labeling; Hidden Markov model; Hypergraph model; Multiclass classification; Probabilistic graph matching
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2021.102249

•We present a hypergraph representation of the abdominal arterial system as a family tree using a probabilistic graph matching framework.•In topology, the de fined family tree model is used for topological recognition of the abdominal artery system, and it is optimized by an HMM with a Markov chain.•For geometry, we use XGBoost ensemble learning with intrinsic geometric features for branch level labeling. Automated anatomical vessel labeling of the abdominal arterial system is a crucial topic in medical image processing. One reason for this is the importance of the abdominal arterial system in the human body, and another is that such labeling is necessary for the related disease diagnoses, treatments and epidemiological population analyses. We define a hypergraph representation of the abdominal arterial system as a family tree model with a probabilistic hypergraph matching framework for automated vessel labeling. Then we treat the labelling problem as the convex optimization problem and solve it with the maximum a posteriori(MAP) combined the likelihood obtained by geometric labelling with the family tree topology-based knowledge. Geometrically, we utilize XGBoost ensemble learning with an intrinsic geometric feature importance analysis for branch-level labeling. In topology, the defined family tree model of the abdominal arterial system is transferred as a Markov chain model using a constrained traversal order method and further the Markov chain model is optimized by a hidden Markov model (HMM). The probability distribution of the target branches for each candidate anatomical name is predicted and effectively embedded in the HMM model. This approach is evaluated with the leave-one-out method on 37 clinical patients’ abdominal arteries, and the average accuracy is 91.94%. The obtained results are better than those of the state-of-art method with an F1 score of 93.00% and a recall of 93.00%, as the proposed method simultaneously handles the anatomical structural variability and discriminates between the symmetric branches. It is demonstrated to be suitable for labelling branches of the abdominal arterial system and can also be extended to similar tubular organ networks, such as arterial or airway networks.