DHR<sup>2</sup>-Net: A Dual-Hierarchical Relational Reasoning Framework for Surgical Action Triplet Recognition.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41662550.
- Also identified by DOI 10.1109/TMI.2026.3662737.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Surgical action triplet recognition plays a vital role in computer-assisted and anatomical surgery. A fine-grained formulation of this task aims to simultaneously identify the surgical instrument, operative verb, and anatomical target, which are represented as triplets in the form of <instrument, verb, target>. Existing methods face two key challenges: 1) Relying solely on the visual features of instruments fails to identify abstract functional operations. 2) Limited modeling of inter-entity relationships hampers accurate triplet recognition. To address these challenges, we propose DHR<sup>2</sup>-Net, a novel Dual-Hierarchical Relational Reasoning framework for surgical action triplet recognition. First, DHR<sup>2</sup>-Net explicitly models verbs as semantic interactions between instruments and targets to capture the underlying surgical intent. Then, we construct first-order (instrument-context and target-context) and high-order (instrument-verb-target) dependencies through dual-hierarchical relational reasoning to build clear internal associations of triplets. To further enhance feature representation during the high-order reasoning stage, we introduce an inter-sample high-order relational reasoning module (IHR<sup>2</sup>) that leverages relational cues shared across samples within each batch for more explicit relational modeling. Meanwhile, an auxiliary actor identity preservation module enables the final triplet-level embedding to capture both identity and relational semantics. We evaluate DHR<sup>2</sup>-Net on the CholecT45 dataset using 5-fold cross-validation and the CholecTriplet2021 challenge splits. The experimental results show that DHR<sup>2</sup>-Net achieves superior performance in fine-grained component recognition and interaction modeling, as well as robust accuracy in triplet recognition. The visualization analyses further highlight its strong clinical interpretability and potential for practical deployment in computer-assisted intervention systems.