Mining Domain Knowledge: Improved Framework towards Automatically Standardizing Anatomical Structure Nomenclature in Radiotherapy

TL;DR

This paper introduces a novel AI framework, 3DNNV, that improves automatic standardization of anatomical structure names in radiotherapy data, handling imbalanced datasets and small-volume organs effectively for better clinical research.

Contribution

The paper presents an innovative 3D Non-local Network with Voting (3DNNV) framework that enhances nomenclature standardization in radiotherapy by simulating clinician recognition and addressing data imbalance issues.

Findings

3DNNV achieved higher true positive rates across datasets.

It significantly improved F1 scores for small-volume organs with limited training data.

The framework demonstrated strong generalizability across multiple institutions.

Abstract

The automatic standardization of nomenclature for anatomical structures in radiotherapy (RT) clinical data is a critical prerequisite for data curation and data-driven research in the era of big data and artificial intelligence, but it is currently an unmet need. Existing methods either cannot handle cross-institutional datasets or suffer from heavy imbalance and poor-quality delineation in clinical RT datasets. To solve these problems, we propose an automated structure nomenclature standardization framework, 3D Non-local Network with Voting (3DNNV). This framework consists of an improved data processing strategy, namely, adaptive sampling and adaptive cropping (ASAC) with voting, and an optimized feature extraction module. The framework simulates clinicians' domain knowledge and recognition mechanisms to identify small-volume organs at risk (OARs) with heavily imbalanced data better than other methods. We used partial data from an open-source head-and-neck cancer dataset to train the model, then tested the model on three cross-institutional datasets to demonstrate its generalizability. 3DNNV outperformed the baseline model, achieving higher average true positive rates (TPR) overall categories on the three test datasets (+8.27%, +2.39%, and +5.53%, respectively). More importantly, the 3DNNV outperformed the baseline on the test dataset, 28.63% to 91.17%, in terms of F1 score for a small-volume OAR with only 9 training samples. The results show that 3DNNV can be applied to identify OARs, even error-prone ones. Furthermore, we discussed the limitations and applicability of the framework in practical scenarios. The framework we developed can assist in standardizing structure nomenclature to facilitate data-driven clinical research in cancer radiotherapy.