Big Data Readiness in Radiation Oncology: An Efficient Approach for Relabeling Radiation Therapy Structures With Their TG-263 Standard Name in Real-World Data Sets

Abstract

PurposeTo prepare for big data analyses on radiation therapy data, we developed Stature, a tool-supported approach for standardization of structure names in existing radiation therapy plans. We applied the widely endorsed nomenclature standard TG-263 as the mapping target and quantified the structure name inconsistency in 2 real-world data sets.Methods and MaterialsThe clinically relevant structures in the radiation therapy plans were identified by reference to randomized controlled trials. The Stature approach was used by clinicians to identify the synonyms for each relevant structure, which was then mapped to the corresponding TG-263 name. We applied Stature to standardize the structure names for 654 patients with prostate cancer (PCa) and 224 patients with head and neck squamous cell carcinoma (HNSCC) who received curative radiation therapy at our institution between 2007 and 2017. The accuracy of the Stature process was manually validated in a random sample from each cohort. For the HNSCC cohort we measured the resource requirements for Stature, and for the PCa cohort we demonstrated its impact on an example clinical analytics scenario.ResultsAll but 1 synonym group (“Hydrogel”) was mapped to the corresponding TG-263 name, resulting in a TG-263 relabel rate of 99% (8837 of 8925 structures). For the PCa cohort, Stature matched a total of 5969 structures. Of these, 5682 structures were exact matches (ie, following local naming convention), 284 were matched via a synonym, and 3 required manual matching. This original radiation therapy structure names therefore had a naming inconsistency rate of 4.81%. For the HNSCC cohort, Stature mapped a total of 2956 structures (2638 exact, 304 synonym, 14 manual; 10.76% inconsistency rate) and required 7.5 clinician hours. The clinician hours required were one-fifth of those that would be required for manual relabeling. The accuracy of Stature was 99.97% (PCa) and 99.61% (HNSCC).ConclusionsThe Stature approach was highly accurate and had significant resource efficiencies compared with manual curation.

Technical Note: An open source solution for improving TG‐263 compliance

“…Schuler et. al reported on a tool, Stature, to retrospectively relabel structures in existing radiotherapy plans . This tool was also implemented in the TPS and required physician review of structure names to ensure correct mapping.…”

Radiation Therapy Quality Assurance Tasks and Tools: The Many Roles of Machine Learning

“…One way to tackle the problem of poor data structure in both retrospective and currently generated information is to automate processing of already stored data. Schuler et al., for example, developed a tool to retroactively standardize structure names in RT Plans in conformance with TG 263 by renaming those structures . In that study, they had panel of experts develop a mapping and structure synonym set for 36 structures in the clinical database.…”

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

“…This is a prerequisite for clinical data curation and datadriven research, especially in the era of big data and artificial intelligence [1,4,5,6,7]. However, because of differences in local policies, vendors, and language environments, structure labels are often inconsistent [8,9]. A large number of retrospective RT datasets [10,11] cannot be shared and reused without consistent labels, and manually cleaning RT data is very expensive and time-consuming [8,9,12,13,14].…”

“…However, because of differences in local policies, vendors, and language environments, structure labels are often inconsistent [8,9]. A large number of retrospective RT datasets [10,11] cannot be shared and reused without consistent labels, and manually cleaning RT data is very expensive and time-consuming [8,9,12,13,14]. Therefore, it is necessary to develop software tools to automate nomenclature standardization to facilitate datadriven clinical research.…”

“…Previous works have proposed standardizing the nomenclature of anatomical structures via text-based methods that rely on label matching and clinicians' intervention to correct mismatched labels at a single institution [8,15,16]. However, language constantly changes, and different naming conventions make the convert the task of structure nomenclature standardization to OAR classification based on deep learning (DL) frameworks [17,20].…”