A Machine Learning method for relabeling arbitrary DICOM structure sets to TG-263 defined labels

Radiotherapy (RT) datasets can suffer from variations in annotation of organ at risk (OAR) and target structures.Annotation standards exist,but their description for prostate targets is limited. This restricts the use of such data for supervised machine learning purposes as it requires properly annotated data. The aim of this work was to develop a modality independent deep learning (DL) model for automatic classification and annotation of prostate RT DICOM structures. Delineated prostate organs at risk (OAR), support-and target structures (gross tumor volume [GTV]/clinical target volume [CTV]/planning target volume [PTV]), along with or without separate vesicles and/or lymph nodes, were extracted as binary masks from 1854 patients. An image modality independent 2D Inception-ResNetV2 classification network was trained with varying amounts of training data using four image input channels. Channel 1-3 consisted of orthogonal 2D projections from each individual binary structure. The fourth channel contained a summation of the other available binary structure masks. Structure classification performance was assessed in independent CT (n = 200 pat) and magnetic resonance imaging (MRI) (n = 40 pat) test datasets and an external CT (n = 99 pat) dataset from another clinic. A weighted classification accuracy of 99.4% was achieved during training. The unweighted classification accuracy and the weighted average F1 score among different structures in the CT test dataset were 98.8% and 98.4% and 98.6% and 98.5% for the MRI test dataset, respectively. The external CT dataset yielded the corresponding results 98.4% and 98.7% when analyzed for trained structures only, and results from the full dataset yielded 79.6% and 75.2%. Most misclassifications in the external CT dataset occurred due to multiple CTVs and PTVs being fused together, which was not included in the training data. Our proposed DL-based method for automated renaming and standardization of prostate radiotherapy annotations shows great potential. Clinic specific contouring standards however need to be represented in the training data for successful use.

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning‐based classification and structure name standardization for organ at risk and target delineations in prostate cancer radiotherapy

Gustafsson

Lempart

Swärd

et al. 2021

“…In addition to simple text mapping, Machine Learning based methods are being used to automate the process of relabeling physician specified target and OAR names to the TG-263 specified names. Success in this approach has been shown using target and OAR text labels, 19 geometric information, [20][21][22] and radiomics features, 23…”

Section: B2 | Tps-hinge Integrationmentioning

confidence: 99%

“…In addition to simple text mapping, Machine Learning based methods are being used to automate the process of relabeling physician specified target and OAR names to the TG‐263 specified names. Success in this approach has been shown using target and OAR text labels, 19 geometric information, 20–22 and radiomics features, 23 all found in the DICOM structure set, dose, and reference imaging (CT) datasets. All these methods have shown reasonably good accuracy over many different structure types, and the HINGE platform has the capability of deploying such methods as it has all of the treatment planning DICOM files as well as access to cloud‐based machine learning frameworks including Amazon Web Services (AWS) Elastic Map Reduce and Deep Learning Containers.…”

Section: Key Design Featuresmentioning

confidence: 99%

Automated data abstraction for quality surveillance and outcome assessment in radiation oncology

Kapoor

Sleeman

Nalluri

et al. 2021

Self Cite

Rigorous radiotherapy quality surveillance and comprehensive outcome assessment require electronic capture and automatic abstraction of clinical, radiation treatment planning, and delivery data. We present the design and implementation framework of an integrated data abstraction, aggregation, and storage, curation, and analytics software: the Health Information Gateway and Exchange (HINGE), which collates data for cancer patients receiving radiotherapy. The HINGE software abstracts structured DICOM-RT data from the treatment planning system (TPS), treatment data from the treatment management system (TMS), and clinical data from the electronic health records (EHRs). HINGE software has disease site-specific "Smart" templates that facilitate the entry of relevant clinical information by physicians and clinical staff in a discrete manner as part of the routine clinical documentation.Radiotherapy data abstracted from these disparate sources and the smart templates are processed for quality and outcome assessment. The predictive data analyses are done on using well-defined clinical and dosimetry quality measures defined by disease site experts in radiation oncology. HINGE application software connects seamlessly to the local IT/medical infrastructure via interfaces and cloud services and performs data extraction and aggregation functions without human intervention. It provides tools to assess variations in radiation oncology practices and outcomes and determines gaps in radiotherapy quality delivered by each provider. K E Y W O R D S big data in radiation oncology, quality surveillance 1 | INTRODUCTION Advanced technologies in health care are bringing a sharper focus on clinical outcome assessment and the assessment of health care quality. Manual abstraction, collation, and subsequent analysis of health care quality from patient treatment and outcome data are onerous, expensive, and impractical. Advances in computer storage, computing power, and the ability to electronically mine data from disparate sources (e.g., demographics, genetics, imaging, treatment, clinical decisions, and outcomes) have enabled big data research in medicine. The evolution of several initiatives in the realm of interconnectivity of health care data sources and the availability of advanced computing frameworks have opened doors for answering a broad array of questions related to quality, safety, and outcomes of

Deep learning‐based classification of organs at risk and delineation guideline in pelvic cancer radiation therapy

Lempart

Scherman

Nilsson

et al. 2023

Deep learning (DL) models for radiation therapy (RT) image segmentation require accurately annotated training data. Multiple organ delineation guidelines exist; however, information on the used guideline is not provided with the delineation. Extraction of training data with coherent guidelines can therefore be challenging. We present a supervised classification method for pelvis structure delineations where bowel cavity, femoral heads, bladder, and rectum data, with two guidelines, were classified. The impact on DL‐based segmentation quality using mixed guideline training data was also demonstrated. Bowel cavity was manually delineated on CT images for anal cancer patients (n = 170) according to guidelines Devisetty and RTOG. The DL segmentation quality from using training data with coherent or mixed guidelines was investigated. A supervised 3D squeeze‐and‐excite SENet‐154 model was trained to classify two bowel cavity delineation guidelines. In addition, a pelvis CT dataset with manual delineations from prostate cancer patients (n = 1854) was used where data with an alternative guideline for femoral heads, rectum, and bladder were generated using commercial software. The model was evaluated on internal (n = 200) and external test data (n = 99). By using mixed, compared to coherent, delineation guideline training data mean DICE score decreased 3% units, mean Hausdorff distance (95%) increased 5 mm and mean surface distance (MSD) increased 1 mm. The classification of bowel cavity test data achieved 99.8% unweighted classification accuracy, 99.9% macro average precision, 97.2% macro average recall, and 98.5% macro average F1. Corresponding metrics for the pelvis internal test data were all 99% or above and for the external pelvis test data they were 96.3%, 96.6%, 93.3%, and 94.6%. Impaired segmentation performance was observed for training data with mixed guidelines. The DL delineation classification models achieved excellent results on internal and external test data. This can facilitate automated guideline‐specific data extraction while avoiding the need for consistent and correct structure labels.