Abstract Purpose: We developed Label-It, a new web-application for rapid review of radiotherapy (RT) target volumes, and used it to evaluate the relationship between target delineation compliance to the international guidelines and treatment outcomes of nasopharyngeal carcinoma (NPC) patients undergoing definitive RT. Methods and Materials: Our radiographic image database consists of anonymized simulation CT scans, RT structures, and treatment data of 3,211 head and neck cancer patients treated between July 2005 and August 2017. We used 332 patients treated with intensity-modulated RT for pathologically confirmed NPC as the study cohort and imported intermediate risk clinical target volumes of the primary tumor (IR-CTVp) receiving 56 Gy into Label-It. We determined inclusion of anatomic sites within IR-CTVp in accordance with 2018 International guideline for CTV delineation for NPC and correlated the results with time to local failure (TTLF) using Cox-regression. Results: At a median follow-up of 5.6 years, 5-year TTLF and overall survival rates were 93.1% and 85.9% respectively. The most frequently non-compliant anatomic sites were sphenoid sinus (n = 69, 20.8%), followed by cavernous sinus (n = 38, 11.4%), left and right petrous apices (n = 37 and 32, 11.1% and 9.6%), clivus (n = 14, 4.2%), and right and left foramen rotundum (n = 14 and 12, 4.2% and 3.6%). Among 23 patients with a local failure (6.9%), the number of non-compliant cases were 8 for sphenoid sinus, 7 cavernous sinus, 4 left and 3 right petrous apices, and 2 clivus. In Cox regression analysis, T4 disease (p = 0.003), RT alone (p = 0.007), cavernous sinus non-conformity (p = 0.020) were independent prognostic factors for TTLF. Conclusions: Label-It was an effective tool for rapid review of target volumes in a large patient cohort. Despite a high compliance to the international guidelines, inadequate coverage of cavernous sinus was correlated with decreased TTLF. Citation Format: Jun Won Kim, Joseph Marsilla, Michal Kazmierski, Denis Tkachuk, Benjamin Haibe-Kains, Andrew Hope. Development of web-based quality-assurance tool for radiotherapy target delineation for head and neck cancer: Quality evaluation of nasopharyngeal carcinoma [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-051.
Abstract Purpose This manuscript presents RADCURE, one of the most extensive head and neck cancer (HNC) imaging datasets accessible to the public. Initially collected for clinical radiation therapy (RT) treatment planning, this dataset has been retrospectively reconstructed for use in imaging research. Acquisition and Validation Methods RADCURE encompasses data from 3346 patients, featuring computed tomography (CT) RT simulation images with corresponding target and organ‐at‐risk contours. These CT scans were collected using systems from three different manufacturers. Standard clinical imaging protocols were followed, and contours were manually generated and reviewed at weekly RT quality assurance rounds. RADCURE imaging and structure set data was extracted from our institution's radiation treatment planning and oncology information systems using a custom‐built data mining and processing system. Furthermore, images were linked to our clinical anthology of outcomes data for each patient and includes demographic, clinical and treatment information based on the 7th edition TNM staging system (Tumor‐Node‐Metastasis Classification System of Malignant Tumors). The median patient age is 63, with the final dataset including 80% males. Half of the cohort is diagnosed with oropharyngeal cancer, while laryngeal, nasopharyngeal, and hypopharyngeal cancers account for 25%, 12%, and 5% of cases, respectively. The median duration of follow‐up is five years, with 60% of the cohort surviving until the last follow‐up point. Data Format and Usage Notes The dataset provides images and contours in DICOM CT and RT‐STRUCT formats, respectively. We have standardized the nomenclature for individual contours—such as the gross primary tumor, gross nodal volumes, and 19 organs‐at‐risk—to enhance the RT‐STRUCT files’ utility. Accompanying demographic, clinical, and treatment data are supplied in a comma‐separated values (CSV) file format. This comprehensive dataset is publicly accessible via The Cancer Imaging Archive. Potential Applications RADCURE's amalgamation of imaging, clinical, demographic, and treatment data renders it an invaluable resource for a broad spectrum of radiomics image analysis research endeavors. Researchers can utilize this dataset to advance routine clinical procedures using machine learning or artificial intelligence, to identify new non‐invasive biomarkers, or to forge prognostic models.
Background Machine learning and AI promise to revolutionize the way we leverage medical imaging data for improving care but require large datasets to train computational models that can be implemented in clinical practice. However, processing large and complex medical imaging datasets remains an open challenge. Methods To address this issue, we developed Med-ImageTools, a new Python open-source software package to automate data curation and processing while allowing researchers to share their data processing configurations more easily, lowering the barrier for other researchers to reproduce published works. Use cases We have demonstrated the efficiency of Med-ImageTools across three different datasets, resulting in significantly reduced processing times. Conclusions The AutoPipeline feature will improve the accessibility of raw clinical datasets on public archives, such as the Cancer Imaging Archive (TCIA), the largest public repository of cancer imaging, allowing machine learning researchers to process analysis-ready formats without requiring deep domain knowledge.
Abstract Open source code helps the scientific community converge to breakthroughs at an accelerated rate. Only one of 14 previous deep learning based OAR segmentation studies met most open-source standards. Using this study as a benchmark, we will assess the segmentation quality of each network discussed and provide the community with pre-trained weights of the top-performing models. 11 open-source 3D segmentation models originally engineered for medical image segmentation in both the 2D and 3D domains were trained to automatically segment 19 OaR classes. For this study, a large internally curated dataset from the University Health Network (UHN) of 582 patient scans was used. All models were tested on a hold out set from the 582 cohort of 59 patients. Models were also tested on 98 external patient scans from publicly available sources. 10 test set contours from the winning network were assessed by an expert radiation oncologist with 10+ years of experience to identify the observer of the contour set (whether AI or human). Preliminary results show that only 13 out of 20 scans were identified correctly. Results show that simple 3D architectures consistently outcompete more complex networks by producing more accurate, clinically acceptable contours. A more thorough clinical acceptability test is underway to establish a protocol for integrating deep learning based auto contouring models into radiation therapy planning workflows. Citation Format: Joseph Marsilla, Benjamin Haibe-Kains. Evaluating clinical utility of organs-at-risk segmentation in head & neck cancer by simple open-source 3D CNNs [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-031.
Abstract Purpose We developed QUANNOTATE , a new web-application for rapid review of radiotherapy (RT) target volumes, and used it to evaluate the relationship between target delineation compliance with the international guidelines and treatment outcomes in nasopharyngeal carcinoma (NPC) patients undergoing definitive RT. Methods and Materials The dataset used for this study consists of anonymized CT simulation scans, RT structures, and clinical data of 332 pathologically confirmed NPC patients treated with intensity-modulated RT between July 2005 and August 2017. We imported the contours of intermediate risk clinical target volumes of the primary tumor (IR-CTVp) receiving 56 Gy into QUANNOTATE . We determined inclusion of anatomic sites within IR-CTVp in accordance with 2018 International guideline for CTV delineation for NPC and correlated the results with time to local failure (TTLF) using Cox-regression. Results At a median follow-up of 5.6 years, 5-year TTLF and overall survival rates were 93.1% and 85.9% respectively. The most frequently non-guideline compliant anatomic sites were sphenoid sinus (n = 69, 20.8%), followed by cavernous sinus (n = 38, 19.3%), left and right petrous apices (n = 37 and 32, 11.1% and 9.6%), clivus (n = 14, 4.2%), and right and left foramen rotundum (n = 14 and 12, 4.2% and 3.6%). Among 23 patients with a local failure (6.9%), the number of non-compliant cases were 8 for sphenoid sinus, 7 cavernous sinus, 4 left and 3 right petrous apices, and 2 clivus. Compared to conforming cases, cases which did not contour the cavernous sinus had a higher local failure (LF) rate (89.1% vs 93.6%, p= 0.013). Multivariable analysis confirmed that lack of cavernous sinus contouring was prognostic for LF. Conclusions QUANNOTATE allowed rapid review of target volumes in a large patient cohort. Despite an overall high compliance with the international guidelines, undercoverage of the cavernous sinus was correlated with LF.
