Search

Your search keyword '"Hurkmans Coen W"' showing total 2 results
Start Over Author "Hurkmans Coen W" Publisher elsevier
2 results on '"Hurkmans Coen W"'

1. Anatomical evaluation of deep-learning synthetic computed tomography images generated from male pelvis cone-beam computed tomography

Author

de Hond, Yvonne J.M., Kerckhaert, Camiel E.M., van Eijnatten, Maureen A.J.M., van Haaren, Paul M.A., Hurkmans, Coen W., Tijssen, Rob H.N., Medical Image Analysis, and EAISI Health

Subjects
Radiation, Deep-Learning, Volume difference, Anatomical comparison, SDG 3 - Good Health and Well-being, Average surface distance, Synthetic computed tomography, Cone-beam computed tomography, Radiology, Nuclear Medicine and imaging, SDG 3 – Goede gezondheid en welzijn
Abstract

Background and purpose: To improve cone-beam computed tomography (CBCT), deep-learning (DL)-models are being explored to generate synthetic CTs (sCT). The sCT evaluation is mainly focused on image quality and CT number accuracy. However, correct representation of daily anatomy of the CBCT is also important for sCTs in adaptive radiotherapy. The aim of this study was to emphasize the importance of anatomical correctness by quantitatively assessing sCT scans generated from CBCT scans using different paired and unpaired DL-models. Materials and methods: Planning CTs (pCT) and CBCTs of 56 prostate cancer patients were included to generate sCTs. Three different DL-models, Dual-UNet, Single-UNet and Cycle-consistent Generative Adversarial Network (CycleGAN), were evaluated on image quality and anatomical correctness. The image quality was assessed using image metrics, such as Mean Absolute Error (MAE). The anatomical correctness between sCT and CBCT was quantified using organs-at-risk volumes and average surface distances (ASD). Results: MAE was 24 Hounsfield Unit (HU) [range:19-30 HU] for Dual-UNet, 40 HU [range:34-56 HU] for Single-UNet and 41HU [range:37-46 HU] for CycleGAN. Bladder ASD was 4.5 mm [range:1.6–12.3 mm] for Dual-UNet, 0.7 mm [range:0.4–1.2 mm] for Single-UNet and 0.9 mm [range:0.4–1.1 mm] CycleGAN. Conclusions: Although Dual-UNet performed best in standard image quality measures, such as MAE, the contour based anatomical feature comparison with the CBCT showed that Dual-UNet performed worst on anatomical comparison. This emphasizes the importance of adding anatomy based evaluation of sCTs generated by DL-models. For applications in the pelvic area, direct anatomical comparison with the CBCT may provide a useful method to assess the clinical applicability of DL-based sCT generation methods.

Published
2023

2. Organ at risk delineation for radiation therapy clinical trials: Global Harmonization Group consensus guidelines

Author

Mir, Romaana; https://orcid.org/0000-0002-2807-4525, Kelly, Sarah M; https://orcid.org/0000-0002-0318-9940, Xiao, Ying, Moore, Alisha, Clark, Catharine H; https://orcid.org/0000-0003-2287-8212, Clementel, Enrico, Corning, Coreen; https://orcid.org/0000-0001-6962-6501, Ebert, Martin, Hoskin, Peter, Hurkmans, Coen W, Ishikura, Satoshi, Kristensen, Ingrid, Kry, Stephen F, Lehmann, Joerg, Michalski, Jeff M, Monti, Angelo F, Nakamura, Mitsuhiro, Thompson, Kenton, Yang, Huiqi, Zubizarreta, Eduardo, Andratschke, Nicolaus; https://orcid.org/0000-0003-3647-5916, Miles, Elizabeth, Mir, Romaana; https://orcid.org/0000-0002-2807-4525, Kelly, Sarah M; https://orcid.org/0000-0002-0318-9940, Xiao, Ying, Moore, Alisha, Clark, Catharine H; https://orcid.org/0000-0003-2287-8212, Clementel, Enrico, Corning, Coreen; https://orcid.org/0000-0001-6962-6501, Ebert, Martin, Hoskin, Peter, Hurkmans, Coen W, Ishikura, Satoshi, Kristensen, Ingrid, Kry, Stephen F, Lehmann, Joerg, Michalski, Jeff M, Monti, Angelo F, Nakamura, Mitsuhiro, Thompson, Kenton, Yang, Huiqi, Zubizarreta, Eduardo, Andratschke, Nicolaus; https://orcid.org/0000-0003-3647-5916, and Miles, Elizabeth

Abstract

Background and purpose: The Global Quality Assurance of Radiation Therapy Clinical Trials Harmonization Group (GHG) is a collaborative group of Radiation Therapy Quality Assurance (RTQA) Groups harmonizing and improving RTQA for multi-institutional clinical trials. The objective of the GHG OAR Working Group was to unify OAR contouring guidance across RTQA groups by compiling a single reference list of OARs in line with AAPM TG 263 and ASTRO, together with peer-reviewed, anatomically defined contouring guidance for integration into clinical trial protocols independent of the radiation therapy delivery technique. Materials and methods: The GHG OAR Working Group comprised of 22 multi-professional members from 6 international RTQA Groups and affiliated organizations conducted the work in 3 stages: (1) Clinical trial documentation review and identification of structures of interest (2) Review of existing contouring guidance and survey of proposed OAR contouring guidance (3) Review of survey feedback with recommendations for contouring guidance with standardized OAR nomenclature. Results: 157 clinical trials were examined; 222 OAR structures were identified. Duplicates, non-anatomical, non-specific, structures with more specific alternative nomenclature, and structures identified by one RTQA group were excluded leaving 58 structures of interest. 6 OAR descriptions were accepted with no amendments, 41 required minor amendments, 6 major amendments, 20 developed as a result of feedback, and 5 structures excluded in response to feedback. The final GHG consensus guidance includes 73 OARs with peer-reviewed descriptions (Appendix A). Conclusion: We provide OAR descriptions with standardized nomenclature for use in clinical trials. A more uniform dataset supports the delivery of clinically relevant and valid conclusions from clinical trials.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results