Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions
Background and purpose: Autocontouring for radiotherapy has the potential to significantly save time and reduce interobserver variability. We aimed to assess the performance of a commercial autocontouring model for head and neck (H&N) patients in eight orientations relevant to particle therapy w...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Physics and Imaging in Radiation Oncology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405631623001185 |
| _version_ | 1797248351989661696 |
|---|---|
| author | Linda Chen Patricia Platzer Christian Reschl Mansure Schafasand Ankita Nachankar Christoph Lukas Hajdusich Peter Kuess Markus Stock Steven Habraken Antonio Carlino |
| author_facet | Linda Chen Patricia Platzer Christian Reschl Mansure Schafasand Ankita Nachankar Christoph Lukas Hajdusich Peter Kuess Markus Stock Steven Habraken Antonio Carlino |
| author_sort | Linda Chen |
| collection | DOAJ |
| description | Background and purpose: Autocontouring for radiotherapy has the potential to significantly save time and reduce interobserver variability. We aimed to assess the performance of a commercial autocontouring model for head and neck (H&N) patients in eight orientations relevant to particle therapy with fixed beam lines, focusing on validation and implementation for routine clinical use. Materials and methods: Autocontouring was performed on sixteen organs at risk (OARs) for 98 adult and pediatric patients with 137 H&N CT scans in eight orientations. A geometric comparison of the autocontours and manual segmentations was performed using the Hausdorff Distance 95th percentile, Dice Similarity Coefficient (DSC) and surface DSC and compared to interobserver variability where available. Additional qualitative scoring and dose-volume-histogram (DVH) parameters analyses were performed for twenty patients in two positions, consisting of scoring on a 0–3 scale based on clinical usability and comparing the mean (Dmean) and near-maximum (D2%) dose, respectively. Results: For the geometric analysis, the model performance in head-first-supine straight and hyperextended orientations was in the same range as the interobserver variability. HD95, DSC and surface DSC was heterogeneous in other orientations. No significant geometric differences were found between pediatric and adult autocontours. The qualitative scoring yielded a median score of ≥ 2 for 13/16 OARs while 7/32 DVH parameters were significantly different. Conclusions: For head-first-supine straight and hyperextended scans, we found that 13/16 OAR autocontours were suited for use in daily clinical practice and subsequently implemented. Further development is needed for other patient orientations before implementation. |
| first_indexed | 2024-03-08T18:29:49Z |
| format | Article |
| id | doaj.art-7f3c0b60551d4ab29722b96dd8d63e0b |
| institution | Directory Open Access Journal |
| issn | 2405-6316 |
| language | English |
| last_indexed | 2024-04-24T20:13:13Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Physics and Imaging in Radiation Oncology |
| spelling | doaj.art-7f3c0b60551d4ab29722b96dd8d63e0b2024-03-23T06:24:58ZengElsevierPhysics and Imaging in Radiation Oncology2405-63162024-01-0129100527Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positionsLinda Chen0Patricia Platzer1Christian Reschl2Mansure Schafasand3Ankita Nachankar4Christoph Lukas Hajdusich5Peter Kuess6Markus Stock7Steven Habraken8Antonio Carlino9MedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, Austria; Erasmus MC Cancer Institute, University Medical Center, Department of Radiotherapy, Rotterdam, the Netherlands; Delft University of Technology, Faculty of Mechanical, Maritime and Materials Engineering, Delft, the Netherlands; Leiden University Medical Center, Faculty of Medicine, Leiden, the Netherlands; Corresponding author at: Erasmus Medical Center, Dr. Molewaterplein 40, 3015 GD, Rotterdam, the Netherlands.MedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, Austria; Fachhochschule Wiener Neustadt, Department MedTech, Wiener Neustadt, AustriaMedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, AustriaMedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, Austria; Medical University of Vienna, Department of Radiation Oncology, Vienna, Austria; Karl Landsteiner University of Health Sciences, Department of Oncology, Krems an der Donau, AustriaMedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, Austria; ACMIT Gmbh, Department of Medicine, Wiener Neustadt, AustriaMedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, AustriaMedical University of Vienna, Department of Radiation Oncology, Vienna, AustriaMedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, Austria; Karl Landsteiner University of Health Sciences, Department of Oncology, Krems an der Donau, AustriaErasmus MC Cancer Institute, University Medical Center, Department of Radiotherapy, Rotterdam, the Netherlands; Holland Proton Therapy Center, Department of Medical Physics & Informatics, Delft, the NetherlandsMedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, AustriaBackground and purpose: Autocontouring for radiotherapy has the potential to significantly save time and reduce interobserver variability. We aimed to assess the performance of a commercial autocontouring model for head and neck (H&N) patients in eight orientations relevant to particle therapy with fixed beam lines, focusing on validation and implementation for routine clinical use. Materials and methods: Autocontouring was performed on sixteen organs at risk (OARs) for 98 adult and pediatric patients with 137 H&N CT scans in eight orientations. A geometric comparison of the autocontours and manual segmentations was performed using the Hausdorff Distance 95th percentile, Dice Similarity Coefficient (DSC) and surface DSC and compared to interobserver variability where available. Additional qualitative scoring and dose-volume-histogram (DVH) parameters analyses were performed for twenty patients in two positions, consisting of scoring on a 0–3 scale based on clinical usability and comparing the mean (Dmean) and near-maximum (D2%) dose, respectively. Results: For the geometric analysis, the model performance in head-first-supine straight and hyperextended orientations was in the same range as the interobserver variability. HD95, DSC and surface DSC was heterogeneous in other orientations. No significant geometric differences were found between pediatric and adult autocontours. The qualitative scoring yielded a median score of ≥ 2 for 13/16 OARs while 7/32 DVH parameters were significantly different. Conclusions: For head-first-supine straight and hyperextended scans, we found that 13/16 OAR autocontours were suited for use in daily clinical practice and subsequently implemented. Further development is needed for other patient orientations before implementation.http://www.sciencedirect.com/science/article/pii/S2405631623001185AutocontouringRadiation therapyArtificial IntelligenceHead and neck cancerAuto-segmentationOrgans-at-risk |
| spellingShingle | Linda Chen Patricia Platzer Christian Reschl Mansure Schafasand Ankita Nachankar Christoph Lukas Hajdusich Peter Kuess Markus Stock Steven Habraken Antonio Carlino Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions Physics and Imaging in Radiation Oncology Autocontouring Radiation therapy Artificial Intelligence Head and neck cancer Auto-segmentation Organs-at-risk |
| title | Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions |
| title_full | Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions |
| title_fullStr | Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions |
| title_full_unstemmed | Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions |
| title_short | Validation of a deep-learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions |
| title_sort | validation of a deep learning segmentation model for adult and pediatric head and neck radiotherapy in different patient positions |
| topic | Autocontouring Radiation therapy Artificial Intelligence Head and neck cancer Auto-segmentation Organs-at-risk |
| url | http://www.sciencedirect.com/science/article/pii/S2405631623001185 |
| work_keys_str_mv | AT lindachen validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT patriciaplatzer validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT christianreschl validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT mansureschafasand validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT ankitanachankar validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT christophlukashajdusich validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT peterkuess validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT markusstock validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT stevenhabraken validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions AT antoniocarlino validationofadeeplearningsegmentationmodelforadultandpediatricheadandneckradiotherapyindifferentpatientpositions |