yngvemm

• Grøndahl, Aurora Rosvoll; Moe, Yngve Mardal; Kaushal, Christine Kiran; Huynh, Bao Ngoc; Rusten, Espen & Tomic, Oliver [Show all 12 contributors for this article] (2021). Deep learning-based automatic delineation of anal cancer gross tumour volume: a multimodality comparison of CT, PET and MRI. Acta Oncologica. ISSN 0284-186X. 61(1), p. 89–96. doi: 10.1080/0284186X.2021.1994645.
• Grøndahl, Aurora Rosvoll; Knudtsen, Ingerid Skjei; Huynh, Bao Ngoc; Mulstad, Martine; Moe, Yngve Mardal & Knuth, Franziska [Show all 12 contributors for this article] (2021). A comparison of methods for fully automatic segmentation of tumors and involved nodes in PET/CT of head and neck cancers. Physics in Medicine and Biology. ISSN 0031-9155. 66(6). doi: 10.1088/1361-6560/abe553.
• Moe, Yngve Mardal; Grøndahl, Aurora Rosvoll; Tomic, Oliver; Dale, Einar; Malinen, Eirik & Futsæther, Cecilia Marie (2021). Deep learning-based auto-delineation of gross tumour volumes and involved nodes in PET/CT images of head and neck cancer patients. European Journal of Nuclear Medicine and Molecular Imaging. ISSN 1619-7070. 48, p. 2782–2792. doi: 10.1007/s00259-020-05125-x. Full text in Research Archive Show summary

  Abstract Purpose Identification and delineation of the gross tumour and malignant nodal volume (GTV) in medical images are vital in radiotherapy. We assessed the applicability of convolutional neural networks (CNNs) for fully automatic delineation of the GTV from FDG-PET/CT images of patients with head and neck cancer (HNC). CNN models were compared to manual GTV delineations made by experienced specialists. New structure-based performance metrics were introduced to enable in-depth assessment of auto-delineation of multiple malignant structures in individual patients. Methods U-Net CNN models were trained and evaluated on images and manual GTV delineations from 197 HNC patients. The dataset was split into training, validation and test cohorts (n= 142, n = 15 and n = 40, respectively). The Dice score, surface distance metrics and the new structure-based metrics were used for model evaluation. Additionally, auto-delineations were manually assessed by an oncologist for 15 randomly selected patients in the test cohort. Results The mean Dice scores of the auto-delineations were 55%, 69% and 71% for the CT-based, PET-based and PET/CT-based CNN models, respectively. The PET signal was essential for delineating all structures. Models based on PET/CT images identified 86% of the true GTV structures, whereas models built solely on CT images identified only 55% of the true structures. The oncologist reported very high-quality auto-delineations for 14 out of the 15 randomly selected patients. Conclusions CNNs provided high-quality auto-delineations for HNC using multimodality PET/CT. The introduced structure-wise evaluation metrics provided valuable information on CNN model strengths and weaknesses for multi-structure auto-delineation.

View all works in Cristin

• Huynh, Bao Ngoc; Grøndahl, Aurora Rosvoll; Moe, Yngve Mardal; Tomic, Oliver; Dale, Einar & Malinen, Eirik [Show all 7 contributors for this article] (2021). Deep learning for automatic segmentation of head and neck cancers in PET/CT images: the simpler, the better.
• Grøndahl, Aurora Rosvoll; Huynh, Bao Ngoc; Moe, Yngve Mardal; Kaushal, Christine Kiran; Rusten, Espen & Tomic, Oliver [Show all 13 contributors for this article] (2021). Deep learning for automatic target volume delineation .
• Grøndahl, Aurora Rosvoll; Huynh, Bao Ngoc; Moe, Yngve Mardal; Kaushal, Christine Kiran; Rusten, Espen & Tomic, Oliver [Show all 12 contributors for this article] (2021). Deep learning-based automatic delineation of anal cancer gross tumour volume: A multimodality comparison of CT,PET and MRI.
• Grøndahl, Aurora Rosvoll; Huynh, Bao Ngoc; Moe, Yngve Mardal; Kaushal, Christine Kiran; Rusten, Espen & Tomic, Oliver [Show all 12 contributors for this article] (2021). Deep learning-based automatic delineation of anal cancer gross tumour volume: A multimodality comparison of CT, PET and MRI.
• Grøndahl, Aurora Rosvoll; Mulstad, Martine; Moe, Yngve Mardal; Knudtsen, Ingerid Skjei; Torheim, Turid Katrine Gjerstad & Tomic, Oliver [Show all 10 contributors for this article] (2019). Comparison of automatic tumour segmentation approaches for head and neck cancers in PET/CT images. Radiotherapy and Oncology. ISSN 0167-8140. 133, p. 557–557.
• Grøndahl, Aurora Rosvoll; Knudtsen, Ingerid Skjei; Mulstad, Martine; Tomic, Oliver; Moe, Yngve Mardal & Indahl, Ulf Geir [Show all 10 contributors for this article] (2019). Automatic tumour delineation of head and neck cancers in PET/CT images using thresholding and machine learning methods.

View all works in Cristin