Parotid gland segmentation with nnU-Net: deployment scenario and inter-observer variability analysis
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Parotid gland segmentation with nnU-Net : deployment scenario and inter-observer variability analysis. / Podobnik, Gašper; Strojan, Primož; Peterlin, Primož; Ibragimov, Bulat; Vrtovec, Tomaž.
Medical Imaging 2022: Image Processing. ed. / Olivier Colliot; Ivana Isgum; Bennett A. Landman; Murray H. Loew. SPIE, 2022. p. 1-8 120321N (Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol. 12032).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Parotid gland segmentation with nnU-Net
T2 - Medical Imaging 2022: Image Processing
AU - Podobnik, Gašper
AU - Strojan, Primož
AU - Peterlin, Primož
AU - Ibragimov, Bulat
AU - Vrtovec, Tomaž
N1 - Publisher Copyright: © 2022 SPIE
PY - 2022
Y1 - 2022
N2 - Head and neck cancer is the sixth most common form of cancer in the world population. A commonly used treatment is radiotherapy, which requires physicians to first segment organs at risk (OARs) and tumors in computed tomography images, which is a laborious and time-consuming process. Therefore, a lot of research is being done to develop automatic methods for OAR segmentation. In this paper, we present the results of parotid gland segmentation with nnU-Net using data from two public datasets (Head-Neck-Radiomics-HN1 and PDDCA) and one private dataset acquired at the local hospital. To simulate a possible model deployment scenario, the first model was trained only on publicly available datasets and evaluated on the private dataset, and then compared to the second model that was trained on the same data with additional 10 images from the private dataset. We enrich the interpretation of the results with the comparison among different datasets and among delineations generated with a deep learning model against the delineations of a junior and senior expert that are available for our private dataset. Significant differences were observed among model performance on different datasets, but not among different observers. The performance of nnU-Net on the PDDCA dataset is on par with the state-of-the-art results reported in the literature. Also, the method performed very well compared to the inter-observer variability calculated on our private dataset.
AB - Head and neck cancer is the sixth most common form of cancer in the world population. A commonly used treatment is radiotherapy, which requires physicians to first segment organs at risk (OARs) and tumors in computed tomography images, which is a laborious and time-consuming process. Therefore, a lot of research is being done to develop automatic methods for OAR segmentation. In this paper, we present the results of parotid gland segmentation with nnU-Net using data from two public datasets (Head-Neck-Radiomics-HN1 and PDDCA) and one private dataset acquired at the local hospital. To simulate a possible model deployment scenario, the first model was trained only on publicly available datasets and evaluated on the private dataset, and then compared to the second model that was trained on the same data with additional 10 images from the private dataset. We enrich the interpretation of the results with the comparison among different datasets and among delineations generated with a deep learning model against the delineations of a junior and senior expert that are available for our private dataset. Significant differences were observed among model performance on different datasets, but not among different observers. The performance of nnU-Net on the PDDCA dataset is on par with the state-of-the-art results reported in the literature. Also, the method performed very well compared to the inter-observer variability calculated on our private dataset.
KW - Deep Learning
KW - Head and Neck Cancer
KW - Inter-observer Variability
KW - nnU-Net
KW - Organs at Risk
KW - Parotid Glands
KW - Segmentation
U2 - 10.1117/12.2609406
DO - 10.1117/12.2609406
M3 - Article in proceedings
AN - SCOPUS:85131917270
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
SP - 1
EP - 8
BT - Medical Imaging 2022
A2 - Colliot, Olivier
A2 - Isgum, Ivana
A2 - Landman, Bennett A.
A2 - Loew, Murray H.
PB - SPIE
Y2 - 21 March 2021 through 27 March 2021
ER -
ID: 314303221