HEad and neCK TumOR segmentation and outcome prediction in PET/CT images
- 1. Institute of Information Systems, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland
- 2. Institute of Information Systems, University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland AND Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
- 3. Martin Vallières
- 4. LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
- 5. Nuclear medicine department, CHU Poitiers, Poitiers, France and LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
- 6. Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
- 7. Cleveland Clinic Foundation, Department of Radiation Oncology, Cleveland, OH, USA
Head and Neck (H&N) cancers are among the most common cancers worldwide (5th leading cancer by incidence) (Parkin et al. 2005). Radiotherapy combined with cetuximab has been established as standard treatment (Bonner et al. 2010). However, locoregional failures remain a major challenge and occur in up to 40% of patients in the first two years after the treatment (Chajon et al. 2013). Recently, several radiomics studies based on Positron Emission Tomography (PET) and Computed Tomography (CT) imaging were proposed to better identify patients with a worse prognosis in a non-invasive fashion and by exploiting already available images such as these acquired for diagnosis and treatment planning (Vallières et al. 2017),(Bogowicz et al. 2017),(Castelli et al. 2017). Although highly promising, these methods were validated on 100-400 patients. Further validation on larger cohorts (e.g. 300-3000 patients) is required to ensure an adequate ratio between the number of variables and observations in order to avoid an overestimation of the generalization performance. Achieving such a validation requires the manual delineation of primary tumors and nodal metastases for every patient and in three dimensions, which is intractable and error-prone.
Methods for automated lesion segmentation in medical images were proposed in various contexts, often achieving expert-level performance (Heimann and Meinzer 2009), (Menze et al. 2015). Surprisingly few studies evaluated the performance of computerized automated segmentation of tumor lesions in PET and CT images (Song et al. 2013),(Blanc-Durand et al. 2018), (Moe et al. 2019).
In 2020, we organized the first HECKTOR challenge to offer an opportunity for participants working on 3D segmentation algorithms to develop automatic bi-modal approaches for the segmentation of H&N tumors in PET/CT scans, focusing on oropharyngeal cancers. Following good participation and promising results in the 2020 challenge, we will increase the dataset size with 81 new cases provided by additional organization partners, from another clinical center with a different PET/CT scanner model and associated reconstruction settings (CHU Milétrie, Poitiers, France). In addition, we expand the scope of the challenge by considering an additional task with the purpose of outcome prediction based on the PET/CT images. A clinically-relevant endpoint that can be leveraged for personalizing patient management at diagnosis will be considered: prediction of progression-free survival from diagnostic PET/CT images. By focusing on metabolic and morphological tissue properties respectively, PET and CT modalities include complementary and synergistic information for cancerous lesion segmentation as well as tumor characteristics relevant for patient outcome prediction, in addition to usual clinical variables (e.g., clinical stage, age, gender, treatment modality). Modern image analysis methods must be developed to best extract and leverage this information. The data used in this challenge is multi centric, including four centers in Canada (Vallières et al. 2017), one center in Switzerland (Castelli et al. 2017), and one center in France (Hatt et al. 2019; Legot et al. 2018) for a total of 335 patients with annotated primary tumors.
Andrearczyk, Vincent, Valentin Oreiller, and Adrien Depeursinge. "Oropharynx detection in PET-CT for tumor segmentation." Irish Machine Vision and Image Processing (2020).
Blanc-Durand, Paul, Axel Van Der Gucht, Niklaus Schaefer, Emmanuel Itti, and John O. Prior. 2018. “Automatic Lesion Detection and Segmentation of 18F-FET PET in Gliomas: A Full 3D U-Net Convolutional Neural Network Study.” PloS One 13 (4): e0195798.
Bogowicz, Marta, Oliver Riesterer, Luisa Sabrina Stark, Gabriela Studer, Jan Unkelbach, Matthias Guckenberger, and Stephanie Tanadini-Lang. 2017. “Comparison of PET and CT Radiomics for Prediction of Local Tumor Control in Head and Neck Squamous Cell Carcinoma.” Acta Oncologica 56 (11): 1531–36.
Bonner, James A., Paul M. Harari, Jordi Giralt, Roger B. Cohen, Christopher U. Jones, Ranjan K. Sur, David Raben, et al. 2010. “Radiotherapy plus Cetuximab for Locoregionally Advanced Head and Neck Cancer: 5-Year Survival Data from a Phase 3 Randomised Trial, and Relation between Cetuximab-Induced Rash and Survival.” The Lancet Oncology 11 (1): 21–28.
Castelli, J., A. Depeursinge, V. Ndoh, J. O. Prior, M. Ozsahin, A. Devillers, H. Bouchaab, et al. 2017. “A PET-Based Nomogram for Oropharyngeal Cancers.” European Journal of Cancer 75 (April): 222–30.
Chajon, Enrique, Caroline Lafond, Guillaume Louvel, Joël Castelli, Danièle Williaume, Olivier Henry, Franck Jégoux, et al. 2013. “Salivary Gland-Sparing Other than Parotid-Sparing in Definitive Head-and-Neck Intensity-Modulated Radiotherapy Does Not Seem to Jeopardize Local Control.” Radiation Oncology. https://doi.org/10.1186/1748-717x-8-132.
Harrell, Frank E. 1982. “Evaluating the Yield of Medical Tests.” JAMA: The Journal of the American Medical Association. https://doi.org/10.1001/jama.1982.03320430047030.
Hatt, Mathieu, Catherine Cheze le Rest, Alexandre Turzo, Christian Roux, and Dimitris Visvikis. 2009. “A Fuzzy Locally Adaptive Bayesian Segmentation Approach for Volume Determination in PET.” IEEE Transactions on Medical Imaging 28 (6): 881–93.
Hatt, Mathieu, Florent Tixier, Marie-Charlotte Desseroit, Bogdan Badic, Baptiste Laurent, Dimitris Visvikis, and Catherine Cheze Le Rest. 2019. “Revisiting the Identification of Tumor Sub-Volumes Predictive of Residual Uptake after (chemo)radiotherapy: Influence of Segmentation Methods on F-FDG PET/CT Images.” Scientific Reports 9 (1): 14925.
Heimann, Tobias, and Hans-Peter Meinzer. 2009. “Statistical Shape Models for 3D Medical Image Segmentation: A Review.” Medical Image Analysis. https://doi.org/10.1016/j.media.2009.05.004.
Legot, Floriane, Florent Tixier, Minea Hadzic, Thomas Pinto-Leite, Christelle Gallais, Rémy Perdrisot, Xavier Dufour, and Catherine Cheze-Le-Rest. 2018. “Use of Baseline 18F-FDG PET Scan to Identify Initial Sub-Volumes with Local Failure after Concomitant Radio-Chemotherapy in Head and Neck Cancer.” Oncotarget 9 (31): 21811–19.
Menze, Bjoern H., Andras Jakab, Stefan Bauer, Jayashree Kalpathy-Cramer, Keyvan Farahani, Justin Kirby, Yuliya Burren, et al. 2015. “The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS).” IEEE Transactions on Medical Imaging 34 (10): 1993–2024.
Parkin, D. M., F. Bray, J. Ferlay, and P. Pisani. 2005. “Global Cancer Statistics, 2002.” CA: A Cancer Journal for Clinicians. https://doi.org/10.3322/canjclin.55.2.74.
Song, Qi, Junjie Bai, Dongfeng Han, Sudershan Bhatia, Wenqing Sun, William Rockey, John E. Bayouth, John M. Buatti, and Xiaodong Wu. 2013. “Optimal Co-Segmentation of Tumor in PET-CT Images with Context Information.” IEEE Transactions on Medical Imaging 32 (9): 1685–97.
Uno, Hajime, Tianxi Cai, Michael J. Pencina, Ralph B. D’Agostino, and L. J. Wei. 2011. “On the C-Statistics for Evaluating Overall Adequacy of Risk Prediction Procedures with Censored Survival Data.” Statistics in Medicine 30 (10): 1105–17.
Vallières, Martin, Emily Kay-Rivest, Léo Jean Perrin, Xavier Liem, Christophe Furstoss, Hugo J. W. L. Aerts, Nader Khaouam, et al. 2017. “Radiomics Strategies for Risk Assessment of Tumour Failure in Head-and-Neck Cancer.” Scientific Reports 7 (1): 10117.
Warfield, Simon K., Kelly H. Zou, and William M. Wells. 2004. “Simultaneous Truth and Performance Level Estimation (STAPLE): An Algorithm for the Validation of Image Segmentation.” IEEE Transactions on Medical Imaging 23 (7): 903–21.
Grossberg A, Mohamed A, Elhalawani H, Bennett W, Smith K, Nolan T, Chamchod S, Kantor M, Browne T, Hutcheson K, Gunn G, Garden A, Frank S, Rosenthal D, Freymann J, Fuller C.(2017). Data from Head and Neck Cancer CT Atlas. The Cancer Imaging Archive. DOI: 10.7937/K9/TCIA.2017.umz8dv6s
Moe, Yngve Mardal, Aurora Rosvoll Groendahl, Martine Mulstad, Oliver Tomic, Ulf Indahl, Einar Dale, Eirik Malinen, and Cecilia Marie Futsaether. "Deep learning for automatic tumour segmentation in PET/CT images of patients with head and neck cancers." (2019).
Wee, L., & Dekker, A. (2019). Data from Head-Neck-Radiomics-HN1 [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/tcia.2019.8kap372n