Abstract
Background: Accurate prognostic stratification and segmentation of Head-and-Neck Squamous-Cell-Carcinoma (HNSCC) patients can be an important clinical reference when designing therapeutic strategies. We set to automatically segment HNSCC using advanced deep learning techniques linked to the image fusion technique.
Method: 883 subjects were extracted from HECKTOR-Challenge. 524 subjects were considered for the training and validation procedure, and 359 subjects as external testing were employed to validate our segmentation models. First, PET images were registered to CT images. The resultant images are cropped after an enhancement procedure. Subsequently, a weighted fusion technique was employed to combine PET and CT information. To this end, we developed a Cascade-Net consisting of two states of art neural networks to segment the tumors via the fused image. Our segmentation framework performs in three main stages. In the first stage, which is an organ localizer module, a candidate segmentation region of interest (ROIs) for each organ is generated. The second stage is a 3D U-Net refinement organ segmentation which produces a more robust and accurate contour from the previous coarse segmentation mask. This network is equipped with an attention mechanism on skip connections and a deep supervision concept that generates ROIs by eliminating irrelevant background information. This network will identify the probability of the presence of each organ. In the last stage, the extracted regions will be fed to the 3D ResU-Net to generate a fine segmentation. The performance of the proposed framework was evaluated through well-established quantitative metrics such as the dice similarity coefficient.
Result: Using the weighted fusion technique linked with Cascade-Net, our method provided the average dice score of 0.71. Moreover, this algorithm resulted in dice score of 0.74, and 0.68 for the primary gross tumor volume (GTVp) and metastatic nodes (GTVn), respectively.
Conclusion: We demonstrated that using the fusion technique followed by an appropriate automatic segmentation technique provides a good performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wu, Z.-H., Zhong, Y., Zhou, T., Xiao, H.-J.: miRNA biomarkers for predicting overall survival outcomes for head and neck squamous cell carcinoma. Genomics 113(1), 135–141 (2021)
Butowski, N.A.: Epidemiology and diagnosis of brain tumors. CONTINUUM: Lifelong Learn. Neurol. 21(2), 301–313 (2015)
Drevelegas, A., Papanikolaou, N.: Imaging modalities in brain tumors. In: Drevelegas, A. (ed.) Imaging of Brain Tumors with Histological Correlations, pp. 13–33. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-540-87650-2_2
Wang, J., Peng, Y., Guo, Y., Li, D., Sun, J. (2022). CCUT-Net: pixel-wise global context channel attention UT-Net for head and neck tumor segmentation. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds.) HECKTOR 2021. LNCS, vol. 13209, pp. 38–49. Springer, Cham. https://doi.org/10.1007/978-3-030-98253-9_2
Fatan, M., Hosseinzadeh, M., Askari, D., Sheikhi, H., Rezaeijo, S.M., Salmanpour, M.R.: Fusion-based head and neck tumor segmentation and survival prediction using robust deep learning techniques and advanced hybrid machine learning systems. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds.) HECKTOR 2021. LNCS, vol. 13209, pp. 211–23. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-98253-9_20
Rahmim, A., Zaidi, H.: PET versus SPECT: strengths, limitations and challenges. Nucl. Med. Commun. 29(3), 193–207 (2008)
Ren, J., Eriksen, J.G., Nijkamp, J., Korreman, S.S.: Comparing different CT, PET and MRI multi-modality image combinations for deep learning-based head and neck tumor segmentation. Acta Oncol. 60(11), 1399–1406 (2021)
Javanmardi A, Hosseinzadeh M, Hajianfar G, Nabizadeh AH, Rezaeijo SM, Rahmim A, et al. Multi-modality fusion coupled with deep learning for improved outcome prediction in head and neck cancer. In: Medical Imaging 2022: Image Processing, pp. 664–668. SPIE (2022)
Salmanpour, M.R., Hajianfar, G., Rezaeijo, S.M., Ghaemi, M., Rahmim, A.: Advanced automatic segmentation of tumors and survival prediction in head and neck cancer. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds.) HECKTOR 2021. LNCS, vol. 13209, pp. 202–10. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-98253-9_19
Salmanpour, M.R., Hosseinzadeh, M., Modiri, E., Akbari, A., Hajianfar, G., Askari, D., et al.: Advanced survival prediction in head and neck cancer using hybrid machine learning systems and radiomics features. In: Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging, pp. 314–321. SPIE (2022)
Taxak, N., Singhal, S.: A Review of image fusion methods. Int. J. Innovative Sci. Res. Tech. 8(3), 598–601 (2018)
Rezaeijo, S.M., Hashemi, B., Mofid, B., Bakhshandeh, M., Mahdavi, A., Hashemi, M.S.: The feasibility of a dose painting procedure to treat prostate cancer based on mpMR images and hierarchical clustering. Radiat. Oncol. 16(1), 1–16 (2021)
Andrearczyk, V., et al.: Overview of the HECKTOR challenge at MICCAI 2021: automatic head and neck tumor segmentation and outcome prediction in PET/CT images. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds.) HECKTOR 2021. LNCS, vol. 13209, pp. 1–37. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-98253-9_1
Wang, Q., Shen, Y., Jin, J.: Performance evaluation of image fusion techniques. Image Fusion: Algorithms Appl. 19, 469–492 (2008)
Salmanpour, M.R., Hajianfar, G., Lv, W., Lu, L., Rahmim, A.: Multitask Outcome Prediction using Hybrid Machine Learning and PET-CT Fusion Radiomics. Soc. Nucl. Med. 62(supplement 1), 1424 (2021)
Salmanpour, M.R., Hosseinzadeh, M., Akbari, A., Borazjani, K., Mojallal, K., Askari, D., et al.: Prediction of TNM stage in head and neck cancer using hybrid machine learning systems and radiomics features. In: Medical Imaging 2022: Computer-Aided Diagnosis, pp. 648–53. SPIE (2022)
Salmanpour, M.R., Hosseinzadeh, M., Rezaeijo, S.M., Uribe, C., Rahmim, A.: Robustness and reproducibility of radiomics features from fusions of PET-CT images. Soc. Nucl. Med. 63(supplement 2), 3179 (2022)
Andrearczyk, V., et al.: Overview of the HECKTOR challenge at MICCAI 2020: automatic head and neck tumor segmentation in PET/CT. In: Andrearczyk, V., Oreiller, V., Depeursinge, A. (eds.) HECKTOR 2020. LNCS, vol. 12603, pp. 1–21. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67194-5_1
Wang, G., Huang, Z., Shen, H., Hu, Z.: The head and neck tumor segmentation in PET/CT based on multi-channel attention network. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds.) HECKTOR 2021. LNCS, vol. 13209, pp. 68–74. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-98253-9_5
Xie, J., Peng, Y.: The head and neck tumor segmentation based on 3D U-Net. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds.) HECKTOR 2021. LNCS, vol. 13209, pp. 92–98. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-98253-9_8
Oreiller, V., Andrearczyk, V., Jreige, M., Boughdad, S., Elhalawani, H., Castelli, J., et al.: Head and neck tumor segmentation in PET/CT: the HECKTOR challenge. Med. Image Anal. 77, 102336 (2022)
Iantsen, A., Visvikis, D., Hatt, M.: Squeeze-and-excitation normalization for automated delineation of head and neck primary tumors in combined PET and CT images. In: Andrearczyk, V., Oreiller, V., Depeursinge, A. (eds.) HECKTOR 2020. LNCS, vol. 12603, pp. 37–43. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67194-5_4
Chen, H., Chen, H., Wang, L.: Iteratively refine the segmentation of head and neck tumor in FDG-PET and CT images. In: Andrearczyk, V., Oreiller, V., Depeursinge, A. (eds.) HECKTOR 2020. LNCS, vol. 12603, pp. 53–58 . Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67194-5_6
Acknowledgement
This study was supported by Technological Virtual Collaboration Corporation (TECVICO Corp.) located in Vancouver, BC, Canada.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Code Availability
All codes are publicly shared at: https://github.com/Tecvico.
Conflict of Interest
The authors have no relevant conflicts of interest to disclose.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rezaeijo, S.M., Harimi, A., Salmanpour, M.R. (2023). Fusion-Based Automated Segmentation in Head and Neck Cancer via Advance Deep Learning Techniques. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds) Head and Neck Tumor Segmentation and Outcome Prediction. HECKTOR 2022. Lecture Notes in Computer Science, vol 13626. Springer, Cham. https://doi.org/10.1007/978-3-031-27420-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-27420-6_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27419-0
Online ISBN: 978-3-031-27420-6
eBook Packages: Computer ScienceComputer Science (R0)
