Abstract
We implemented a 2D U-Net model with an ImageNet-pretrained ResNet50 encoder for performing segmentation of primary tumors (GTVp) and metastatic lymph nodes (GTVn) from PET/CT images provided by the HEad and neCK TumOR segmentation challenge (HECKTOR) 2022. We utilized a multiclass Dice Loss for model training which was minimized using the AMSGrad variant of the Adam algorithm optimizer. We trained our 2D models on the axial slices of the images in a 5-fold cross-validation setting and stacked the 2D predictions axially to obtain the predicted 3D segmentation masks. We obtained mean aggregate Dice similarity coefficients (mean DSC\(_{\text {agg}}\)) of 0.6865, 0.6689, 0.6768, 0.6792, and 0.6726 on the 5 validation sets respectively. The model with the best performance on the validation set (validation split 1) was chosen for evaluating segmentation masks on the test set for submission to the challenge. Our model achieved a mean DSC\(_{\text {agg}}\) = 0.6345 on the test set, with DSC\(_{\text {agg}}\)(GTVp) = 0.6955 and DSC\(_{\text {agg}}\)(GTVn) = 0.5734. The implementation can be found under our Github repository.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
ReduceLROnPlateau. https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html
Ahamed, S., et al.: A cascaded deep network for automated tumor detection and segmentation in clinical PET imaging of diffuse large B-cell lymphoma. In: Colliot, O., Išgum, I. (eds.) Medical Imaging 2022: Image Processing, vol. 12032, p. 120323M. International Society for Optics and Photonics, SPIE (2022). https://doi.org/10.1117/12.2612684
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 (2022). https://doi.org/10.48550/ARXIV.2201.04138, https://arxiv.org/abs/2201.04138
Antonelli, M., et al.: The medical segmentation Decathlon (2021). https://doi.org/10.48550/ARXIV.2106.05735, https://arxiv.org/abs/2106.05735
Ardila, D., Kiraly, A., Bharadwaj, S., et al.: End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat. Med. 25(4), 954–961 (2019). https://doi.org/10.1038/s41591-019-0447-x. Accessed 07 Sep 2022
Bi, L., Kim, J., Feng, D., Fulham, M.: Multi-stage thresholded region classification for whole-body PET-CT lymphoma studies. Med. Image Comput. Comput. Assist. Interv. 17(Pt 1), 569–576 (2014)
Blanc-Durand, P., Van Der Gucht, A., Schaefer, N., Itti, E., Prior, J.O.: 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 (2018)
Bogowicz, M., et al.: Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma. Acta Oncol. 56(11), 1531–1536 (2017)
Castelli, J., et al.: A PET-based nomogram for oropharyngeal cancers. Eur. J. Cancer 75, 222–230 (2017)
Cottereau, A.S., et al.: New approaches in characterization of lesions dissemination in DLBCL patients on baseline PET/CT. Cancers 13(16), 3998 (2021). https://doi.org/10.3390/cancers13163998, https://europepmc.org/articles/PMC8392801
DiGiulio, S.: Oropharyngeal cancer now most common head & neck cancer. Oncol. Times 36(22) (2014). https://journals.lww.com/oncology-times/Fulltext/2014/11250/Oropharyngeal_Cancer_Now_Most_Common_Head___Neck. 26.aspx
Driessen, J., et al.: Baseline metabolic tumor volume in 18FDG-PET-CT scans in classical Hodgkin lymphoma using semi-automatic segmentation. Blood 134, 4049 (2019). https://doi.org/10.1182/blood-2019-125495, https://www.sciencedirect.com/science/article/pii/S0006497118619779
Ger, R.B., et al.: Radiomics features of the primary tumor fail to improve prediction of overall survival in large cohorts of CT- and PET-imaged head and neck cancer patients. PLoS ONE 14(9), e0222509 (2019)
Guo, B., Tan, X., Ke, Q., Cen, H.: Prognostic value of baseline metabolic tumor volume and total lesion glycolysis in patients with lymphoma: a meta-analysis. PLoS ONE 14(1), e0210224 (2019)
Haenssle, H.A., et al.: Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann. Oncol. 29(8), 1836–1842 (2018)
Hatt, M., et al.: The first MICCAI challenge on PET tumor segmentation. Med. Image Anal. 44, 177–195 (2018)
Hatt, M., et al.: Classification and evaluation strategies of auto-segmentation approaches for PET: report of AAPM task group no. 211. Med. Phys. 44(6), e1–e42 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). https://doi.org/10.48550/ARXIV.1512.03385, https://arxiv.org/abs/1512.03385
Iakubovskii, P.: Segmentation models PyTorch (2019). https://github.com/qubvel/
Isensee, F., Jaeger, P., Kohl, S., et al.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203–211 (2021)
Johnson, D.E., Burtness, B., Leemans, C.R., Lui, V.W.Y., Bauman, J.E., Grandis, J.R.: Head and neck squamous cell carcinoma. Nat. Rev. Dis. Primers. 6(1), 92 (2020)
Kim, H.E., Cosa-Linan, A., Santhanam, N., Jannesari, M., Maros, M.E., Ganslandt, T.: Transfer learning for medical image classification: a literature review. BMC Med. Imaging 22(1), 69 (2022). https://doi.org/10.1186/s12880-022-00793-7
Legot, F., et al.: 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), 21811–21819 (2018)
McKinney, S.M., et al.: International evaluation of an AI system for breast cancer screening. Nature 577(7788), 89–94 (2020)
Nickel, P.J.: Trust in medical artificial intelligence: a discretionary account. Ethics Inf. Technol. 24(1), 1–10 (2022). https://doi.org/10.1007/s10676-022-09630-5
Oreiller, V., et al.: Head and neck tumor segmentation in PET/CT: the HECKTOR challenge. Med. Image Anal. 77, 102336 (2022). https://doi.org/10.1016/j.media.2021.102336, https://www.sciencedirect.com/science/article/pii/S1361841521003819
Orlhac, F., Nioche, C., Klyuzhin, I., Rahmim, A., Buvat, I.: Radiomics in PET imaging: a practical guide for newcomers. PET Clin. 16(4), 597–612 (2021)
Reddi, S.J., Kale, S., Kumar, S.: On the convergence of Adam and beyond. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=ryQu7f-RZ
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation (2015). https://doi.org/10.48550/ARXIV.1505.04597, https://arxiv.org/abs/1505.04597
Slattery, A.: Validating an image segmentation program devised for staging lymphoma. Australas. Phys. Eng. Sci. Med. 40(4), 799–809 (2017)
Vallières, M., et al.: Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci. Rep. 7(1), 10117 (2017)
Vercellino, L., et al.: High total metabolic tumor volume at baseline predicts survival independent of response to therapy. Blood 135(16), 1396–1405 (2020)
Wu, N., et al.: Deep neural networks improve radiologists’ performance in breast cancer screening. IEEE Trans. Med. Imaging 39(4), 1184–1194 (2020). https://doi.org/10.1109/TMI.2019.2945514
Yaniv, Z., Lowekamp, B.C., Johnson, H.J., Beare, R.: SimpleITK image-analysis notebooks: a collaborative environment for education and reproducible Research. J. Digit. Imaging 31(3), 290–303 (2017). https://doi.org/10.1007/s10278-017-0037-8
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? (2014)
Zhou, T., Ruan, S., Canu, S.: A review: deep learning for medical image segmentation using multi-modality fusion. Array 3–4, 100004 (2019). https://doi.org/10.1016/j.array.2019.100004
Acknowledgement
The authors would like to thank Isaac Shiri for insightful technical discussions throughout the course of working on this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ahamed, S., Polson, L., Rahmim, A. (2023). A U-Net Convolutional Neural Network with Multiclass Dice Loss for Automated Segmentation of Tumors and Lymph Nodes from Head and Neck Cancer PET/CT Images. 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_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-27420-6_10
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)