Swin Transformer-based Automatic Delineation of the Hippocampus by MRI in Hippocampus-sparing Whole-brain Radiotherapy

Overview

Journal Front Neurosci

Date 2024 Oct 28

PMID 39464425

Authors

Liang Li

Zhennan Lu

Aijun Jiang

Guanchen Sha

Zhaoyang Luo

Xin Xie

Xin Ding

Affiliations

Soon will be listed here.

Abstract

Objective: This study aims to develop and validate SwinHS, a deep learning-based automatic segmentation model designed for precise hippocampus delineation in patients receiving hippocampus-protected whole-brain radiotherapy. By streamlining this process, we seek to significantly improve workflow efficiency for clinicians.

Methods: A total of 100 three-dimensional T1-weighted MR images were collected, with 70 patients allocated for training and 30 for testing. Manual delineation of the hippocampus was performed according to RTOG0933 guidelines. The SwinHS model, which incorporates a 3D ELSA Transformer module and an sSE CNN decoder, was trained and tested on these datasets. To prove the effectiveness of SwinHS, this study compared the segmentation performance of SwinHS with that of V-Net, U-Net, ResNet and VIT. Evaluation metrics included the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), and Hausdorff distance (HD). Dosimetric evaluation compared radiotherapy plans generated using automatic segmentation (plan AD) versus manual hippocampus segmentation (plan MD).

Results: SwinHS outperformed four advanced deep learning-based models, achieving an average DSC of 0.894, a JSC of 0.817, and an HD of 3.430 mm. Dosimetric evaluation revealed that both plan (AD) and plan (MD) met treatment plan constraints for the target volume (PTV). However, the hippocampal D in plan (AD) was significantly greater than that in plan (MD), approaching the 17 Gy constraint limit. Nonetheless, there were no significant differences in D or maximum doses to other critical structures between the two plans.

Conclusion: Compared with manual delineation, SwinHS demonstrated superior segmentation performance and a significantly shorter delineation time. While plan (AD) met clinical requirements, caution should be exercised regarding hippocampal D. SwinHS offers a promising tool to enhance workflow efficiency and facilitate hippocampal protection in radiotherapy planning for patients with brain metastases.

References

Ji T, Sun L, Cai F, Li G . Comparison between flattening filter-free (FFF) and flattened photon beam VMAT plans for the whole brain radiotherapy (WBRT) with hippocampus sparing. Asia Pac J Clin Oncol. 2021; 18(5):e263-e267. PMC: 9540553. DOI: 10.1111/ajco.13624. View

Peters S, Bexelius C, Munk V, Leighl N . The impact of brain metastasis on quality of life, resource utilization and survival in patients with non-small-cell lung cancer. Cancer Treat Rev. 2016; 45:139-62. DOI: 10.1016/j.ctrv.2016.03.009. View

Wang J, Chen Z, Yang C, Qu B, Ma L, Fan W . Evaluation Exploration of Atlas-Based and Deep Learning-Based Automatic Contouring for Nasopharyngeal Carcinoma. Front Oncol. 2022; 12:833816. PMC: 9008357. DOI: 10.3389/fonc.2022.833816. View

Soydemir G, Bilici N, Tiken E, Yentek Balkanay A, Sisman A, Karacetin D . Hippocampal sparing for brain tumor radiotherapy: A retrospective study comparing intensity-modulated radiotherapy and volumetric-modulated arc therapy. J Cancer Res Ther. 2021; 17(1):99-105. DOI: 10.4103/jcrt.JCRT_32_19. View

Erickson B . Basic Artificial Intelligence Techniques: Machine Learning and Deep Learning. Radiol Clin North Am. 2021; 59(6):933-940. DOI: 10.1016/j.rcl.2021.06.004. View

Gondi V, Cui Y, Mehta M, Manfredi D, Xiao Y, Galvin J . Real-time pretreatment review limits unacceptable deviations on a cooperative group radiation therapy technique trial: quality assurance results of RTOG 0933. Int J Radiat Oncol Biol Phys. 2015; 91(3):564-70. PMC: 4508857. DOI: 10.1016/j.ijrobp.2014.10.054. View

Eelbode T, Bertels J, Berman M, Vandermeulen D, Maes F, Bisschops R . Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index. IEEE Trans Med Imaging. 2020; 39(11):3679-3690. DOI: 10.1109/TMI.2020.3002417. View

Taha A, Hanbury A . Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging. 2015; 15:29. PMC: 4533825. DOI: 10.1186/s12880-015-0068-x. View

Brown P, Gondi V, Pugh S, Tome W, Wefel J, Armstrong T . Hippocampal Avoidance During Whole-Brain Radiotherapy Plus Memantine for Patients With Brain Metastases: Phase III Trial NRG Oncology CC001. J Clin Oncol. 2020; 38(10):1019-1029. PMC: 7106984. DOI: 10.1200/JCO.19.02767. View

10.

Jiang Y, Zhang Y, Lin X, Dong J, Cheng T, Liang J . SwinBTS: A Method for 3D Multimodal Brain Tumor Segmentation Using Swin Transformer. Brain Sci. 2022; 12(6). PMC: 9221215. DOI: 10.3390/brainsci12060797. View

11.

Fike J, Rosi S, Limoli C . Neural precursor cells and central nervous system radiation sensitivity. Semin Radiat Oncol. 2009; 19(2):122-32. PMC: 2683587. DOI: 10.1016/j.semradonc.2008.12.003. View

12.

Fischl B, Salat D, Busa E, Albert M, Dieterich M, Haselgrove C . Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron. 2002; 33(3):341-55. DOI: 10.1016/s0896-6273(02)00569-x. View

13.

Walker G, Awan M, Tao R, Koay E, Boehling N, Grant J . Prospective randomized double-blind study of atlas-based organ-at-risk autosegmentation-assisted radiation planning in head and neck cancer. Radiother Oncol. 2014; 112(3):321-5. PMC: 4252740. DOI: 10.1016/j.radonc.2014.08.028. View

14.

Li Q, Shen L . Neuron segmentation using 3D wavelet integrated encoder-decoder network. Bioinformatics. 2021; 38(3):809-817. PMC: 8756182. DOI: 10.1093/bioinformatics/btab716. View

15.

Jiang A, Sun W, Zhao F, Wu Z, Shang D, Yu Q . Dosimetric evaluation of four whole brain radiation therapy approaches with hippocampus and inner ear avoidance and simultaneous integrated boost for limited brain metastases. Radiat Oncol. 2019; 14(1):46. PMC: 6419811. DOI: 10.1186/s13014-019-1255-7. View

16.

Berghoff A, Preusser M . New developments in brain metastases. Ther Adv Neurol Disord. 2018; 11:1756286418785502. PMC: 6048670. DOI: 10.1177/1756286418785502. View

17.

Porter E, Fuentes P, Siddiqui Z, Thompson A, Levitin R, Solis D . Hippocampus segmentation on noncontrast CT using deep learning. Med Phys. 2020; 47(7):2950-2961. DOI: 10.1002/mp.14098. View

18.

Chen J, Frey E, He Y, Segars W, Li Y, Du Y . TransMorph: Transformer for unsupervised medical image registration. Med Image Anal. 2022; 82:102615. PMC: 9999483. DOI: 10.1016/j.media.2022.102615. View

19.

Gondi V, Pugh S, Tome W, Caine C, Corn B, Kanner A . Preservation of memory with conformal avoidance of the hippocampal neural stem-cell compartment during whole-brain radiotherapy for brain metastases (RTOG 0933): a phase II multi-institutional trial. J Clin Oncol. 2014; 32(34):3810-6. PMC: 4239303. DOI: 10.1200/JCO.2014.57.2909. View

20.

Qiu Q, Yang Z, Wu S, Qian D, Wei J, Gong G . Automatic segmentation of hippocampus in hippocampal sparing whole brain radiotherapy: A multitask edge-aware learning. Med Phys. 2021; 48(4):1771-1780. DOI: 10.1002/mp.14760. View