Deep Learning Algorithm Performance in Contouring Head and Neck Organs at Risk: a Systematic Review and Single-arm Meta-analysis

Overview

Journal Biomed Eng Online

Publisher Biomed Central

Specialty Biomedical Engineering

Date 2023 Nov 2

PMID 37915046

Authors

Peiru Liu

Ying Sun

Xinzhuo Zhao

Ying Yan

Affiliations

Soon will be listed here.

Abstract

Purpose: The contouring of organs at risk (OARs) in head and neck cancer radiation treatment planning is a crucial, yet repetitive and time-consuming process. Recent studies have applied deep learning (DL) algorithms to automatically contour head and neck OARs. This study aims to conduct a systematic review and meta-analysis to summarize and analyze the performance of DL algorithms in contouring head and neck OARs. The objective is to assess the advantages and limitations of DL algorithms in contour planning of head and neck OARs.

Methods: This study conducted a literature search of Pubmed, Embase and Cochrane Library databases, to include studies related to DL contouring head and neck OARs, and the dice similarity coefficient (DSC) of four categories of OARs from the results of each study are selected as effect sizes for meta-analysis. Furthermore, this study conducted a subgroup analysis of OARs characterized by image modality and image type.

Results: 149 articles were retrieved, and 22 studies were included in the meta-analysis after excluding duplicate literature, primary screening, and re-screening. The combined effect sizes of DSC for brainstem, spinal cord, mandible, left eye, right eye, left optic nerve, right optic nerve, optic chiasm, left parotid, right parotid, left submandibular, and right submandibular are 0.87, 0.83, 0.92, 0.90, 0.90, 0.71, 0.74, 0.62, 0.85, 0.85, 0.82, and 0.82, respectively. For subgroup analysis, the combined effect sizes for segmentation of the brainstem, mandible, left optic nerve, and left parotid gland using CT and MRI images are 0.86/0.92, 0.92/0.90, 0.71/0.73, and 0.84/0.87, respectively. Pooled effect sizes using 2D and 3D images of the brainstem, mandible, left optic nerve, and left parotid gland for contouring are 0.88/0.87, 0.92/0.92, 0.75/0.71 and 0.87/0.85.

Conclusions: The use of automated contouring technology based on DL algorithms is an essential tool for contouring head and neck OARs, achieving high accuracy, reducing the workload of clinical radiation oncologists, and providing individualized, standardized, and refined treatment plans for implementing "precision radiotherapy". Improving DL performance requires the construction of high-quality data sets and enhancing algorithm optimization and innovation.

Citing Articles

A systematic review of the role of artificial intelligence in automating computed tomography-based adaptive radiotherapy for head and neck cancer.

Mastella E, Calderoni F, Manco L, Ferioli M, Medoro S, Turra A Phys Imaging Radiat Oncol. 2025; 33:100731.

PMID: 40026912 PMC: 11871500. DOI: 10.1016/j.phro.2025.100731.

MR-linac: role of artificial intelligence and automation.

Psoroulas S, Paunoiu A, Corradini S, Horner-Rieber J, Tanadini-Lang S Strahlenther Onkol. 2025; 201(3):298-305.

PMID: 39843783 PMC: 11839841. DOI: 10.1007/s00066-024-02358-9.

A Method for Sensitivity Analysis of Automatic Contouring Algorithms Across Different MRI Contrast Weightings Using SyntheticMR.

McCullum L, Belal Z, Floyd W, Ali A, West N, Mulder S medRxiv. 2025; .

PMID: 39830240 PMC: 11741493. DOI: 10.1101/2025.01.10.25319895.

Head and neck automatic multi-organ segmentation on Dual-Energy Computed Tomography.

Le A, Sambourg K, Sun R, Deny N, Cifliku V, Rouhi R Phys Imaging Radiat Oncol. 2025; 32():100654.

PMID: 39803347 PMC: 11718415. DOI: 10.1016/j.phro.2024.100654.

Impact of annotation imperfections and auto-curation for deep learning-based organ-at-risk segmentation.

Strijbis V, Gurney-Champion O, Slotman B, Verbakel W Phys Imaging Radiat Oncol. 2024; 32:100684.

PMID: 39720784 PMC: 11667007. DOI: 10.1016/j.phro.2024.100684.

References

Chen X, Sun S, Bai N, Han K, Liu Q, Yao S . A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy. Radiother Oncol. 2021; 160:175-184. DOI: 10.1016/j.radonc.2021.04.019. View

Oktay O, Nanavati J, Schwaighofer A, Carter D, Bristow M, Tanno R . Evaluation of Deep Learning to Augment Image-Guided Radiotherapy for Head and Neck and Prostate Cancers. JAMA Netw Open. 2020; 3(11):e2027426. PMC: 7705593. DOI: 10.1001/jamanetworkopen.2020.27426. View

Ye X, Guo D, Ge J, Yan S, Xin Y, Song Y . Comprehensive and clinically accurate head and neck cancer organs-at-risk delineation on a multi-institutional study. Nat Commun. 2022; 13(1):6137. PMC: 9576793. DOI: 10.1038/s41467-022-33178-z. View

Geets X, Daisne J, Arcangeli S, Coche E, De Poel M, Duprez T . Inter-observer variability in the delineation of pharyngo-laryngeal tumor, parotid glands and cervical spinal cord: comparison between CT-scan and MRI. Radiother Oncol. 2005; 77(1):25-31. DOI: 10.1016/j.radonc.2005.04.010. View

Kieselmann J, Fuller C, Gurney-Champion O, Oelfke U . Cross-modality deep learning: Contouring of MRI data from annotated CT data only. Med Phys. 2020; 48(4):1673-1684. PMC: 8058228. DOI: 10.1002/mp.14619. View

Tong N, Gou S, Yang S, Cao M, Sheng K . Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low-field MR images. Med Phys. 2019; 46(6):2669-2682. PMC: 6581189. DOI: 10.1002/mp.13553. View

Applebaum K, Furniss C, Zeka A, Posner M, Smith J, Bryan J . Lack of association of alcohol and tobacco with HPV16-associated head and neck cancer. J Natl Cancer Inst. 2007; 99(23):1801-10. DOI: 10.1093/jnci/djm233. View

Tappeiner E, Proll S, Honig M, Raudaschl P, Zaffino P, Spadea M . Multi-organ segmentation of the head and neck area: an efficient hierarchical neural networks approach. Int J Comput Assist Radiol Surg. 2019; 14(5):745-754. DOI: 10.1007/s11548-019-01922-4. View

Frizzell T, Glashutter M, Liu C, Zeng A, Pan D, Ghosh Hajra S . Artificial intelligence in brain MRI analysis of Alzheimer's disease over the past 12 years: A systematic review. Ageing Res Rev. 2022; 77:101614. DOI: 10.1016/j.arr.2022.101614. View

10.

Liang S, Thung K, Nie D, Zhang Y, Shen D . Multi-View Spatial Aggregation Framework for Joint Localization and Segmentation of Organs at Risk in Head and Neck CT Images. IEEE Trans Med Imaging. 2020; 39(9):2794-2805. DOI: 10.1109/TMI.2020.2975853. View

11.

Vorwerk H, Zink K, Schiller R, Budach V, Bohmer D, Kampfer S . Protection of quality and innovation in radiation oncology: the prospective multicenter trial the German Society of Radiation Oncology (DEGRO-QUIRO study). Evaluation of time, attendance of medical staff, and resources during radiotherapy with IMRT. Strahlenther Onkol. 2014; 190(5):433-43. DOI: 10.1007/s00066-014-0634-0. View

12.

Gu L, Cai X . Fusing 2D and 3D convolutional neural networks for the segmentation of aorta and coronary arteries from CT images. Artif Intell Med. 2021; 121:102189. DOI: 10.1016/j.artmed.2021.102189. View

13.

Chan J, Kearney V, Haaf S, Wu S, Bogdanov M, Reddick M . A convolutional neural network algorithm for automatic segmentation of head and neck organs at risk using deep lifelong learning. Med Phys. 2019; 46(5):2204-2213. DOI: 10.1002/mp.13495. View

14.

Gujral D, Nutting C . Patterns of failure, treatment outcomes and late toxicities of head and neck cancer in the current era of IMRT. Oral Oncol. 2018; 86:225-233. DOI: 10.1016/j.oraloncology.2018.09.011. View

15.

Liberati A, Altman D, Tetzlaff J, Mulrow C, Gotzsche P, Ioannidis J . The PRISMA statement for reporting systematic reviews and meta-analyses of studies that evaluate healthcare interventions: explanation and elaboration. BMJ. 2009; 339:b2700. PMC: 2714672. DOI: 10.1136/bmj.b2700. View

16.

Wolff R, Moons K, Riley R, Whiting P, Westwood M, Collins G . PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies. Ann Intern Med. 2019; 170(1):51-58. DOI: 10.7326/M18-1376. View

17.

Yee E, Ma D, Popuri K, Chen S, Lee H, Chow V . 3D hemisphere-based convolutional neural network for whole-brain MRI segmentation. Comput Med Imaging Graph. 2021; 95:102000. PMC: 10116838. DOI: 10.1016/j.compmedimag.2021.102000. View

18.

Amjad A, Xu J, Thill D, Lawton C, Hall W, Awan M . General and custom deep learning autosegmentation models for organs in head and neck, abdomen, and male pelvis. Med Phys. 2022; 49(3):1686-1700. PMC: 8917093. DOI: 10.1002/mp.15507. View

19.

Dai X, Lei Y, Wang T, Zhou J, Rudra S, McDonald M . Multi-organ auto-delineation in head-and-neck MRI for radiation therapy using regional convolutional neural network. Phys Med Biol. 2021; 67(2). PMC: 8811683. DOI: 10.1088/1361-6560/ac3b34. View

20.

Collins G, Reitsma J, Altman D, Moons K . Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. 2015; 350:g7594. DOI: 10.1136/bmj.g7594. View