Quality Assessment of Commercial Contouring Software based on Convolutional Neural Networks: Implications for Clinical Practice

RICARDO GOMES DOS REIS; Otacílio P. L. Frota; Wenzel C. de Abreu; Giullianne Rivelli R. Zaratim; Thyago F. Mangueira; Luis Felipe Oliveira e Silva

doi:10.29384/rbfm.2025.v19.19849001797

Autores

RICARDO GOMES DOS REIS HOSPITAL UNIVERSITÁRIO DE BRASÍLIA https://orcid.org/0000-0003-4266-7690
Otacílio P. L. Frota
Wenzel C. de Abreu
Giullianne Rivelli R. Zaratim https://orcid.org/0009-0007-4217-0437
Thyago F. Mangueira https://orcid.org/0000-0002-7587-527X
Luis Felipe Oliveira e Silva https://orcid.org/0009-0002-6453-9403

DOI:

https://doi.org/10.29384/rbfm.2025.v19.19849001797

Palavras-chave:

Convolutional Neural Networks, Automatic delineation, Treatment Planning, Radiation Therapy, Uterine Cervix Cancer

Resumo

The treatment planning for radiotherapy, particularly the delineation of pelvic structures, is a complex and time-consuming task, demanding considerable expertise from physicians. The development of automation tools for these procedures could potentially reduce the workload and improve treatment planning efficiency. The goal of this study is to evaluate the efficacy of the AutoContour software, a commercial auto-segmentation tool utilizing convolutional neural networks, in delineating organs at risk during cervical cancer radiotherapy. We evaluated the performance of the AutoContour software on fifteen pelvic CT scans from cervical cancer patients previously treated at our institution. This study compared the automatically generated structures with those manually delineated by two experienced radiation oncologists. The comparison employed the Dice Similarity Coefficient (DSC) to assess the quality of structures, and we also measured the time savings achieved by using the auto-segmentation tool. The study found that most of the structures delineated by the AutoContour software closely matched those contoured by the radiation oncologists, with DSC values greater than 0.80, indicating high similarity. However, the bowel bag showed lower similarity, which could be attributed to interobserver variability among the physicians themselves. The use of AutoContour resulted in a reduction of up to 25.86 minutes in the time required per patient for structure delineation, demonstrating substantial efficiency gains without compromising the quality of the contours. The AutoContour software streamlines the delineation process in cervical cancer radiotherapy planning, maintaining high-quality output with minimal need for adjustments. These results suggest that the integration of this auto-segmentation tool could considerably decrease the specialized workload, enhancing the overall efficiency of clinical workflows in radiation oncology departments. This automation not only saves time but also reduces the potential for human error, promising more consistent and reliable treatment planning.

Downloads

Não há dados estatísticos.

Referências

Instituto Nacional de Câncer. Estimativa 2023: incidência de câncer no Brasil. 2022.

Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J

Clin. 2021 May;71(3):209–49.

World Health Organization. Global strategy to accelerate the elimination of cervical cancer as a public health problem. 2020.

Lukka H, Hirte H, Fyles A, Thomas G, Elit L, Johnston M, et al. Concurrent cisplatin-based chemotherapy plus radiotherapy for cervical cancer - A meta-analysis. Clin Oncol. 2002;14(3):203–12.

Vale C, Tierney JF, Stewart LA, Brady M, Dinshaw K, Jakobsen A, et al. Reducing uncertainties about the

effects of chemoradiotherapy for cervical cancer: A systematic review and meta-analysis of individual patient data from 18 randomized trials. Journal of Clinical Oncology. 2008 Dec 10;26(35):5802–12.

Montague E, Roques T, Spencer K, Burnett A, Lourenco J, Thorp N. How long does contouring really take? Results of the Royal College of Radiologists contouring surveys. Clin Oncol. 2024 Mar;

Bilimagga R, Anchineyan P, Nmugam M, Thalluri S, Goud P. Autodelineation of organ at risk in head and neck cancer radiotherapy using artificial intelligence. J Cancer Res Ther. 2022 Dec 1;18(9):S141–5.

Ibragimov B, Xing L. Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks: Med Phys. 2017 Feb 1;44(2):547–57.

Lin TC, Lin CY, Li KC, Ji JH, Liang JA, Shiau AC, et al. Automated Hypofractionated IMRT treatment planning for early-stage breast Cancer. Radiation Oncology. 2020 Mar 17;15(1).

Liu P, Sun Y, Zhao X, Yan Y. Deep learning algorithm performance in contouring head and neck organs at risk: a systematic review and single-arm meta-analysis. Vol. 22, BioMedical Engineering Online. BioMed Central Ltd; 2023.

Tong N, Gou S, Yang S, Ruan D, Sheng K. Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks. Med Phys. 2018 Oct 1;45(10):4558–67.

Xhaferllari I, Wong E, Bzdusek K, Lock M, Chen JZ. Automated IMRT planning with regional optimization using planning scripts. J Appl Clin Med Phys. 2013;14:176–91.

Samuel Avelino, Sandro José Martins, Rejane Leite de Souza Soares, Aline Leal Gonçalves Creder Lopes,

Jaqueline Silva Misael. CENSO RADIOTERAPIA. 2018.

Arthur Accioly Rosa, Homero Lavieri Martins, Leonardo Pimentel, Marcus Simões Castilho, Silvério Marinho, Virginia Izabel Oliveira. Projeto RT2030: Planejamento de Desenvolvimento da Radioterapia para a Próxima Década. Sociedade Brasileira de Radioterapia. 2021.

Lawton CAF, Michalski J, El-Naqa I, Buyyounouski MK, Lee WR, Menard C, et al. RTOG GU Radiation Oncology Specialists Reach Consensus on Pelvic Lymph Node Volumes for High-Risk Prostate Cancer. Int J Radiat Oncol Biol Phys. 2009 Jun 1;74(2):383–7.

Student. The probable error of a mean. Biometrika. 1908;6:1.

Mann HB, Donald R. Whitney. On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other. The annals of mathematical statistics. 1947;50–60.

Shapiro SS, Wilk AMB. An analysis of variance test for normality (complete samples). Biometrika [Internet]. 1965;52:591–611. Available from: http://biomet.oxfordjournals.org/

Brouwer CL, JHM Steenbakkers R, van den Heuvel E, Duppen JC, Navran A, Bijl HP, et al. 3D Variation in

delineation of head and neck organs at risk. Radiation Oncology [Internet]. 2012;7:32. Available from:

http://www.ro-journal.com/content/7/1/32

El I, Li NR, Murphy MJ. Machine Learning in Radiation Oncology: Theory and Applications. Springer; 2015.

Jarrett D, Stride E, Vallis K, Gooding MJ. Applications and limitations of machine learning in radiation oncology. Br J Radiol. 2019;92.

Doolan PJ, Charalambous S, Roussakis Y, Leczynski A, Peratikou M, Benjamin M, et al. A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy. Front Oncol. 2023;13.

Kim H, Jung J, Kim J, Cho B, Kwak J, Jang JY, et al. Abdominal multi-organ auto-segmentation using 3Dpatch-based deep convolutional neural network. Sci Rep. 2020 Dec 1;10(1).

Fechter T, Adebahr S, Baltas D, Ben Ayed I, Desrosiers C, Dolz J. Esophagus segmentation in CT via 3D fully convolutional neural network and random walk: Med Phys. 2017 Dec 1;44(12):6341–52.

Guo Y, Gao Y, Shen D. Deformable MR Prostate Segmentation via Deep Feature Learning and Sparse

Patch Matching. IEEE Trans Med Imaging. 2016 Apr 1;35(4):1077–89.

Landman BA, Bobo MF, Huo Y, Yao Y, Bao S, Virostko J, et al. Fully convolutional neural networks improve abdominal organ segmentation. In SPIE-Intl Soc Optical Eng; 2018. p. 100.

Lustberg T, van Soest J, Gooding M, Peressutti D, Aljabar P, van der Stoep J, et al. Clinical evaluation of atlas and deep learning based automatic contouring for lung cancer. Radiotherapy and Oncology. 2018 Feb 1;126(2):312–7.

Adams J, Luca K, Yang X, Patel P, Jani A, Roper J, et al. Plan Quality Analysis of Automated Treatment Planning Workflow With Commercial Auto-Segmentation Tools and Clinical Knowledge-Based Planning Models for Prostate Cancer. Cureus. 2023 Jul 1;15(7).

Baroudi H, Brock KK, Cao W, Chen X, Chung C, Court LE, et al. Automated Contouring and Planning in Radiation Therapy: What Is ‘Clinically Acceptable’? Vol. 13, Diagnostics. Multidisciplinary Digital Publishing Institute (MDPI); 2023.