Interobserver and sequence variability in the delineation of pelvic organs at risk on magnetic resonance images

Zheng, Wanjia; Yang, Xin; Cheng, Zesen; Lian, Jinxing; Li, Enting; Mo, Shaoling; Liu, Yimei; Huang, Sijuan

doi:10.2478/raon-2025-0006

Abstract

Background

This study evaluates the contouring variability among observers using MR images reconstructed by different sequences and quantifies the differences of automatic segmentation models for different sequences.

Patients and methods

Eighty-three patients with pelvic tumors underwent T1-weighted image (T1WI), contrast enhanced Dixon T1-weighted (T1dixonc), and T2-weighted image (T2WI) MR imaging on a simulator. Two observers performed manual delineation of the bladder, anal canal, rectum, and femoral heads on all images. Contour differences were used to analyze the interobserver and intersequence variability. A single-sequence automatic segmentation network was established using the U-Net network, and the segmentation results were analyzed.

Results

Variability analysis among observers showed that the bladder, rectum, and left femoral head on T1WI yielded the highest dice similarity coefficient (DSC) and the lowest 95% Hausdorff distance (HD) (all three sequences). Regarding sequence variability analysis for the same observer, the difference between T1WI and T2WI was the smallest. The DSC of the bladder, rectum, and femoral heads exceeded 0.88 for T1WI–T2WI. The differences between automatic segmentations and manual delineations were minimal on T2WI. The averaged DSC of automatic and manual segmentation of all organs on T2WI exceeded 0.81, and the averaged 95% HD value was lower than 7 mm. Similarly, the sequence variability analysis of automatic segmentation indicates that the automatic segmentation differences between T2WI and T1WI are minimal.

Conclusions

T1WI and T2WI yielded better results in manual delineation and automatic segmentation, respectively. The analysis of variability among three sequences indicates that the yielded good similarity outcomes between the T1WI and T2WI cases in manual and automatic segmentation. We infer that the T1WI and T2WI (or their combination) can be used for MR-only radiation therapy.

References

Hardcastle N, Tomé WA, Cannon DM, Brouwer CL, Wittendorp PW, Dogan N, et al. A multi-institution evaluation of deformable image registration algorithms for automatic organ delineation in adaptive head and neck radiotherapy. Radiat Oncol 2012; 7: 90. doi: 10.1186/1748-717X-7-90
Open DOI Search in Google Scholar Back to article
Burridge N, Amer A, Marchant T, Sykes J, Stratford J, Henry A, et al. Online adaptive radiotherapy of the bladder: small bowel irradiated-volume reduction. Int J Radiat Oncol Biol Phys 2006; 66: 892-7. doi: 10.1016/j.ijrobp.2006.07.013
Open DOI Search in Google Scholar Back to article
Noel CE, Parikh PJ, Spencer CR, Green OL, Hu Y, Mutic S, et al. Comparison of onboard low-field magnetic resonance imaging versus onboard computed tomography for anatomy visualization in radiotherapy. Acta Oncol 2015; 54: 1474-82. doi: 10.3109/0284186X.2015.1062541
Open DOI Search in Google Scholar Back to article
Lütgendorf-Caucig C, Fotina I, Stock M, Pötter R, Goldner G, Georg D. Feasibility of CBCT-based target and normal structure delineation in prostate cancer radiotherapy: multi-observer and image multi-modality study. Radiother Oncol 2011; 98: 154-61. doi: 10.1016/j.radonc.2010.11.016
Open DOI Search in Google Scholar Back to article
Hunt A, Hansen VN, Oelfke U, Nill S, Hafeez S. Adaptive radiotherapy enabled by MRI guidance. Clin Oncol (R Coll Radiol) 2018; 30: 711-9. doi: 10.1016/j.clon.2018.08.001
Open DOI Search in Google Scholar Back to article
Ahmed M, Schmidt M, Sohaib A, Kong C, Burke K, Richardson C, et al. The value of magnetic resonance imaging in target volume delineation of base of tongue tumours – a study using flexible surface coils. Radiother Oncol 2010; 94: 161-7. doi: 10.1016/j.radonc.2009.12.021
Open DOI Search in Google Scholar Back to article
Sander L, Langkilde NC, Holmberg M, Carl J. MRI target delineation may reduce long-term toxicity after prostate radiotherapy. Acta Oncol 2014; 53: 809-14. doi: 10.3109/0284186X.2013.865077
Open DOI Search in Google Scholar Back to article
Tanaka H, Hayashi S, Ohtakara K, Hoshi H, Iida T. Usefulness of CT-MRI fusion in radiotherapy planning for localized prostate cancer. J Radiat Res 2011; 52: 782-8. doi: 10.1269/jrr.11053
Open DOI Search in Google Scholar Back to article
Hijab A, Tocco B, Hanson I, Meijer H, Nyborg CJ, Bertelsen AS, et al. MR-guided adaptive radiotherapy for bladder cancer. Front Oncol 2021; 11: 637591. doi: 10.3389/fonc.2021.637591
Open DOI Search in Google Scholar Back to article
Pathmanathan AU, van As NJ, Kerkmeijer LGW, Christodouleas J, Lawton CAF, Vesprini D, et al. Magnetic resonance imaging-guided adaptive radiation therapy: a “Game Changer” for prostate treatment? Int J Radiat Oncol Biol Phys 2018; 100: 361-73. doi: 10.1016/j.ijrobp.2017.10.020
Open DOI Search in Google Scholar Back to article
Vestergaard A, Hafeez S, Muren LP, Nill S, Høyer M, Hansen VN, et al. The potential of MRI-guided online adaptive re-optimisation in radiotherapy of urinary bladder cancer. Radiother Oncol 2016; 118: 154-9. doi: 10.1016/j.radonc.2015.11.003
Open DOI Search in Google Scholar Back to article
Kerkmeijer LGW, Maspero M, Meijer GJ, van der Voort van Zyp JRN, de Boer HCJ, van den Berg CAT. Magnetic resonance imaging only workflow for radiotherapy simulation and planning in prostate cancer. Clin Oncol (R Coll Radiol) 2018; 30: 692-701. doi: 10.1016/j.clon.2018.08.009
Open DOI Search in Google Scholar Back to article
Paulson ES, Crijns SP, Keller BM, Wang J, Schmidt MA, Coutts G, et al. Consensus opinion on MRI simulation for external beam radiation treatment planning. Radiother Oncol 2016; 121: 187-92. doi: 10.1016/j.radonc.2016.09.018
Open DOI Search in Google Scholar Back to article
Gay HA, Barthold HJ, O’Meara E, Bosch WR, El Naqa I, Al-Lozi R, et al. Pelvic normal tissue contouring guidelines for radiation therapy: a Radiation Therapy Oncology Group consensus panel atlas. Int J Radiat Oncol Biol Phys 2012; 83: e353-e62. doi: 10.1016/j.ijrobp.2012.01.023
Open DOI Search in Google Scholar Back to article
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, editors. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. 18^th International Conference, Munich, Germany; October 5-9, 2015. Proceedings. Lecture Notes in Computer Science, vol 9351. Springer, Cham. doi: 10.1007/978-3-319-24574-4_28
Open DOI Search in Google Scholar Back to article
Kieselmann JP, Kamerling CP, Burgos N, Menten MJ, Fuller CD, Nill S, et al. Geometric and dosimetric evaluations of atlas-based segmentation methods of MR images in the head and neck region. Phys Med Biol 2018; 63: 145007. doi: 10.1088/1361-6560/aacb65
Open DOI Search in Google Scholar Back to article
Noel CE, Zhu F, Lee AY, Yanle H, Parikh PJ. Segmentation precision of abdominal anatomy for MRI-based radiotherapy. Med Dosim 2014; 39: 212-7. doi: 10.1016/j.meddos.2014.02.003
Open DOI Search in Google Scholar Back to article
Pekar V, Allaire S, Qazi A, Kim JJ, Jaffray DA. Head and neck auto-segmentation challenge: segmentation of the parotid lands. In: Jang Z, Navab N, Pluim JPW, Viergever MA, editors. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2010. 13^th International Conference, Beijing, China; September 20-24, 2010. Proceedings. Lecture Notes in Computer Science, vol 6362. p. 273-80. Springer. doi: 10.1007/978-3-642-15745-5
Open DOI Search in Google Scholar Back to article
Romeo V, Cavaliere C, Imbriaco M, Verde F, Petretta M, Franzese M, et al. Tumor segmentation analysis at different post-contrast time points: A possible source of variability of quantitative DCE-MRI parameters in locally advanced breast cancer. Eur J Radiol 2020; 126: 108907. doi: 10.1016/j.ejrad.2020.108907
Open DOI Search in Google Scholar Back to article
O’Connor LM, Dowling JA, Choi JH, Martin J, Warren-Forward H, Richardson H, et al. Validation of an MRI-only planning workflow for definitive pelvic radiotherapy. Radiat Oncol 2022; 17: 55. doi: 10.1186/s13014-022-02023-4
Open DOI Search in Google Scholar Back to article
Tyagi P, Moon CH, Connell M, Ganguly A, Cho KJ, Tarin T, et al. Intravesical contrast-enhanced MRI: a potential tool for bladder cancer surveillance and staging. Curr Oncol 2023; 30: 4632-47. doi: 10.3390/curroncol30050350
Open DOI Search in Google Scholar Back to article
Zhu QK, Du B, Yan PK, Lu HB, Zhang LP. Shape prior constrained PSO model for bladder wall MRI segmentation. Neurocomputing 2017; 294: 19-28. doi: 10.1016/j.neucom.2017.12.011
Open DOI Search in Google Scholar Back to article
Paley MR, Ros PR. MRI of the rectum: non-neoplastic disease. Eur Radiol 1998; 8: 3-8. doi: 10.1007/s003300050328
Open DOI Search in Google Scholar Back to article
Hwee J, Louie AV, Gaede S, Bauman G, D’Souza D, Sexton T, et al. Technology assessment of automated atlas based segmentation in prostate bed contouring. Radiat Oncol 2011; 6: 110. doi: 10.1186/1748-717X-6-110
Open DOI Search in Google Scholar Back to article
Huang S, Cheng Z, Lai L, Zheng W, He M, Li J, et al. Integrating multiple MRI sequences for pelvic organs segmentation via the attention mechanism. Med Phys 2021; 48: 7930-45. doi: 10.1002/mp.15285
Open DOI Search in Google Scholar Back to article
Chi JW, Brady M, Moore NR, Schnabel JA. Segmentation of the bladder wall using coupled level set methods. Proceedings of the 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Chicago, Illinois, USA 2011; 1653-6. doi: 10.1109/ISBI.2011.5872721
Open DOI Search in Google Scholar Back to article