Abstract
Automated organ at risk (OAR) segmentation is crucial for radiation therapy planning in CT scans, but the generated contours by automated models can be inaccurate, potentially leading to treatment planning issues. The reasons for these inaccuracies could be varied, such as unclear organ boundaries or inaccurate ground truth due to annotation errors. To improve the model’s performance, it is necessary to identify these failure cases during the training process and to correct them with some potential post-processing techniques. However, this process can be time-consuming, as traditionally it requires manual inspection of the predicted output. This paper proposes a method to automatically identify failure cases by setting a threshold for the combination of Dice and Hausdorff distances. This approach reduces the time-consuming task of visually inspecting predicted outputs, allowing for faster identification of failure case candidates. The method was evaluated on 20 cases of six different organs in CT images from clinical expert curated datasets. By setting the thresholds for the Dice and Hausdorff distances, the study was able to differentiate between various states of failure cases and evaluate over 12 cases visually. This thresholding approach could be extended to other organs, leading to faster identification of failure cases and thereby improving the quality of radiation therapy planning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Altman, M.B., et al.: A framework for automated contour quality assurance in radiation therapy including adaptive techniques. Phys. Med. Biol. 60(13), 5199 (2015)
Breunig, J., et al.: A system for continual quality improvement of normal tissue delineation for radiation therapy treatment planning. Int. J. Radiat. Oncol. Biol. Phys. 83(5), 703–708 (2012)
Brouwer, C.L., et al.: 3D Variation in delineation of head and neck organs at risk. Radiat. Oncol. 7(1), 1–10 (2012)
Brouwer, C.L., et al.: CT-based delineation of organs at risk in the head and neck region: DAHANCA, EORTC, GORTEC, HKNPCSG, NCIC CTG, NCRI, NRG Oncology and TROG consensus guidelines. Radiother. Oncol. 117(1), 83–90 (2015)
Csapó, T.G., et al.: Optimizing the ultrasound tongue image representation for residual network-based articulatory-to-acoustic mapping. Sensors 22(22), 8601 (2022)
Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)
Fung, N.T.C., et al.: Automatic segmentation for adaptive planning in nasopharyngeal carcinoma IMRT: time, geometrical, and dosimetric analysis. Med. Dosim. 45(1), 60–65 (2020)
He, T., et al.: Multi-task learning for the segmentation of organs at risk with label dependence. Med. Image Anal. 61, 101666 (2020)
Honarmandi Shandiz, A., Tóth, L.: Voice activity detection for ultrasound-based silent speech interfaces using convolutional neural networks. In: Ekštein, K., Pártl, F., Konopík, M. (eds.) TSD 2021. LNCS (LNAI), vol. 12848, pp. 499–510. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-83527-9_43
Huttenlocher, D.P., Klanderman, G.A., Rucklidge, W.J.: Comparing images using the Hausdorff distance. IEEE Trans. Pattern Anal. Mach. Intell. 15(9), 850–863 (1993)
Jadon, S.: A survey of loss functions for semantic segmentation. In: 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pp. 1–7. IEEE (2020)
Karimi, D., Salcudean, S.E.: Reducing the Hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Trans. Med. Imag. 39(2), 499–513 (2019)
Ma, J., et al.: Loss odyssey in medical image segmentation. Med. Image Anal. 71, 102035 (2021)
Maiseli, B.J.: Hausdorff distance with outliers and noise resilience capabilities. SN Comput. Sci. 2(5), 358 (2021)
Roth, H.R., et al.: A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 520–527. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10404-1_65
Seff, A., et al.: 2D view aggregation for lymph node detection using a shallow hierarchy of linear classifiers. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part I 17. LNCS, vol. 8673, pp. 544–552. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10404-1_68
Seff, A., Lu, L., Barbu, A., Roth, H., Shin, H.-C., Summers, R.M.: Leveraging mid-level semantic boundary cues for automated lymph node detection. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part II 18. LNCS, vol. 9350, pp. 53–61. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24571-3_7
Shandiz, A.H., Tóth, L., Gosztolya, G., Markó, A., Csapó, T.G.: Improving neural silent speech interface models by adversarial training. In: Hassanien, A.E., et al. (eds.) AICV 2021. AISC, vol. 1377, pp. 430–440. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-76346-6_39
Shandiz, A.H., et al.: Neural speaker embeddings for ultrasound based silent speech interfaces. arXiv preprint arXiv:2106.04552 (2021)
Tóth, L., Shandiz, A.H.: 3D convolutional neural networks for ultrasound-based silent speech interfaces. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2020, Part I 19. LNCS (LNAI), vol. 12415, pp. 159–169. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-61401-0_16
Van der Heide, U.A., et al.: Functional MRI for radiotherapy dose painting. Magn. Reson. Imaging 30(9), 1216–1223 (2012)
Yide, Y., Shandiz, A.H., Tóth, L.: Reconstructing speech from real-time articulatory MRI using neural vocoders. In: 2021 29th European Signal Processing Conference (EUSIPCO), pp. 945–949. IEEE (2021)
Acknowledgments
We would like to thank all the contributors from the Deep Learning Auto Segmentation (DLAS) project for facilitating this study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shandiz, A.H. et al. (2024). Automated Identification of Failure Cases in Organ at Risk Segmentation Using Distance Metrics: A Study on CT Data. In: Foresti, G.L., Fusiello, A., Hancock, E. (eds) Image Analysis and Processing - ICIAP 2023 Workshops. ICIAP 2023. Lecture Notes in Computer Science, vol 14365. Springer, Cham. https://doi.org/10.1007/978-3-031-51023-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-51023-6_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-51022-9
Online ISBN: 978-3-031-51023-6
eBook Packages: Computer ScienceComputer Science (R0)