Top

Published in:

01-12-2021 | Artificial Intelligence | Original research

Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET

Authors: Elisabeth Pfaehler, Liesbet Mesotten, Gem Kramer, Michiel Thomeer, Karolien Vanhove, Johan de Jong, Peter Adriaensens, Otto S. Hoekstra, Ronald Boellaard

Published in: EJNMMI Research | Issue 1/2021

Abstract

Background

Positron emission tomography (PET) is routinely used for cancer staging and treatment follow-up. Metabolic active tumor volume (MATV) as well as total MATV (TMATV—including primary tumor, lymph nodes and metastasis) and/or total lesion glycolysis derived from PET images have been identified as prognostic factor or for the evaluation of treatment efficacy in cancer patients. To this end, a segmentation approach with high precision and repeatability is important. However, the implementation of a repeatable and accurate segmentation algorithm remains an ongoing challenge.

Methods

In this study, we compare two semi-automatic artificial intelligence (AI)-based segmentation methods with conventional semi-automatic segmentation approaches in terms of repeatability. One segmentation approach is based on a textural feature (TF) segmentation approach designed for accurate and repeatable segmentation of primary tumors and metastasis. Moreover, a convolutional neural network (CNN) is trained. The algorithms are trained, validated and tested using a lung cancer PET dataset. The segmentation accuracy of both segmentation approaches is compared using the Jaccard coefficient (JC). Additionally, the approaches are externally tested on a fully independent test–retest dataset. The repeatability of the methods is compared with those of two majority vote (MV2, MV3) approaches, 41%SUV_MAX, and a SUV > 4 segmentation (SUV4). Repeatability is assessed with test–retest coefficients (TRT%) and intraclass correlation coefficient (ICC). An ICC > 0.9 was regarded as representing excellent repeatability.

Results

The accuracy of the segmentations with the reference segmentation was good (JC median TF: 0.7, CNN: 0.73). Both segmentation approaches outperformed most other conventional segmentation methods in terms of test–retest coefficient (TRT% mean: TF: 13.0%, CNN: 13.9%, MV2: 14.1%, MV3: 28.1%, 41%SUV_MAX: 28.1%, SUV4: 18.1%) and ICC (TF: 0.98, MV2: 0.97, CNN: 0.99, MV3: 0.73, SUV4: 0.81, and 41%SUV_MAX: 0.68).

Conclusion

The semi-automatic AI-based segmentation approaches used in this study provided better repeatability than conventional segmentation approaches. Moreover, both algorithms lead to accurate segmentations for both primary tumors as well as metastasis and are therefore good candidates for PET tumor segmentation.

Available only for authorised users

Volpi S, Ali JM, Tasker A, et al. The role of positron emission tomography in the diagnosis, staging and response assessment of non-small cell lung cancer. Ann Transl Med. 2018;6:95–95. https://doi.org/10.21037/atm.2018.01.25.CrossRefPubMedPubMedCentral

Griffeth LK. Use of PET/CT scanning in cancer patients: technical and practical considerations. Proc (Bayl Univ Med Cent). 2005;18:321–30. https://doi.org/10.1080/08998280.2005.11928089.CrossRef

Hammerschmidt S, Wirtz H. Lung cancer. Dtsch Aerzteblatt Online. 2009. https://doi.org/10.3238/arztebl.2009.0809.CrossRef

Vorwerk H, Beckmann G, Bremer M, et al. The delineation of target volumes for radiotherapy of lung cancer patients. Radiother Oncol. 2009;91:455–60. https://doi.org/10.1016/j.radonc.2009.03.014.CrossRefPubMed

Johansson J, Alakurtti K, Joutsa J, et al. Comparison of manual and automatic techniques for substriatal segmentation in 11C-raclopride high-resolution PET studies. Nucl Med Commun. 2016;37:1074–87. https://doi.org/10.1097/MNM.0000000000000559.CrossRefPubMed

Hatt M, Lee JA, Schmidtlein CR, et al. Classification and evaluation strategies of auto-segmentation approaches for PET: report of AAPM task group No. 211. Med Phys. 2017;44:e1–42. https://doi.org/10.1002/mp.12124.CrossRefPubMed

Kolinger GD, Vállez García D, Kramer GM, et al. Repeatability of [18F]FDG PET/CT total metabolic active tumour volume and total tumour burden in NSCLC patients. EJNMMI Res. 2019;9:14. https://doi.org/10.1186/s13550-019-0481-1.CrossRefPubMedPubMedCentral

Schinagl DAX, Vogel WV, Hoffmann AL, et al. Comparison of five segmentation tools for 18F-fluoro-deoxy-glucose–positron emission tomography-based target volume definition in head and neck cancer. Int J Radiat Oncol. 2007;69:1282–9. https://doi.org/10.1016/j.ijrobp.2007.07.2333.CrossRef

Jentzen W, Freudenberg L, Eising EG, et al. Segmentation of PET volumes by iterative image thresholding. J Nucl Med. 2007;48:108–14.PubMed

10.

Nestle U, Kremp S, Schaefer-Schuler A, et al. Comparison of different methods for delineation of ¹⁸F-FDG PET-positive tissue for target volume definition in radiotherapy of patients with non-Small cell lung cancer. J Nucl Med. 2005;46:1342–8.PubMed

11.

Halt M, Le Rest CC, Turzo A, et al. A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET. IEEE Trans Med Imaging. 2009;28:881–93. https://doi.org/10.1109/TMI.2008.2012036.CrossRef

12.

Foster B, Bagci U, Mansoor A, et al. A review on segmentation of positron emission tomography images. Comput Biol Med. 2014;50:76–96. https://doi.org/10.1016/j.compbiomed.2014.04.014.CrossRefPubMed

13.

Zhang Y, Oikonomou A, Wong A, et al. Radiomics-based prognosis analysis for non-small cell lung cancer. Sci Rep. 2017;7:46349. https://doi.org/10.1038/srep46349.CrossRefPubMedPubMedCentral

14.

Zhong Z, Kim Y, Zhou L, et al. 3D fully convolutional networks for co-segmentation of tumors on PET-CT images. In: Proceedings—international symposium on biomedical imaging; 2018. p. 228–31. https://doi.org/https://doi.org/10.1109/ISBI.2018.8363561.

15.

Blanc-Durand P, Van Der Gucht A, Schaefer N, et al. Automatic lesion detection and segmentation of18F-FET PET in gliomas: a full 3D U-Net convolutional neural network study. PLoS ONE. 2018;13:1–11. https://doi.org/10.1371/journal.pone.0195798.CrossRef

16.

Yu H, Caldwell C, Mah K, Mozeg D. Coregistered FDG PET/CT-based textural characterization of head and neck cancer for radiation treatment planning. IEEE Trans Med Imaging. 2009;28:374–83. https://doi.org/10.1109/TMI.2008.2004425.CrossRefPubMed

17.

Yu H, Caldwell C, Mah K, et al. Automated radiation targeting in head-and-neck cancer using region-based texture analysis of PET and CT images. Int J Radiat Oncol Biol Phys. 2009;75:618–25. https://doi.org/10.1016/j.ijrobp.2009.04.043.CrossRefPubMed

18.

Markel D, Caldwell C, Alasti H, et al. Automatic segmentation of lung carcinoma using 3D texture features in 18-FDG PET/CT. Int J Mol Imaging. 2013;2013:1–13. https://doi.org/10.1155/2013/980769.CrossRef

19.

Aide N, Lasnon C, Veit-Haibach P, et al. EANM/EARL harmonization strategies in PET quantification: from daily practice to multicentre oncological studies. Eur J Nucl Med Mol Imaging. 2017;44:17–31. https://doi.org/10.1007/s00259-017-3740-2.CrossRefPubMedPubMedCentral

20.

Boellaard R, Delgado-Bolton R, Oyen WJG, et al. FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging. 2015;42:328–54. https://doi.org/10.1007/s00259-014-2961-x.CrossRefPubMed

21.

Vanhove K, Mesotten L, Heylen M, et al. Prognostic value of total lesion glycolysis and metabolic active tumor volume in non-small cell lung cancer. Cancer Treat Res Commun. 2018;15:7–12. https://doi.org/10.1016/j.ctarc.2017.11.005.CrossRefPubMed

22.

van Baardwijk A, Bosmans G, Boersma L, et al. PET-CT-based auto-contouring in non-small-cell lung cancer correlates with pathology and reduces interobserver variability in the delineation of the primary tumor and involved nodal volumes. Int J Radiat Oncol Biol Phys. 2007;68:771–8. https://doi.org/10.1016/j.ijrobp.2006.12.067.CrossRefPubMed

23.

Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation; 2015.

24.

Van GJJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017;77:104–8. https://doi.org/10.1158/0008-5472.CAN-17-0339.CrossRef

25.

Pfaehler E, Mesotten L, Kramer G, et al. Textural feature based segmentation: a repeatable and accurate segmentation approach for tumors in PET images; 2020. pp. 3–14.

26.

Koo TK, Li MY. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med. 2016;15:155–63. https://doi.org/10.1016/j.jcm.2016.02.012.CrossRefPubMedPubMedCentral

27.

Hatt M, Laurent B, Ouahabi A, et al. The first MICCAI challenge on PET tumor segmentation. Med Image Anal. 2018;44:177–95. https://doi.org/10.1016/j.media.2017.12.007.CrossRefPubMed

28.

Frings V, de Langen AJ, Smit EF, et al. Repeatability of metabolically active volume measurements with 18F-FDG and 18F-FLT PET in non-small cell lung cancer. J Nucl Med. 2010;51:1870–7. https://doi.org/10.2967/jnumed.110.077255.CrossRefPubMed

Title: Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET
Authors: Elisabeth Pfaehler
Liesbet Mesotten
Gem Kramer
Michiel Thomeer
Karolien Vanhove
Johan de Jong
Peter Adriaensens
Otto S. Hoekstra
Ronald Boellaard
Publication date: 01-12-2021
Publisher: Springer Berlin Heidelberg
Keywords: Artificial Intelligence
Positron Emission Tomography
Published in: EJNMMI Research / Issue 1/2021
Electronic ISSN: 2191-219X
DOI: https://doi.org/10.1186/s13550-020-00744-9

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Repeatability of two semi-automatic artificial intelligence approaches for tumor segmentation in PET

Abstract

Background

Methods

Results

Conclusion

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Background

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2021

Hematologic safety of 177Lu-PSMA-617 radioligand therapy in patients with metastatic castration-resistant prostate cancer

A PSMA-targeted theranostic approach is unlikely to be efficient in serous ovarian cancers

Angiogenesis imaging study using interim [18F] RGD-K5 PET/CT in patients with lymphoma undergoing chemotherapy: preliminary evidence

A preliminary clinical trial to evaluate 64Cu-NOTA-Trastuzumab as a positron emission tomography imaging agent in patients with breast cancer

[18F]FDG-PET/CT in prone compared to supine position for optimal axillary staging and treatment in clinically node-positive breast cancer patients with neoadjuvant systemic therapy

Predicting the nature of pleural effusion in patients with lung adenocarcinoma based on 18F-FDG PET/CT