Ces radiol. 2023, 77(3):156-163 | DOI: 10.55095/CesRadiol2023/019

Accuracy and efficiency of semi-automatic segmentation programs for liver volume determination from MR imagesOriginal article

Petr Kordač1, Bára Šetinová1, Dita Pajuelo1, Monika Dezortová1, Jan Kovář2, Lenka Rossmeislová3, Michaela Šiklová3, Milan Hájek1, Petr Šedivý1
1 Oddělení výpočetní tomografie, magnetické rezonance a klinické a experimentální spektroskopie, Pracoviště zobrazovacích metod (PZM), Institut klinické a experimentální medicíny, Praha
2 Centrum experimentální medicíny, Institut klinické a experimentální medicíny, Praha
3 Ústav patofyziologie 3. LF UK, Praha

Aim: To evaluate various segmentation software for liver segmentation from MRimages.

Method: Three MR examinations were performed on sevenhealthy volunteers (average age 38.2 ± 5.5 years, BMI = 28.6 ±8.3 kg/m2) without known liver or cholestatic diseases - before initiatingfasting, after 48 hours of fasting, and after subsequent two-day carbohydraterealimentation. The livers were segmented using seven (semi)automatic methodsof software 3D Slicer, LiverLab, ITK-SNAP, Myrian and MedSeg and compared tothe reference manual segmentation.

Results: All methods used for liver volume determination showed good accuracy.Intraclass coefficients of consistency and agreement were above 0.95. TheTotalSegmentator module in the 3D Slicer program achieved the best coefficientof variation (CV), and also demonstrated the highest accuracy in theindividual assessment of the dietary intervention effect, with an average CVbelow 10% (other methods ranged from 10-20%).

Conclusion: 3D Slicer can be considered the best among all the testedsegmentation software for liver segmentation from MR images in terms ofprogram availability, accuracy, and speed. In basic tasks such as organsegmentation, it can compete with commercial software. It can accurately trackliver volume changes during short-term dietary interventions.

Keywords: 3D Slicer, MRI, image segmentation, liver segmentation

Published: September 1, 2023  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Kordač P, Šetinová B, Pajuelo D, Dezortová M, Kovář J, Rossmeislová L, et al.. Accuracy and efficiency of semi-automatic segmentation programs for liver volume determination from MR images. Ces radiol. 2023;77(3):156-163. doi: 10.55095/CesRadiol2023/019.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Janek J, Bician P, Kenderessy P, Kothaj P, Novotná K, et al. Experience with hepatoblastoma treatment in small children-the use of preoperative 3D virtual analysis MeVis for liver resections. Rozhledy v Chirurgii: Mesicnik Ceskoslovenske Chirurgicke Spolecnosti 2017; 96(1): 25-33.
    2. Li K, Yan G, Zheng W. Sun J, and Zou Y. Measurement of the Brain Volume/Liver Volume Ratio by Three-Dimensional MRI in Appropriate-for-Gestational Age Fetuses and Those With Fetal Growth Restriction. Journal of Magnetic Resonance Imaging 2021; 54(6): 1796-1801. Go to original source... Go to PubMed...
    3. Ohshima S. Volume analyzer SYNAPSE VINCENT for liver analysis. Journal of Hepato-Biliary-Pancreatic Sciences 2014; 21(4): 235-238. Go to original source... Go to PubMed...
    4. Hájek M, Dezortová M, Burian M, Dusilová T, Kovář J, et al. Determination of liver steatosis by MR spectroscopic methods PRESS, STEAM and HISTO. Česká radiologie 2020; 74(3): 211-221. Go to original source...
    5. Šedivý P, Dezortová M, Burian M, Dusilová T, Kovář J, et al. Porovnání přesnosti spektroskopických a zobrazovacích technik magnetické rezonance pro stanovení jaterní steatózy. Chemicke Listy 2021; 115: 46-53.
    6. Sedivy P, Dusilova T, Setinova B, Dezortova M, Burian M, et al. Liver response to fasting and isocaloric high-carbohydrate refeeding in lean and obese women. Abstract ISMRM London 2022.
    7. 3D Slicer (USA), v. 5.2.2 (vytvořeno 22. 2. 2022) [software] [cit. 27. 7. 2023]. Dostupný z: https://download.slicer.org/. Windows 10, 64 bit, 16 GB RAM, CPU i3.
    8. Fedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin JC, et al. 3D Slicer as an Image Computing Platform for the Quantitative Imaging Network. Magnetic Resonance Imaging 2012; 30(9): 1323-1341. PMID: 22770690. PMCID: PMC3466397. Go to original source... Go to PubMed...
    9. Egger J, Kapur T, Nimsky C, Kikinis R. Pituitary adenoma volumetry with 3D Slicer. PLoS One 2012; 7(12): e51788. Go to original source... Go to PubMed...
    10. Hasan SM, Ahmad M. Two-step verification of brain tumor segmentation using watershed-matching algorithm. Brain informatics 2018; 5(2): 1-11. Go to original source... Go to PubMed...
    11. TotalSegmentator v. 1.0 [modul do programu 3D-Slicer] [cit. 27. 7. 2023]. Dostupný z: https://doi.org/10.48550/arXiv.2208.05868. Windows 10, 64 bit, 16 GB RAM, CPU i3.
    12. Sellers R. MR LiverLab. MAGNETOM Flash 2016; 66.
    13. ITK-SNAP (USA), v. 3.6.0 (vytvořeno 1. 4. 2017) [software] [cit. 27. 7. 2023]. Dostupný z: http://www.itksnap.org/pmwiki/pmwiki.php?n=Downloads.SNAP3. Windows 10, 64 bit, 16 GB RAM, CPU i3.
    14. Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, et al. User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. Neuroimage 2006; 31(3): 1116-1128. Go to original source... Go to PubMed...
    15. Yushkevich, PA, Pashchinskiy A, Oguz I, Mohan S, Schmitt JE, et al. User-guided segmentation of multi-modality medical imaging datasets with ITK-SNAP. Neuroinformatics 2019; 17: 83-102. Go to original source... Go to PubMed...
    16. Myrian® Studio (Intrasense, Francie), v. 2.6.4 (vytvořeno 10. 5. 2019) [software] [cit. 27. 7. 2023]. Dostupný z: https://studio.myrian.fr/downloadoldversions/. Windows 10, 64 bit, 16 GB RAM, CPU i3.
    17. MedSeg (Norsko) (vytvořeno 21. 9. 2019) [webový software] [cit. 27. 7. 2023]. Dostupný z: https://htmlsegmentation.s3.eu-north-1.amazonaws.com/index.html. Windows 10, 64 bit, 16 GB RAM, CPU i3, Google Chrome.
    18. Suri JS, Agarwal S, Carriero A, Paschè A, Danna PS, et al. COVLIAS 1.0 vs. MedSeg: artificial intelligence-based comparative study for automated COVID-19 computed tomography lung segmentation in Italian and Croatian Cohorts. Diagnostics 2021; 11(12): 2367. Go to original source... Go to PubMed...
    19. Shrout PE, Fleiss JL. Intraclass correlations: Uses in assessing rater reliability. Psychological Bulletin 1979; 86: 420-428. Go to original source... Go to PubMed...
    20. Koo TK, Li MY. A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research. Journal of Chiropractic Medicine 2016; 15(2): 155-163. Go to original source... Go to PubMed...
    21. Altman DG, Bland JM. Measurement in medicine: The analysis of method comparison studies. The Statistician 1983; 32: 307-317. Go to original source...

    This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content