Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics.
Computer-assisted image analyses
Deep learning
Liver
Magnetic resonance imaging
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
13 Jan 2024
13 Jan 2024
Historique:
received:
22
08
2023
accepted:
29
10
2023
revised:
20
09
2023
medline:
13
1
2024
pubmed:
13
1
2024
entrez:
13
1
2024
Statut:
aheadofprint
Résumé
To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI). This retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by the Dice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC). In total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets. Automated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction. Liver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI. • This deep convolutional neural network yields robust and generalizable liver segmentation performance on internal, external, and public testing data. • Automated liver volumetry demonstrated excellent agreement with manual volumetry. • Automated liver segmentations can be used for robust and reproducible radiomic feature extraction.
Identifiants
pubmed: 38217704
doi: 10.1007/s00330-023-10495-5
pii: 10.1007/s00330-023-10495-5
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s).
Références
Chernyak V, Fowler KJ, Kamaya A et al (2018) Liver Imaging Reporting and Data System (LI-RADS) version 2018: imaging of hepatocellular carcinoma in at-risk patients. Radiology 289:816–830
doi: 10.1148/radiol.2018181494
pubmed: 30251931
Faria SC, Ganesan K, Mwangi I et al (2009) MR imaging of liver fibrosis: current state of the art. Radiographics 29:1615–1635
doi: 10.1148/rg.296095512
pubmed: 19959511
Gupta AA, Kim DC, Krinsky GA, Lee VS (2004) CT and MRI of cirrhosis and its mimics. AJR Am J Roentgenol 183:1595–1601
doi: 10.2214/ajr.183.6.01831595
pubmed: 15547196
Wang C, Huang Y, Liu C et al (2023) Diagnosis of clinically significant portal hypertension using CT- and MRI-based vascular model. Radiology 307:e221648
doi: 10.1148/radiol.221648
pubmed: 36719293
Taner CB, Dayangac M, Akin B et al (2008) Donor safety and remnant liver volume in living donor liver transplantation. Liver Transpl 14:1174–1179
doi: 10.1002/lt.21562
pubmed: 18668669
Guglielmi A, Ruzzenente A, Conci S, Valdegamberi A, Iacono C (2012) How much remnant is enough in liver resection? Dig Surg 29:6–17
doi: 10.1159/000335713
pubmed: 22441614
Theysohn JM, Ertle J, Muller S et al (2014) Hepatic volume changes after lobar selective internal radiation therapy (SIRT) of hepatocellular carcinoma. Clin Radiol 69:172–178
doi: 10.1016/j.crad.2013.09.009
pubmed: 24209871
Gloger O, Kuhn J, Stanski A, Volzke H, Puls R (2010) A fully automatic three-step liver segmentation method on LDA-based probability maps for multiple contrast MR images. Magn Reson Imaging 28:882–897
doi: 10.1016/j.mri.2010.03.010
pubmed: 20409666
Zygomalas A, Kehagias I (2019) Up-to-date intraoperative computer assisted solutions for liver surgery. World J Gastrointest Surg 11:1–10
doi: 10.4240/wjgs.v11.i1.1
pubmed: 30705734
pmcid: 6354070
Jabbour SK, Hashem SA, Bosch W et al (2014) Upper abdominal normal organ contouring guidelines and atlas: a Radiation Therapy Oncology Group consensus. Pract Radiat Oncol 4:82–89
doi: 10.1016/j.prro.2013.06.004
pubmed: 24890348
Bousabarah K, Letzen B, Tefera J et al (2020) Automated detection and delineation of hepatocellular carcinoma on multiphasic contrast-enhanced MRI using deep learning. Abdom Radiol (NY). https://doi.org/10.1007/s00261-020-02604-5
Gotra A, Sivakumaran L, Chartrand G et al (2017) Liver segmentation: indications, techniques and future directions. Insights Imaging 8:377–392
doi: 10.1007/s13244-017-0558-1
pubmed: 28616760
pmcid: 5519497
Yamashita R, Nishio M, Do RKG, Togashi K (2018) Convolutional neural networks: an overview and application in radiology. Insights Imaging 9:611–629
doi: 10.1007/s13244-018-0639-9
pubmed: 29934920
pmcid: 6108980
Dockes J, Varoquaux G, Poline JB (2021) Preventing dataset shift from breaking machine-learning biomarkers. Gigascience 10
Yu AC, Mohajer B, Eng J (2022) External validation of deep learning algorithms for radiologic diagnosis: a systematic review. Radiol Artif Intell 4:e210064
doi: 10.1148/ryai.210064
pubmed: 35652114
pmcid: 9152694
Gross M, Spektor M, Jaffe A et al (2021) Improved performance and consistency of deep learning 3D liver segmentation with heterogeneous cancer stages in magnetic resonance imaging. PLoS One 16:e0260630
doi: 10.1371/journal.pone.0260630
pubmed: 34852007
pmcid: 8635384
Park HJ, Park B, Lee SS (2020) Radiomics and deep learning: hepatic applications. Korean J Radiol 21:387–401
doi: 10.3348/kjr.2019.0752
pubmed: 32193887
pmcid: 7082656
Rofsky NM, Lee VS, Laub G et al (1999) Abdominal MR imaging with a volumetric interpolated breath-hold examination. Radiology 212:876–884
doi: 10.1148/radiology.212.3.r99se34876
pubmed: 10478260
Gross M, Arora S, Huber S, Kücükkaya AS, Onofrey JA (2023) LiverHccSeg: a publicly available multiphasic MRI dataset with liver and HCC tumor segmentations and inter-rater agreement analysis. Data Brief 51:109662. https://doi.org/10.1016/j.dib.2023.109662
Fedorov A, Beichel R, Kalpathy-Cramer J et al (2012) 3D Slicer as an image computing platform for the quantitative imaging network. Magn Reson Imaging 30:1323–1341
doi: 10.1016/j.mri.2012.05.001
pubmed: 22770690
pmcid: 3466397
Kerfoot E, Clough J, Oksuz I, Lee J, King AP, Schnabel JA (2019) Left-ventricle quantification using residual U-Net. Statistical atlases and computational models of the heart atrial segmentation and LV quantification challenges STACOM 2018 Lecture Notes in Computer Science 11395:371-380
Onofrey JA, Casetti-Dinescu DI, Lauritzen AD et al (2019) Generalizable multi-site training and testing of deep neural networks using image normalization. Proc IEEE Int Symp Biomed Imaging. https://doi.org/10.1109/ISBI.2019.8759295:348-351
Milletari F, Navab N, Ahmadi S-A (2016) V-Net: fully convolutional neural networks for volumetric medical image segmentation. Fourth International Conference on 3D Vision (3DV):565–571
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:14126980
van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107
doi: 10.1158/0008-5472.CAN-17-0339
pubmed: 29092951
pmcid: 5672828
Koo TK, Li MY (2016) A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med 15:155–163
doi: 10.1016/j.jcm.2016.02.012
pubmed: 27330520
pmcid: 4913118
Adams R, Bischof L (1994) Seeded region growing. IEEE Trans Pattern Anal Mach Intell 16:641–647
doi: 10.1109/34.295913
Zhang X, Tian J, Xiang D, Li X, Deng K (2011) Interactive liver tumor segmentation from ct scans using support vector classification with watershed. Annu Int Conf IEEE Eng Med Biol Soc 2011:6005–6008
pubmed: 22255708
Huynh HT, Le-Trong N, Bao PT, Oto A, Suzuki K (2017) Fully automated MR liver volumetry using watershed segmentation coupled with active contouring. Int J Comput Assist Radiol Surg 12:235–243
doi: 10.1007/s11548-016-1498-9
pubmed: 27873147
Lu F, Wu F, Hu P, Peng Z, Kong D (2017) Automatic 3D liver location and segmentation via convolutional neural network and graph cut. Int J Comput Assist Radiol Surg 12:171–182
doi: 10.1007/s11548-016-1467-3
pubmed: 27604760
Huynh HT, Le-Trong N, Bao PT, Oto A, Suzuki K (2017) Fully automated MR liver volumetry using watershed segmentation coupled with active contouring. Int J Comput Assist Radiol Surg 12:235–243
doi: 10.1007/s11548-016-1498-9
pubmed: 27873147
Huynh HT, Karademir I, Oto A, Suzuki K (2014) Computerized liver volumetry on MRI by using 3D geodesic active contour segmentation. AJR Am J Roentgenol 202:152–159
doi: 10.2214/AJR.13.10812
pubmed: 24370139
pmcid: 4271806
Wang K, Mamidipalli A, Retson T et al (2019) Automated CT and MRI liver segmentation and biometry using a generalized convolutional neural network. Radiol Artif Intell 1(2):180022
Jimenez-Pastor A, Alberich-Bayarri A, Lopez-Gonzalez R et al (2021) Precise whole liver automatic segmentation and quantification of PDFF and R2* on MR images. Eur Radiol 31:7876–7887
doi: 10.1007/s00330-021-07838-5
pubmed: 33768292
Dodd GD 3rd, Baron RL, Oliver JH 3rd, Federle MP (1999) Spectrum of imaging findings of the liver in end-stage cirrhosis: part I, gross morphology and diffuse abnormalities. AJR Am J Roentgenol 173:1031–1036
doi: 10.2214/ajr.173.4.10511173
pubmed: 10511173
Huber A, Ebner L, Heverhagen JT, Christe A (2015) State-of-the-art imaging of liver fibrosis and cirrhosis: a comprehensive review of current applications and future perspectives. Eur J Radiol Open 2:90–100
doi: 10.1016/j.ejro.2015.05.002
pubmed: 26937441
pmcid: 4750581
Ivashchenko OV, Rijkhorst EJ, Ter Beek LC et al (2020) A workflow for automated segmentation of the liver surface, hepatic vasculature and biliary tree anatomy from multiphase MR images. Magn Reson Imaging 68:53–65
doi: 10.1016/j.mri.2019.12.008
pubmed: 31935445
Liu M, Vanguri R, Mutasa S et al (2020) Channel width optimized neural networks for liver and vessel segmentation in liver iron quantification. Comput Biol Med 122:103798
doi: 10.1016/j.compbiomed.2020.103798
pubmed: 32658724
Zeng Q, Karimi D, Pang EHT et al (2019) Liver segmentation in magnetic resonance imaging via mean shape fitting with fully convolutional neural networks. Springer International Publishing, Cham, pp 246–254
Wei J, Jiang H, Gu D et al (2020) Radiomics in liver diseases: current progress and future opportunities. Liver Int 40:2050–2063
doi: 10.1111/liv.14555
pubmed: 32515148
pmcid: 7496410
Lin YC, Lin CH, Lu HY et al (2020) Deep learning for fully automated tumor segmentation and extraction of magnetic resonance radiomics features in cervical cancer. Eur Radiol 30:1297–1305
doi: 10.1007/s00330-019-06467-3
pubmed: 31712961
Blanc-Durand P, Van Der Gucht A, Jreige M et al (2018) Signature of survival: a (18)F-FDG PET based whole-liver radiomic analysis predicts survival after (90)Y-TARE for hepatocellular carcinoma. Oncotarget 9:4549–4558
doi: 10.18632/oncotarget.23423
pubmed: 29435123
Demirjian A, Peng P, Geschwind JF et al (2011) Infiltrating hepatocellular carcinoma: seeing the tree through the forest. J Gastrointest Surg 15:2089–2097
doi: 10.1007/s11605-011-1614-7
pubmed: 21725699
pmcid: 3580771