Share：
Share this content in WeChat
X
[Chinese][PDF]261
• Review •
Advances in imaging to assess liver volume
ZHANG Yiming  ZHANG Xiaoyan  QIAO Miaomiao  WANG Miaomiao  GUO Shunlin 

Cite this article as: ZHANG Y M, ZHANG X Y, QIAO M M, et al. Advances in imaging to assess liver volume[J]. Chin J Magn Reson Imaging, 2025, 16(6): 195-200, 227. DOI:10.12015/issn.1674-8034.2025.06.030.


[Abstract] Liver volume measurement is of great clinical value in diagnosing diseases, planning surgeries, and assessing prognoses. As medical imaging technology continues to advance, liver volume measurement methods have evolved remarkably from traditional manual measurement to modern automated segmentation. However, existing techniques still face many challenges. Traditional manual measurements are time-consuming and subjective, while semi-automated or early automated methods have high measurement errors. Artificial intelligence techniques based on deep learning have been found to improve the accuracy and efficiency of liver volume measurements, especially in heterogeneous lesions and regions with ambiguous boundaries. Recently, no systematic review of these techniques has been published. This paper reviews the evolution of liver volumetry techniques in depth, compares and analyzes the advantages and disadvantages of different techniques, and focuses on AI's breakthroughs in this field. However, AI still has limitations, such as insufficient generalization ability for certain complex cases and reliance on high-quality annotated data. Therefore, future research should focus on optimizing imaging techniques, developing efficient automated algorithms, and constructing robust AI models to promote the precision and clinical application of liver volumetric measurements. This will provide systematic references for clinical practice and technological innovation.
[Keywords] liver disease；hepatectomy；liver volume measurement；magnetic resonance imaging；computed tomography；artificial intelligence

ZHANG Yiming1   ZHANG Xiaoyan1   QIAO Miaomiao1   WANG Miaomiao1   GUO Shunlin1, 2*  

1 The First Clinical Medical College of Lanzhou University, Lanzhou 730030, China

2 Department of Radiology, the First Hospital of Lanzhou University, Lanzhou 730030, China

Corresponding author: GUO S L, E-mail: guoshl@lzu.edu.cn

Conflicts of interest   None.

Received  2025-03-07
Accepted  2025-05-20
DOI: 10.12015/issn.1674-8034.2025.06.030
Cite this article as: ZHANG Y M, ZHANG X Y, QIAO M M, et al. Advances in imaging to assess liver volume[J]. Chin J Magn Reson Imaging, 2025, 16(6): 195-200, 227. DOI:10.12015/issn.1674-8034.2025.06.030.

[1]
ZHAO Y D, ZHU Y F. Correlation between liver volume measured by multi-slice spiral CT and liver reserve function in patients with liver cirrhosis[J]. J Imag Res Med Appl, 2024, 8(21): 162-164. DOI: 10.3969/j.issn.2096-3807.2024.21.051.
[2]
XIU Z, ZOU Z C, ZHANG Y L, et al. Application of multi-slice spiral CT volume measurement in evaluating liver reserve function in patients with liver cirrhosis[J]. Chin Hepatol, 2024, 29(10): 1235-1238. DOI: 10.14000/j.cnki.issn.1008-1704.2024.10.005.
[3]
SHI W D, CUI Z X, ZHANG D, et al. Application of MSCT in evaluating liver volume and spleen volume in diagnosing liver cirrhosis and liver reserve function[J]. Imag Sci Photochem, 2022, 40(2): 377-381. DOI: 10.7517/issn.1674-0475.210920.
[4]
ZHU X Q, JIANG K, PAN J. Evaluation of hepatic functional reserve using practical liver volumes measured by enhanced CT scan in patients with hepatitis B liver cirrhosis[J]. J Pract Hepatol, 2020, 23(5): 711-714. DOI: 10.3969/j.issn.1672-5069.2020.05.027.
[5]
GERSTENMAIER J F, GIBSON R N. Ultrasound in chronic liver disease[J]. Insights Imaging, 2014, 5(4): 441-455. DOI: 10.1007/s13244-014-0336-2.
[6]
SEPPELT D, KROMREY M L, ITTERMANN T, et al. Reliability and accuracy of straightforward measurements for liver volume determination in ultrasound and computed tomography compared to real volumetry[J/OL]. Sci Rep, 2022, 12: 12465 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/35864140/. DOI: 10.1038/s41598-022-16736-9.
[7]
PU X L. Ultrasonic image analysis and diagnosis of liver based on machine learning[D]. Shanghai: Shanghai University of Engineering Science, 2022. DOI: 10.27715/d.cnki.gshgj.2022.000981.
[8]
SEO H, HUANG C, BASSENNE M, et al. Modified U-Net (mU-Net) with incorporation of object-dependent high level features for improved liver and liver-tumor segmentation in CT images[J]. IEEE Trans Med Imaging, 2020, 39(5): 1316-1325. DOI: 10.1109/tmi.2019.2948320.
[9]
KAMAL O A, AZAB E A, MAHMOUD A A, et al. Comparison between manual and automated CT liver volumetry in assessment of the liver volume in living donor liver transplantation[J/OL]. QJM, 2021, 114(Supplement_1): hcab106.020 [2025-05-02]. https://academic.oup.com/qjmed/article/114/Supplement1/hcab106.020/6372906. DOI: 10.1093/qjmed/hcab106.020.
[10]
KUTAIBA N, CHUNG W, GOODWIN M, et al. The impact of hepatic and splenic volumetric assessment in imaging for chronic liver disease: a narrative review[J/OL]. Insights Imaging, 2024, 15(1): 146 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/38886297/. DOI: 10.1186/s13244-024-01727-3.
[11]
LIAN D, WANG W, LIU L, et al. CT volumetry helps predict prognosis of large hepatocellular carcinoma after resection[J/OL]. Clin Radiol, 2022, 77(8): e599-e605 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/35483982/. DOI: 10.1016/j.crad.2022.03.018.
[12]
HERMOYE L, LAAMARI-AZJAL I, CAO Z J, et al. Liver segmentation in living liver transplant donors: comparison of semiautomatic and manual methods[J]. Radiology, 2005, 234(1): 171-178. DOI: 10.1148/radiol.2341031801.
[13]
TAN E K, ZHENG V, TUIENG S Y, et al. Evaluation of liver volume estimation methods in living donor liver transplant: CT volumetry vs MeVis, with comparison of open and laparoscopic surgery[J]. Transplant Proc, 2025, 57(2): 292-297. DOI: 10.1016/j.transproceed.2024.12.017.
[14]
JEONG S Y, LEE J, KIM K W, et al. Estimation of the right posterior section volume in live liver donors: semiautomated CT volumetry using portal vein segmentation[J]. Acad Radiol, 2020, 27(2): 210-218. DOI: 10.1016/j.acra.2019.03.018.
[15]
AAPKES S E, BARTEN T R M, COUDYZER W, et al. Validation of a semi-automatic method to measure total liver volumes in polycystic liver disease on computed tomography - high speed and accuracy[J]. Eur Radiol, 2023, 33(5): 3222-3231. DOI: 10.1007/s00330-022-09346-6.
[16]
KALSHABAY Y, ZHOLDYBAY Z, DI MARTINO M, et al. CT volume analysis in living donor liver transplantation: accuracy of three different approaches[J/OL]. Insights Imaging, 2023, 14(1): 82 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/37184628/. DOI: 10.1186/s13244-023-01431-8.
[17]
WINKEL D J, WEIKERT T J, BREIT H C, et al. Validation of a fully automated liver segmentation algorithm using multi-scale deep reinforcement learning and comparison versus manual segmentation[J/OL]. Eur J Radiol, 2020, 126: 108918 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/32171914/. DOI: 10.1016/j.ejrad.2020.108918.
[18]
MACHRY M, FERREIRA L F, LUCCHESE A M, et al. Liver volumetric and anatomic assessment in living donor liver transplantation: The role of modern imaging and artificial intelligence[J]. World J Transplant, 2023, 13(6): 290-298. DOI: 10.5500/wjt.v13.i6.290.
[19]
NÚÑEZ L, FERREIRA C, MOJTAHED A, et al. Assessing the performance of AI-assisted technicians in liver segmentation, Couinaud division, and lesion detection: a pilot study[J]. Abdom Radiol (NY), 2024, 49(12): 4264-4272. DOI: 10.1007/s00261-024-04507-1.
[20]
AHN Y, YOON J S, LEE S S, et al. Deep learning algorithm for automated segmentation and volume measurement of the liver and spleen using portal venous phase computed tomography images[J]. Korean J Radiol, 2020, 21(8): 987-997. DOI: 10.3348/kjr.2020.0237.
[21]
PETTIT R W, MARLATT B B, CORR S J, et al. nnU-net deep learning method for segmenting parenchyma and determining liver volume from computed tomography images[J/OL]. Ann Surg Open, 2022, 3(2): e155 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/36275876/. DOI: 10.1097/as9.0000000000000155.
[22]
PARK J, JOO I, JEON S K, et al. Automated abdominal organ segmentation algorithms for non-enhanced CT for volumetry and 3D radiomics analysis[J]. Abdom Radiol (NY), 2025, 50(3): 1448-1456. DOI: 10.1007/s00261-024-04581-5.
[23]
JEON S K, JOO I, PARK J, et al. Fully-automated multi-organ segmentation tool applicable to both non-contrast and post-contrast abdominal CT: deep learning algorithm developed using dual-energy CT images[J/OL]. Sci Rep, 2024, 14: 4378 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/38388824/. DOI: 10.1038/s41598-024-55137-y.
[24]
LEE S, ELTON D C, YANG A H, et al. Fully automated and explainable liver segmental volume ratio and spleen segmentation at CT for diagnosing cirrhosis[J/OL]. Radiol Artif Intell, 2022, 4(5): e210268 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/36204530/. DOI: 10.1148/ryai.210268.
[25]
GHOBADI V, ISMAIL L I, WAN HASAN W Z, et al. Challenges and solutions of deep learning-based automated liver segmentation: A systematic review[J/OL]. Comput Biol Med, 2025, 185: 109459 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/39642700/. DOI: 10.1016/j.compbiomed.2024.109459.
[26]
CHEN C, MAT ISA N A, LIU X. A review of convolutional neural network based methods for medical image classification[J/OL]. Comput Biol Med, 2025, 185: 109507 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/39631108/. DOI: 10.1016/j.compbiomed.2024.109507.
[27]
RAO S, GLAVIS-BLOOM J, BUI T L, et al. Artificial intelligence for improved hepatosplenomegaly diagnosis[J]. Curr Probl Diagn Radiol, 2023, 52(6): 501-504. DOI: 10.1067/j.cpradiol.2023.05.005.
[28]
OU J, JIANG L, BAI T, et al. ResTransUnet: an effective network combined with Transformer and U-Net for liver segmentation in CT scans[J/OL]. Comput Biol Med, 2024, 177: 108625 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/38823365/. DOI: 10.1016/j.compbiomed.2024.108625.
[29]
WANG H, WANG Z M, CUI X T, et al. TDS-U-Net: automatic liver and tumor separate segmentation of CT volumes using attention gates[J]. J Intell Fuzzy Syst, 2023, 44(6): 8817-8825. DOI: 10.3233/jifs-221111.
[30]
DICKSON J, LINSELY A, ALICE NINETA R J. An integrated 3D-sparse deep belief network with enriched seagull optimization algorithm for liver segmentation[J]. Multimed Syst, 2023, 29(3): 1315-1334. DOI: 10.1007/s00530-023-01056-3.
[31]
PANDE S D, KALYANI P, NAGENDRAM S, et al. Comparative analysis of the DCNN and HFCNN Based Computerized detection of liver cancer[J/OL]. BMC Med Imaging, 2025, 25(1): 37 [2025-05-02]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11792691/. DOI: 10.1186/s12880-025-01578-4.
[32]
ARAÚJO J D L, CRUZ L B DA, FERREIRA J L, et al. An automatic method for segmentation of liver lesions in computed tomography images using deep neural networks[J/OL]. Expert Syst Appl, 2021, 180: 115064 [2025-05-02]. https://www.sciencedirect.com/science/article/pii/S0957417421005054. DOI: 10.1016/j.eswa.2021.115064.
[33]
TU D Y, LIN P C, CHOU H H, et al. Slice-fusion: reducing false positives in liver tumor detection for mask R-CNN[J]. IEEE/ACM Trans Comput Biol Bioinform, 2023, 20(5): 3267-3277. DOI: 10.1109/TCBB.2023.3265394.
[34]
XIA Z, LIAO M, DI S H, et al. Automatic liver segmentation from CT volumes based on multi-view information fusion and condition random fields[J/OL]. Opt Laser Technol, 2024, 179: 111298 [2025-05-02]. https://www.sciencedirect.com/science/article/pii/S0030399224007564. DOI: 10.1016/j.optlastec.2024.111298.
[35]
MARINELLI B, KANG M, MARTINI M, et al. Combination of active transfer learning and natural language processing to improve liver volumetry using surrogate metrics with deep learning[J/OL]. Radiol Artif Intell, 2019, 1(1): e180019 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/33937782/. DOI: 10.1148/ryai.2019180019.
[36]
FANANAPAZIR G, BASHIR M R, MARIN D, et al. Computer-aided liver volumetry: performance of a fully-automated, prototype post-processing solution for whole-organ and lobar segmentation based on MDCT imaging[J]. Abdom Imag, 2015, 40(5): 1203-1212. DOI: 10.1007/s00261-014-0276-9.
[37]
CAO D, YANG Y F, LI M Y, et al. Quantitative comparison of liver volume, proton density fat fraction, and time burden between automatic whole liver segmentation and manual sampling MRI strategies for diagnosing metabolic dysfunction-associated steatotic liver disease in obese patients[J/OL]. Curr Med Imaging, 2024 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/38462830/. DOI: 10.2174/0115734056282249231206060136.
[38]
PARK H J, YOON J S, LEE S S, et al. Deep learning-based assessment of functional liver capacity using gadoxetic acid-enhanced hepatobiliary phase MRI[J]. Korean J Radiol, 2022, 23(7): 720-731. DOI: 10.3348/kjr.2021.0892.
[39]
CHOI J Y, LEE S S, KIM N Y, et al. The effect of hepatic steatosis on liver volume determined by proton density fat fraction and deep learning-measured liver volume[J]. Eur Radiol, 2023, 33(9): 5924-5932. DOI: 10.1007/s00330-023-09603-2.
[40]
SAUNDERS S L, CLARK J M, RUDSER K, et al. Comparison of automatic liver volumetry performance using different types of magnetic resonance images[J]. Magn Reson Imaging, 2022, 91: 16-23. DOI: 10.1016/j.mri.2022.05.002.
[41]
HYODO R, TAKEHARA Y, MIZUNO T, et al. Four-dimensional flow MRI assessment of portal hemodynamics and hepatic regeneration after portal vein embolization[J/OL]. Radiology, 2023, 308(3): e230709 [2025-05-02].https://pubmed.ncbi.nlm.nih.gov/37750777/. DOI: 10.1148/radiol.230709.
[42]
CHOI S H, KWON J H, KIM K W, et al. Measurement of liver volumes by portal vein flow by Doppler ultrasound in living donor liver transplantation[J/OL]. Clin Transplant, 2017, 31(9) [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/28681460/. DOI: 10.1111/ctr.13050.
[43]
MURRAY V, SIDDIQ S, CRANE C, et al. Movienet: Deep space-time-coil reconstruction network without k-space data consistency for fast motion-resolved 4D MRI[J]. Magn Reson Med, 2024, 91(2): 600-614. DOI: 10.1002/mrm.29892.
[44]
XU D, MIAO X, LIU H J, et al. Paired conditional generative adversarial network for highly accelerated liver 4D MRI[J/OL]. Phys Med Biol, 2024, 69(12): 10.1088/1361-10.1088/6560/ad5489 [2025-05-02].https://pubmed.ncbi.nlm.nih.gov/38838679/. DOI: 10.1088/1361-6560/ad5489.
[45]
MOON C M, KIM S K, HEO S, et al. Hemodynamic changes in the portal vein with age: evaluation using four-dimensional flow MRI[J/OL]. Sci Rep, 2023, 13: 7397 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/37149636/. DOI: 10.1038/s41598-023-34522-z.
[46]
XUE Z L, LI P, ZHANG L, et al. Multi-modal co-learning for liver lesion segmentation on PET-CT images[J]. IEEE Trans Med Imaging, 2021, 40(12): 3531-3542. DOI: 10.1109/TMI.2021.3089702.
[47]
OKAJIMA Y, YANAGISAWA S, YAMADA A, et al. Predictability of combining Technetium-99m-galactosyl human serum albumin single-photon emission computed tomography/computed tomography and indocyanine green clearance test for posthepatectomy liver failure[J]. Jpn J Radiol, 2024, 42(11): 1280-1289. DOI: 10.1007/s11604-024-01613-4.
[48]
STRAUSS L G, CLORIUS J H, FRANK T, et al. Single photon emission computerized tomography (SPECT) for estimates of liver and spleen volume[J]. J Nucl Med, 1984, 25(1): 81-85. DOI: 10.1007/s11604-024-01613-4.
[49]
JIMENEZ-MESA C, ARCO J E, MARTINEZ-MURCIA F J, et al. Applications of machine learning and deep learning in SPECT and PET imaging: General overview, challenges and future prospects[J/OL]. Pharmacol Res, 2023, 197: 106984 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/37940064/. DOI: 10.1016/j.phrs.2023.106984.
[50]
KROKOS G, KOTWAL T, MALAIH A, et al. Evaluation of manual and automated approaches for segmentation and extraction of quantitative indices from [18F] FDG PET-CT images[J/OL]. Biomed Phys Eng Express, 2024, 10(2): 025007 [2025-05-02]. https://pubmed.ncbi.nlm.nih.gov/38100790/. DOI: 10.1088/2057-1976/ad160e.
[51]
CIBOROWSKI K, GRAMEK-JEDWABNA A, GOŁĄB M, et al. Performance of a deep learning enhancement method applied to PET images acquired with a reduced acquisition time[J]. Nucl Med Rev Cent East Eur, 2023, 26: 116-122. DOI: 10.5603/nmr.94482.
[52]
AYANA G, DESE K, ABAGARO A M, et al. Multistage transfer learning for medical images[J/OL]. Artif Intell Rev, 2024, 57(9): 232 [2025-05-02]. https://link.springer.com/article/10.1007/s10462-024-10855-7. DOI: 10.1007/s10462-024-10855-7.
[53]
CURRIE G, HEWIS J, HAWK E, et al. Fitness for purpose of text-to-image generative artificial intelligence image creation in medical imaging[J]. J Nucl Med Technol, 2025, 53(1): 63-67. DOI: 10.2967/jnmt.124.268402.

PREV Research progress of radiomics in the prognosis of hepatocellular carcinoma
NEXT Research progress of magnetic resonance elastography in pancreatic diseases
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn