This study was supported by the National Natural Science Foundation of China (91959127, 81873897, 82202185, 82102050), the Funding of Shanghai Municipal Health Commission (202140378), Shanghai Science and Technology Development Foundation (22Y11911500), and Science and Technology Commission of Shanghai Municipality (2018SHZDZX01).

The authors of this manuscript declare no conflict of interest.

Read the full text

About

PDF

Tools

Share a link

Email
Wechat
Bluesky

Abstract

Purpose

Posthepatectomy liver failure (PHLF) is a major cause of postoperative mortality in hepatocellular carcinoma (HCC) patients. The study aimed to develop a method based on the two-dimensional shear wave elastography and clinical data to evaluate the risk of PHLF in HCC patients with chronic hepatitis B.

Methods

This multicenter study proposed a deep learning model (PHLF-Net) incorporating dual-modal ultrasound features and clinical indicators to predict the PHLF risk. The datasets were divided into a training cohort, an internal validation cohort, an internal independent testing cohort, and three external independent testing cohorts. Based on ResNet50 pretrained on ImageNet, PHLF-Net used a progressive training strategy with images of varying granularity and incorporated conventional B-mode and elastography images and clinical indicators related to liver reserve function.

Results

In total, 532 HCC patients who underwent hepatectomy at five hospitals were enrolled. PHLF occurred in 147 patients (27.6%, 147/532). The PHLF-Net combining dual-modal ultrasound and clinical indicators demonstrated high effectiveness for predicting PHLF, with AUCs of 0.957 and 0.923 in the internal validation and testing sets, and AUCs of 0.950, 0.860, and 1.000 in the other three independent external testing sets. The performance of PHLF-Net outperformed models of single- and dual-modal US.

Conclusions

Preoperative ultrasound imaging combining clinical indicators can effectively predict the PHLF probability in patients with HCC. In the internal and external validation sets, PHLF-Net demonstrated its usefulness in predicting PHLF.

Open Research

Data Availability Statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Supporting Information

References

1Ocak I, Topaloglu S, Acarli K. Posthepatectomy liver failure. Turk J Med Sci 2020; 50: 1491–1503.
10.3906/sag-2006-31
CAS PubMed Web of Science® Google Scholar
2Baumgartner R, Engstrand J, Rajala P, et al. Comparing the accuracy of prediction models to detect clinically relevant post-hepatectomy liver failure early after major hepatectomy. Br J Surg 2024; 111: znad433.
10.1093/bjs/znad433
PubMed Google Scholar
3Soreide JA, Deshpande R. Post hepatectomy liver failure (PHLF) - recent advances in prevention and clinical management. Eur J Surg Oncol 2021; 47: 216–224.
10.1016/j.ejso.2020.09.001
PubMed Web of Science® Google Scholar
4Honmyo N, Kobayashi T, Kuroda S, et al. A novel model for predicting posthepatectomy liver failure based on liver function and degree of liver resection in patients with hepatocellular carcinoma. HPB (Oxford) 2021; 23: 134–143.
10.1016/j.hpb.2020.05.008
PubMed Web of Science® Google Scholar
5Yamamoto G, Taura K, Ikai I, et al. ALPlat criterion for the resection of hepatocellular carcinoma based on a predictive model of posthepatectomy liver failure. Surgery 2020; 167: 410–416.
10.1016/j.surg.2019.09.021
PubMed Web of Science® Google Scholar
6Thomas MN, Weninger E, Angele M, et al. Intraoperative simulation of remnant liver function during anatomic liver resection with indocyanine green clearance (LiMON) measurements. HPB (Oxford) 2015; 17: 471–476.
10.1111/hpb.12380
PubMed Web of Science® Google Scholar
7Peng Y, Shen H, Tang H, et al. Nomogram based on CT-derived extracellular volume for the prediction of post-hepatectomy liver failure in patients with resectable hepatocellular carcinoma. Eur Radiol 2022; 32: 8529–8539.
10.1007/s00330-022-08917-x
CAS PubMed Google Scholar
8Nilsson H, Karlgren S, Blomqvist L, Jonas E. The inhomogeneous distribution of liver function: possible impact on the prediction of post-operative remnant liver function. HPB (Oxford) 2015; 17: 272–277.
10.1111/hpb.12348
PubMed Web of Science® Google Scholar
9Wang Q, Wang A, Sparrelid E, et al. Predictive value of gadoxetic acid-enhanced MRI for posthepatectomy liver failure: a systematic review. Eur Radiol 2021; 32: 1792–1803.
10.1007/s00330-021-08297-8
PubMed Google Scholar
10Sofue K, Shimada R, Ueshima E, et al. Evaluation and prediction of post-hepatectomy liver failure using imaging techniques: value of gadoxetic acid-enhanced magnetic resonance imaging. Korean J Radiol 2024; 25: 24–32.
10.3348/kjr.2023.0507
PubMed Google Scholar
11Long H, Peng C, Ding H, et al. Predicting symptomatic post-hepatectomy liver failure in patients with hepatocellular carcinoma: development and validation of a preoperative nomogram. Eur Radiol 2023; 33: 7665–7674.
10.1007/s00330-023-09803-w
PubMed Google Scholar
12Long H, Zhong X, Su L, et al. Liver stiffness measured by two-dimensional shear wave Elastography for predicting symptomatic post-hepatectomy liver failure in patients with hepatocellular carcinoma. Ann Surg Oncol 2022; 29: 327–336.
10.1245/s10434-021-10563-4
PubMed Web of Science® Google Scholar
13Nishio T, Taura K, Koyama Y, et al. Prediction of posthepatectomy liver failure based on liver stiffness measurement in patients with hepatocellular carcinoma. Surgery 2016; 159: 399–408.
10.1016/j.surg.2015.06.024
PubMed Web of Science® Google Scholar
14Han H, Hu H, Xu YD, et al. Liver failure after hepatectomy: a risk assessment using the pre-hepatectomy shear wave elastography technique. Eur J Radiol 2017; 86: 234–240.
10.1016/j.ejrad.2016.11.006
PubMed Web of Science® Google Scholar
15Hu H, Han H, Han XK, Wang WP, Ding H. Nomogram for individualised prediction of liver failure risk after hepatectomy in patients with resectable hepatocellular carcinoma: the evidence from ultrasound data. Eur Radiol 2018; 28: 877–885.
10.1007/s00330-017-4900-2
PubMed Web of Science® Google Scholar
16Mayerhoefer ME, Materka A, Langs G, et al. Introduction to Radiomics. J Nucl Med 2020; 61: 488–495.
10.2967/jnumed.118.222893
CAS PubMed Web of Science® Google Scholar
17Sung YS, Park B, Park HJ, Lee SS. Radiomics and deep learning in liver diseases. J Gastroenterol Hepatol 2021; 36: 561–568.
10.1111/jgh.15414
PubMed Google Scholar
18Liu F, Liu D, Wang K, et al. Deep learning radiomics based on contrast-enhanced ultrasound might optimize curative treatments for very-early or early-stage hepatocellular carcinoma patients. Liver Cancer 2020; 9: 397–413.
10.1159/000505694
PubMed Web of Science® Google Scholar
19Lee I, Huang J, Chen T, et al. Evolutionary learning-derived clinical-radiomic models for predicting early recurrence of hepatocellular carcinoma after resection. Liver Cancer 2021; 10: 572–582.
10.1159/000518728
CAS PubMed Web of Science® Google Scholar
20Xue L, Jiang Z, Fu T, et al. Transfer learning radiomics based on multimodal ultrasound imaging for staging liver fibrosis. Eur Radiol 2020; 30: 2973–2983.
10.1007/s00330-019-06595-w
PubMed Web of Science® Google Scholar
21Rahbari NN, Garden OJ, Padbury R, et al. Posthepatectomy liver failure: a definition and grading by the International Study Group of Liver Surgery (ISGLS). Surgery 2011; 149: 713–724.
10.1016/j.surg.2010.10.001
PubMed Web of Science® Google Scholar
22Dietrich CF, Bamber J, Berzigotti A, et al. EFSUMB guidelines and recommendations on the clinical use of liver ultrasound elastography, update 2017 (long version). Ultraschall Med 2017; 38: e16–e47.
10.1055/s-0043-103952
PubMed Web of Science® Google Scholar
23Strasberg SM. Nomenclature of hepatic anatomy and resections: a review of the Brisbane 2000 system. J Hepato-Biliary-Pancreat Surg 2005; 12: 351–355.
10.1007/s00534-005-0999-7
PubMed Web of Science® Google Scholar
24Vogel A, Meyer T, Sapisochin G, Salem R, Saborowski A. Hepatocellular carcinoma. Lancet 2022; 400: 1345–1362.
10.1016/S0140-6736(22)01200-4
CAS PubMed Web of Science® Google Scholar
25Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. 2015.
Google Scholar
26Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016: 2818–2826.
Google Scholar
27He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016: 770–778.
Google Scholar
28Du R, Chang D, Bhunia AK, et al. Fine-grained visual classification via progressive multi-granularity training of jigsaw patches. arXiv:2003.03836. 2020.
Google Scholar
29Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database. In: CVPR: 2009 IEEE Conference on Computer Vision and Pattern Recognition, Vols 1–4; 2009: 248–255.
Google Scholar
30Zhuang Y, Ding H, Zhang Y, et al. Two-dimensional shear-wave elastography performance in the noninvasive evaluation of liver fibrosis in patients with chronic hepatitis B: comparison with serum fibrosis indexes. Radiology 2017; 283: 873–882.
10.1148/radiol.2016160131
PubMed Web of Science® Google Scholar
31Shen Y, Zhou C, Zhu G, et al. Liver stiffness assessed by shear wave elastography predicts postoperative liver failure in patients with hepatocellular carcinoma. J Gastrointest Surg 2017; 21: 1471–1479.
10.1007/s11605-017-3443-9
PubMed Web of Science® Google Scholar
32Nicolau C, Bianchi L, Vilana R. Gray-scale ultrasound in hepatic cirrhosis and chronic hepatitis: diagnosis, screening, and intervention. Semin Ultrasound CT MR 2002; 23: 3–18.
10.1016/S0887-2171(02)90026-0
PubMed Web of Science® Google Scholar
33Zheng X, Yao Z, Huang Y, et al. Deep learning radiomics can predict axillary lymph node status in early-stage breast cancer. Nat Commun 2020; 11: 1236.
10.1038/s41467-020-15027-z
CAS PubMed Web of Science® Google Scholar
34Yu J, Deng Y, Liu T, et al. Lymph node metastasis prediction of papillary thyroid carcinoma based on transfer learning radiomics. Nat Commun 2020; 11: 4807.
10.1038/s41467-020-18497-3
CAS PubMed Web of Science® Google Scholar

Volume43, Issue12

December 2024

Pages 2269-2280

Preoperative Ultrasound Radomics to Predict Posthepatectomy Liver Failure in Patients With Hepatocellular Carcinoma

Abstract

Purpose

Methods

Results

Conclusions

Open Research

Data Availability Statement

Supporting Information

References

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Preoperative Ultrasound Radomics to Predict Posthepatectomy Liver Failure in Patients With Hepatocellular Carcinoma

Abstract

Purpose

Methods

Results

Conclusions

Open Research

Data Availability Statement

Supporting Information

References

References

Related

Information