Automated graded prognostic assessment for patients with hepatocellular carcinoma using machine learning.
Hepatocellular carcinoma
Machine learning
Magnetic resonance imaging
Medical image processing
Risk assessment
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
27 Mar 2024
27 Mar 2024
Historique:
received:
31
08
2023
accepted:
08
01
2024
revised:
18
12
2023
medline:
27
3
2024
pubmed:
27
3
2024
entrez:
27
3
2024
Statut:
aheadofprint
Résumé
Accurate mortality risk quantification is crucial for the management of hepatocellular carcinoma (HCC); however, most scoring systems are subjective. To develop and independently validate a machine learning mortality risk quantification method for HCC patients using standard-of-care clinical data and liver radiomics on baseline magnetic resonance imaging (MRI). This retrospective study included all patients with multiphasic contrast-enhanced MRI at the time of diagnosis treated at our institution. Patients were censored at their last date of follow-up, end-of-observation, or liver transplantation date. The data were randomly sampled into independent cohorts, with 85% for development and 15% for independent validation. An automated liver segmentation framework was adopted for radiomic feature extraction. A random survival forest combined clinical and radiomic variables to predict overall survival (OS), and performance was evaluated using Harrell's C-index. A total of 555 treatment-naïve HCC patients (mean age, 63.8 years ± 8.9 [standard deviation]; 118 females) with MRI at the time of diagnosis were included, of which 287 (51.7%) died after a median time of 14.40 (interquartile range, 22.23) months, and had median followed up of 32.47 (interquartile range, 61.5) months. The developed risk prediction framework required 1.11 min on average and yielded C-indices of 0.8503 and 0.8234 in the development and independent validation cohorts, respectively, outperforming conventional clinical staging systems. Predicted risk scores were significantly associated with OS (p < .00001 in both cohorts). Machine learning reliably, rapidly, and reproducibly predicts mortality risk in patients with hepatocellular carcinoma from data routinely acquired in clinical practice. Precision mortality risk prediction using routinely available standard-of-care clinical data and automated MRI radiomic features could enable personalized follow-up strategies, guide management decisions, and improve clinical workflow efficiency in tumor boards. • Machine learning enables hepatocellular carcinoma mortality risk prediction using standard-of-care clinical data and automated radiomic features from multiphasic contrast-enhanced MRI. • Automated mortality risk prediction achieved state-of-the-art performances for mortality risk quantification and outperformed conventional clinical staging systems. • Patients were stratified into low, intermediate, and high-risk groups with significantly different survival times, generalizable to an independent evaluation cohort.
Sections du résumé
BACKGROUND
BACKGROUND
Accurate mortality risk quantification is crucial for the management of hepatocellular carcinoma (HCC); however, most scoring systems are subjective.
PURPOSE
OBJECTIVE
To develop and independently validate a machine learning mortality risk quantification method for HCC patients using standard-of-care clinical data and liver radiomics on baseline magnetic resonance imaging (MRI).
METHODS
METHODS
This retrospective study included all patients with multiphasic contrast-enhanced MRI at the time of diagnosis treated at our institution. Patients were censored at their last date of follow-up, end-of-observation, or liver transplantation date. The data were randomly sampled into independent cohorts, with 85% for development and 15% for independent validation. An automated liver segmentation framework was adopted for radiomic feature extraction. A random survival forest combined clinical and radiomic variables to predict overall survival (OS), and performance was evaluated using Harrell's C-index.
RESULTS
RESULTS
A total of 555 treatment-naïve HCC patients (mean age, 63.8 years ± 8.9 [standard deviation]; 118 females) with MRI at the time of diagnosis were included, of which 287 (51.7%) died after a median time of 14.40 (interquartile range, 22.23) months, and had median followed up of 32.47 (interquartile range, 61.5) months. The developed risk prediction framework required 1.11 min on average and yielded C-indices of 0.8503 and 0.8234 in the development and independent validation cohorts, respectively, outperforming conventional clinical staging systems. Predicted risk scores were significantly associated with OS (p < .00001 in both cohorts).
CONCLUSIONS
CONCLUSIONS
Machine learning reliably, rapidly, and reproducibly predicts mortality risk in patients with hepatocellular carcinoma from data routinely acquired in clinical practice.
CLINICAL RELEVANCE STATEMENT
CONCLUSIONS
Precision mortality risk prediction using routinely available standard-of-care clinical data and automated MRI radiomic features could enable personalized follow-up strategies, guide management decisions, and improve clinical workflow efficiency in tumor boards.
KEY POINTS
CONCLUSIONS
• Machine learning enables hepatocellular carcinoma mortality risk prediction using standard-of-care clinical data and automated radiomic features from multiphasic contrast-enhanced MRI. • Automated mortality risk prediction achieved state-of-the-art performances for mortality risk quantification and outperformed conventional clinical staging systems. • Patients were stratified into low, intermediate, and high-risk groups with significantly different survival times, generalizable to an independent evaluation cohort.
Identifiants
pubmed: 38536464
doi: 10.1007/s00330-024-10624-8
pii: 10.1007/s00330-024-10624-8
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : National Institute of Health
ID : P30 KD034989
Organisme : National Institute of Health
ID : DDRCC DK034989-36
Informations de copyright
© 2024. The Author(s).
Références
Sung H, Ferlay J, Siegel RL et al (2021) Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 71:209–249
doi: 10.3322/caac.21660
pubmed: 33538338
Jemal A, Bray F, Center MM, Ferlay J, Ward E, Forman D (2011) Global cancer statistics. CA Cancer J Clin 61:69–90
doi: 10.3322/caac.20107
pubmed: 21296855
Siegel RL, Miller KD, Jemal A (2019) Cancer statistics, 2019. CA Cancer J Clin 69:7–34
doi: 10.3322/caac.21551
pubmed: 30620402
White DL, Thrift AP, Kanwal F, Davila J, El-Serag HB (2017) Incidence of hepatocellular carcinoma in All 50 United States, From 2000 Through 2012. Gastroenterology 152:812-820.e815
doi: 10.1053/j.gastro.2016.11.020
pubmed: 27889576
Perz JF, Armstrong GL, Farrington LA, Hutin YJ, Bell BP (2006) The contributions of hepatitis B virus and hepatitis C virus infections to cirrhosis and primary liver cancer worldwide. J Hepatol 45:529–538
doi: 10.1016/j.jhep.2006.05.013
pubmed: 16879891
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
Hamer OW, Schlottmann K, Sirlin CB, Feuerbach S (2007) Technology insight: advances in liver imaging. Nat Clin Pract Gastroenterol Hepatol 4:215–228
doi: 10.1038/ncpgasthep0766
pubmed: 17404589
Child CG, Turcotte JG (1964) Surgery and portal hypertension. Major Probl Clin Surg 1:1–85
pubmed: 4950264
Reig M, Forner A, Rimola J et al (2022) BCLC strategy for prognosis prediction and treatment recommendation: the 2022 update. J Hepatol 76:681–693
doi: 10.1016/j.jhep.2021.11.018
pubmed: 34801630
Yau T, Tang VY, Yao TJ, Fan ST, Lo CM, Poon RT (2014) Development of Hong Kong Liver Cancer staging system with treatment stratification for patients with hepatocellular carcinoma. Gastroenterology 146:1691–1700
doi: 10.1053/j.gastro.2014.02.032
pubmed: 24583061
Amin MB, Greene FL, Edge SB et al (2017) The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more “personalized” approach to cancer staging. CA Cancer J Clin 67:93–99
doi: 10.3322/caac.21388
pubmed: 28094848
Japan TLCSGo (1989) The general rules for the clinical and pathological study of primary liver cancer. Jpn J Surg 19:98–129
doi: 10.1007/BF02471576
Kudo M, Chung H, Osaki Y (2003) Prognostic staging system for hepatocellular carcinoma (CLIP score): its value and limitations, and a proposal for a new staging system, the Japan Integrated Staging Score (JIS score). J Gastroenterol 38:207–215
doi: 10.1007/s005350300038
pubmed: 12673442
Johnson PJ, Berhane S, Kagebayashi C et al (2015) Assessment of liver function in patients with hepatocellular carcinoma: a new evidence-based approach-the ALBI grade. J Clin Oncol 33:550–558
doi: 10.1200/JCO.2014.57.9151
pubmed: 25512453
Tacher V, Lin M, Duran R et al (2016) Comparison of existing response criteria in patients with hepatocellular carcinoma treated with transarterial chemoembolization using a 3D quantitative approach. Radiology 278:275–284
doi: 10.1148/radiol.2015142951
pubmed: 26131913
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
Gross M, Huber S, Arora S et al (2024) Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics. Eur Radiol. https://doi.org/10.1007/s00330-023-10495-5
Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS (2008) Random survival forests. Ann Appl Statist 2:841–860
doi: 10.1214/08-AOAS169
Crowley J, Mitchell A, Qu P, Morgan G, Barlogie B (2017) Optimal three group splits based on a survival outcome. Frontiers of Biostatistical Methods and Applications in Clinical Oncology:231–242. https://doi.org/10.1007/978-981-10-0126-0_14
Harrell FE Jr, Lee KL, Mark DB (1996) Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat Med 15:361–387
doi: 10.1002/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4
pubmed: 8668867
Blanche P, Dartigues JF, Jacqmin-Gadda H (2013) Estimating and comparing time-dependent areas under receiver operating characteristic curves for censored event times with competing risks. Stat Med 32:5381–5397
doi: 10.1002/sim.5958
pubmed: 24027076
Pyradiomics-community (February 11, 2020) pyradiomics Documentation Release v3.0. Available via https://pyradiomics.readthedocs.io/en/v3.0/features.html . Accessed 2023 Feb 24
Park T, Yoon MA, Cho YC et al (2022) Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy. Sci Rep 12:6735
doi: 10.1038/s41598-022-10807-7
pubmed: 35468985
pmcid: 9038736
Zhao Y, Zhao T, Chen S et al (2022) Fully automated radiomic screening pipeline for osteoporosis and abnormal bone density with a deep learning-based segmentation using a short lumbar mDixon sequence. Quant Imaging Med Surg 12:1198–1213
doi: 10.21037/qims-21-587
pubmed: 35111616
pmcid: 8739149
Kim KM, Sinn DH, Jung SH et al (2016) The recommended treatment algorithms of the BCLC and HKLC staging systems: does following these always improve survival rates for HCC patients? Liver Int 36:1490–1497
doi: 10.1111/liv.13107
pubmed: 26936471
Adhoute X, Penaranda G, Raoul JL, Bourliere M (2017) Usefulness of the MESH score in a European hepatocellular carcinoma cohort. World J Hepatol 9:711–714
doi: 10.4254/wjh.v9.i15.711
pubmed: 28596819
pmcid: 5440775
Zhao S, Wang M, Yang Z et al (2020) Comparison between Child-Pugh score and Albumin-Bilirubin grade in the prognosis of patients with HCC after liver resection using time-dependent ROC. Ann Transl Med 8:539
doi: 10.21037/atm.2020.02.85
pubmed: 32411762
pmcid: 7214905
op den Winkel M, Nagel D, Sappl J et al (2012) Prognosis of patients with hepatocellular carcinoma Validation and ranking of established staging-systems in a large western HCC-cohort. PLoS One 7:e45066
doi: 10.1371/journal.pone.0045066
pubmed: 23071507
pmcid: 3465308
Gui B, Weiner AA, Nosher J et al (2018) Assessment of the albumin-bilirubin (ALBI) grade as a prognostic indicator for hepatocellular carcinoma patients treated with radioembolization. Am J Clin Oncol 41:861–866
doi: 10.1097/COC.0000000000000384
pubmed: 28418940
pmcid: 5645222
Bai Y, Lian Y, Wu J et al (2021) A prognostic scoring system for predicting overall survival of patients with the TNM 8th edition stage I and II hepatocellular carcinoma after surgery: a population-based study. Cancer Manag Res 13:2131–2142
doi: 10.2147/CMAR.S289826
pubmed: 33688256
pmcid: 7936669
Parikh ND, Scaglione S, Li Y et al (2018) A comparison of staging systems for hepatocellular carcinoma in a multicenter US cohort. Clin Gastroenterol Hepatol 16:781–782
doi: 10.1016/j.cgh.2017.10.001
pubmed: 28987503
Mei J, Lin WP, Shi F et al (2021) Prognostic nomogram predicting survival of patients with unresectable hepatocellular carcinoma after hepatic arterial infusion chemotherapy. Eur J Radiol 142:109890
doi: 10.1016/j.ejrad.2021.109890
pubmed: 34375811
Liu Q, Li J, Liu F et al (2020) A radiomics nomogram for the prediction of overall survival in patients with hepatocellular carcinoma after hepatectomy. Cancer Imaging 20:82
doi: 10.1186/s40644-020-00360-9
pubmed: 33198809
pmcid: 7667801
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
Ji GW, Zhu FP, Xu Q et al (2019) Machine-learning analysis of contrast-enhanced CT radiomics predicts recurrence of hepatocellular carcinoma after resection: a multi-institutional study. EBioMedicine 50:156–165
doi: 10.1016/j.ebiom.2019.10.057
pubmed: 31735556
pmcid: 6923482