The Capabilities of Machine Learning Radiomics Based Models in the MRI Diagnosis of Early HCC
I. V. Molostova,
B. M. Medvedeva,
E. V. Kondratyev,
A. A. Ustalov,
M. S. Novruzbekov,
O. D. Olisov,
V. M. Tarnoposky https://doi.org/10.37174/2587-7593-2024-7-4-68-73
Abstract
Purpose: To evaluate machine-learning radiomics based models on enhanced MR images in diagnostics of early HCC.
Material and methods: Data from 72 patients with 93 masses who underwent Gadoxetic acid-enhanced MRI scans was retrospectively analyzed.
Results: Binary classification models were produced for the differential diagnosis of regenerative and dysplastic nodes, early HCC and HCC nodes with an atypical enhancement with high discriminatory capabilities; the area under the ROC-curve ranged from 0.89 to 0.95 in various models.
Conclusion: The performed radiomic models can be used as an effective method for differential diagnostics of HCC with typical and atypical enhancement, dysplastic and regenerative nodes.
About the Authors
I. V. Molostova
N.N. Blokhin National Medical Research Center of Oncology, Russian Ministry of Health
Russian Federation
Competing Interests:
Russian Federation
Molostova Iuliia Viktorovna
tel: 8916091148
24 Kashirskoe shosse, Moscow, 115478, Russia
Competing Interests:
Conflict of interests. Not declared
B. M. Medvedeva
N.N. Blokhin National Medical Research Center of Oncology, Russian Ministry of Health
Russian Federation
Competing Interests:
Russian Federation
24 Kashirskoe shosse, Moscow, 115478, Russia
Competing Interests:
Conflict of interests. Not declared
E. V. Kondratyev
A. V. Vishnevsky National Medical Research Center of Surgery
Russian Federation
Competing Interests:
Russian Federation
27 Bolshaya Serpukhovskaya Moscow, 115093, Russia
Competing Interests:
Conflict of interests. Not declared
A. A. Ustalov
A. V. Vishnevsky National Medical Research Center of Surgery
Russian Federation
Competing Interests:
Russian Federation
27 Bolshaya Serpukhovskaya Moscow, 115093, Russia
Competing Interests:
Conflict of interests. Not declared
M. S. Novruzbekov
N.V. Sklifosovsky Research Institute for Emergency Medicine
Russian Federation
Competing Interests:
Russian Federation
3 Bolshaya Suharevskaya ploshad, Moscow, 129090, Russia
Competing Interests:
Conflict of interests. Not declared
O. D. Olisov
N.V. Sklifosovsky Research Institute for Emergency Medicine
Russian Federation
Competing Interests:
Russian Federation
3 Bolshaya Suharevskaya ploshad, Moscow, 129090, Russia
Competing Interests:
Conflict of interests. Not declared
V. M. Tarnoposky
S.S. Yudin State Clinical Hospital
Russian Federation
Competing Interests:
Russian Federation
18A building 7 Zagorodnoe shosse, Moscow, 117152, Russia
Competing Interests:
Conflict of interests. Not declared
References
1. Siegel RL, Miller KD, Fuchs HE, et al. Cancer Statistics. 2021. CA Cancer J Clin. 2021;71(1):7-33. https://doi.org/10.3322/caac.21669
2. Roberts LR, Sirlin CB, Zaiem F, et al. Imaging for the diagnosis of hepatocellular carcinoma: A systematic review and meta-analysis. Hepatology. 2018;67(1):401-21. https://doi.10.1002/hep.29487
3. Marrero JA, Kulik LM, Sirlin CB, et al. Diagnosis, Staging, and Management of Hepatocellular Carcinoma: 2018 Practice Guidance by the American Association for the Study of Liver Diseases. Hepatology. 2018;68(2):723-50. https://doi.10.1002/hep.29913
4. EASL Clinical Practice Guidelines: Management of hepatocellular carcinoma. J Hepatol. 2018;69(1):182-236. https://doi.10.1016/j.jhep.2018.03.019.
5. Motosugi U, Bannas P, Sano K, Reeder SB. Hepatobiliary MR contrast agents in hypovascular hepatocellular carcinoma. J Magn Reson Imaging. 2015;41(2):251-65. https://doi.10.1002/jmri.24712.
6. Karmazanovsky GG, Kondratyev EV, Gruzdev IS, et al. Radiation diagnostics and intelligent personalized technologies in hepatopancreatology Bulletin of RMAS. 2022;77(4):245-53 (In Russ.) https://doi.10.15690/vramn2053
7. Mirestean CC, Pagute O, Buzea C, et al. Radiomic Machine Learning and Texture Analysis — New Horizons for Head and Neck Oncology. Maedica (Bucur). 2019;14(2):126-30. https://doi.10.26574/maedica.2019.14.2.126
8. Sagir Kahraman A. Radiomics in Hepatocellular Carcinoma. J Gastrointest Cancer. 2020;51(4):1165-8. https://doi.10.1007/s12029-020-00493-x
9. Masokano IB, Liu W, yie S, et al. The application of texture quantification in hepatocellular carcinoma using CT and MRI: a review of perspectives and challenges. Cancer Imaging. 2020;20(1):67. https://doi.10.1186/s40644-020-00341-y
10. Zwanenburg A, Valliğres M, Abdalah MA, et al. The Image Biomarker Standardization Initiative: Standardized Yuantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020;295(2):328-38. https://doi.10.1148/radiol.2020191145
11. Breiman L. Random forests. Machine Learning. 2001;45:5-32. https://doi.10.1023/A:1010933404324
12. Lee CS, Cheang PYS, Moslehpour M. Predictive Analytics in Business Analytics: Decision Tree. Advances in Decision Sciences. 2022;26:1-29. https://doi.10.47654/v26y2022i1p1-30
13. Connelly L. Logistic regression. MEDSURG Nursing 2020;29:353-4. https://doi.10.56687/9781847423399-016
14. BentĠjac C, CsƂrgƅ A, Marơnez-MuŹoz G. A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review. 2021;54:1937-67. https://doi. 10.1007/s10462-020-09896-5
15. Cortes C, Vapnik V. Support-Vector Networks. Machine Learning. 1995;20:273-97. https://doi. 10.1023/A:1022627411411
16. Cunningham P, Delany SK. Nearest Neighbour Classifiers A Tutorial. ACM Computing Surveys. 2021;54. https://doi. 10.1145/3459665
17. Breder VV, Balakhnin PV, Virshke ER, et al. Practical recommendations for medicinal treatment for individual patients with hepatocellular cancer. Malignant Tumors. 2020;10(3s2-1):450-69. (In Russ.) https://doi.10.18027/2224-5057-2020-10-3s2-25
18. EASL Clinical Practice Guidelines: Management of hepatocellular carcinoma published correction appears in J Hepatol. 2019;70(4):817. doi: 10.1016/j.jhep.2019.01.020. J Hepatol. 2018;69(1):182-236. https://doi.10.1016/j.jhep.2018.03.019
19. Chou R, Cuevas C, Fu R, et al. Imaging Techniques for the Diagnosis and Staging of Hepatocellular Carcinoma. Rockville (MD): Agency for Healthcare Research and Yuality (US). 2014.
20. Medvedeva BM, Molostova YuV, Lapteva MG. Diagnostic Value of Gadoxetic Acid-Enhanced MRI for Differential Diagnosis of Rare Types of Hepatocellular Carcinoma. Journal of Oncology: Diagnostic Radiology and Radiotherapy. 2024;7(3):54-61. (In Russ.) https://doi. 10.37174/2587-7593-2024-7-3-54-61
21. Feng B, Ma yH, Wang S, et al. Application of artificial intelligence in preoperative imaging of hepatocellular carcinoma: Current status and future perspectives. World J Gastroenterol. 2021;27(32):5341-50. https://doi. 10.3748/wjg.v27.i32.5341.
22. Jiang H, Liu y, Chen J, et al. Man or machine͍ Cancer Imaging. 2019;19:84. https://doi. 10.1186/s40644-019-0266-9.
23. Zhen SH, Cheng M, Tao YB, et al. Deep Learning for Accurate Diagnosis of Liver Tumor Based on Magnetic Resonance Imaging and Clinical Data. Front Oncol. 2020;10:680. https://doi.10.3389/fonc.2020.00680.
24. Kitao A, Matsui O, Yoneda N, et al. The uptake transporter OATP8 expression decreases during multistep hepatocarcinogenesis: correlation with gadoxetic acid enhanced MR imaging. Eur Radiol. 2011;21(10):2056-66. https://doi.10.1007/s00330-011-2165-8
Review
For citations:
Molostova I.V., Medvedeva B.M., Kondratyev E.V., Ustalov A.A., Novruzbekov M.S., Olisov O.D., Tarnoposky V.M. The Capabilities of Machine Learning Radiomics Based Models in the MRI Diagnosis of Early HCC. Journal of oncology: diagnostic radiology and radiotherapy. 2024;7(4):68-73. (In Russ.) https://doi.org/10.37174/2587-7593-2024-7-4-68-73
Views:
172
Email this article 