Development of a clinical decision support system for the diagnosis of space-occupying liver lesions using artificial intelligence methods

Aim. To develop an artificial intelligence-based system for the diagnosis of focal liver lesions aimed at supporting clinical decision-making in surgical hepatology.

Materials and methods. An artificial intelligence-based technological service was developed for the automatic segmentation and classification of contrast-enhanced computed tomography (CT) images of four types of liver lesions: focal nodular hyperplasia, carcinoma, hemangioma, and simple cyst. The service was trained and tested on datasets comprising 725 CT images using the nnU-Net architecture. Diagnostic performance was evaluated by calculating the AUC-ROC, sensitivity, specificity, and accuracy.

Results. The service achieved high performance metrics. The AUC-ROC ranged from 0.847 to 0.928, with a maximum sensitivity of 0.940 for carcinoma and a specificity of 0.900 for focal nodular hyperplasia. Accuracy ranged from 0.883 to 0.922, which demonstrates the algorithm's ability to clearly differentiate between malignant and benign lesions.

Conclusion. The machine learning-based service demonstrated high diagnostic performance and shows promise for integration into clinical practice, offering improved detection and classification of liver lesions.

1. Sung H., Ferlay J., Siegel R.L., Laversanne M., Soerjomataram I., Jemal A., Bray F. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers. CA Cancer J. Clin. 2021; 71 (3): 209–249. https://doi.org/10.3322/caac.21660

2. Akgül Ö., Çetinkaya E., Ersöz S., Tez M. Role of surgery in colorectal cancer liver metastases. World J. Gastroenterol. 2014; 20 (20): 6113–6122. https://doi.org/10.3748/wjg.v20.i20.6113

3. Chakedis J., Squires M.H., Beal E.W., Hughes T., Lewis H., Paredes A., Al-Mansour M., Sun S., Cloyd J.M., Pawlik T.M. Update on current problems in colorectal liver metastasis. Curr. Probl. Surg. 2017; 54 (11): 554–602. https://doi.org/10.1067/j.cpsurg.2017.10.002

4. Engstrand J., Nilsson H., Strömberg C., Jonas E., Freedman J. Colorectal cancer liver metastases – a population-based study on incidence, management and survival. BMC Cancer. 2018; 18 (1): 78. https://doi.org/10.1186/s12885-017-3925-x

5. Horn S.R., Stoltzfus K.C., Lehrer E.J., Dawson L.A., Tchelebi L., Gusani N.J., Sharma N.K., Chen H., Trifiletti D.M., Zaorsky N.G. Epidemiology of liver metastases. Cancer Epidemiol. 2020; 67: 101760. https://doi.org/10.1016/j.canep.2020.101760

6. Park H.J., Kim J.H., Choi S.Y., Lee E.S., Park S.J., Park J.H., Lee K.H. Radiomics and deep learning: hepatic applications. Korean J. Radiol. 2020; 21 (4): 387–401. https://doi.org/10.3348/kjr.2019.0752

7. Yasaka K., Akai H., Kunimatsu A., Kiryu S., Abe O. Deep learning with convolutional neural network in radiology. Jpn. J. Radiol. 2018; 36 (4): 257–272. https://doi.org/10.1007/s11604-018-0726-3

8. Hamm C.A., Wang C.J., Savic L.J., Ferrante M., Schobert I., Schlachter T., Lin M., Duncan J.S., Weinreb J.C., Chapiro J. Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phase CT images. Eur. Radiol. 2019; 29 (7): 3338–3347. https://doi.org/10.1007/s00330-018-5945-z

9. Chen J., Lu Y., Yu Q., Luo X., Adeli E., Wang Y., Lu L., Yuille A.L., Zhou Y. TransUNet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306. 2021. URL: https://arxiv.org/abs/2102.04306

10. Shirota M., Saito K., Sato Y., Matsuo Y., Takayama T. Evaluation of deep learning for segmentation of liver tumors in CT images. Med. Phys. 2021; 48 (1): 368–377. https://doi.org/10.1002/mp.14496

11. Doi K. Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput. Med. Imaging Graph. 2007; 31 (4–5): 198–211. https://doi.org/10.1016/j.compmedimag.2007.02.002

12. Chlebus G., Schenk A., Moltz J.H., van Ginneken B., Hahn H.K., Meine H. Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing. Sci. Rep. 2018; 8: 15497. https://doi.org/10.1038/s41598-018-33564-8

13. Esteva A., Kuprel B., Novoa R.A., Ko J., Swetter S.M., Blau H.M., Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542 (7639): 115–118. https://doi.org/10.1038/nature21056

14. Ahn S.J., Lee J.M., Chang W., Lee S.M., Yoon J.H. Liver imaging using deep learning: current status and future directions. Korean J. Radiol. 2021; 22 (2): 203–216. https://doi.org/10.3348/kjr.2020.0503

15. Liu M., Zeng W., Zhang Y., Wu X., Wang J. Liver tumor segmentation based on hybrid convolutional neural networks with dual feature fusion. Biomed. Signal Process. Control. 2021; 68: 102746. https://doi.org/10.1016/j.bspc.2021.102746

16. Krizhevsky A., Sutskever I., Hinton G.E. ImageNet classification with deep convolutional neural networks. Commun. ACM. 2017; 60 (6): 84–90. https://doi.org/10.1145/3065386

17. Wang K., Lu X., Zhou H., Gao Y., Zheng J., Tong M., Wu C., Liu C., Huang L., Meng X. Deep learning-based classification of hepatocellular carcinoma and cirrhotic nodules in multiphase CT images: a feasibility study. Eur. Radiol. 2019; 29 (7): 2899–2907. https://doi.org/10.1007/s00330-018-5894-6

18. Lambin P., Rios-Velazquez E., Leijenaar R., Carvalho S., van Stiphout R.G.P.M., Granton P., Zegers C.M.L., Gillies R., Boellard R., Dekker A., Aerts H.J.W.L. Radiomics: extracting more information from medical images using advanced feature analysis. Eur. J. Cancer. 2012; 48 (4): 441–446. https://doi.org/10.1016/j.ejca.2011.11.036

19. Gillies R.J., Kinahan P.E., Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016; 278 (2): 563–577. https://doi.org/10.1148/radiol.2015151169

20. Aerts H.J., Velazquez E.R., Leijenaar R.T.H., Parmar C., Grossmann P., Carvalho S., Bussink J., Monshouwer R., HaibeKains B., Rietveld D., Hoebers F., Rietbergen M.M., Leijenaar R.T.H. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat. Commun. 2014; 5: 4006. https://doi.org/10.1038/ncomms5006

21. Huo Y., Tang Y., Kim Y., Xu W., Wang Z., Wang X. CT segmentation of the liver and tumors from portal phase images using deep learning: a feasibility study. Med. Phys. 2019; 46 (11): 5129–5136. https://doi.org/10.1002/mp.13729

22. Liu F., Guan W., Tian J., Zhang Z., Wang X. Automatic detection and classification of focal liver lesions using deep learning algorithms: a feasibility study. Eur. Radiol. 2021; 31 (2): 966–975. https://doi.org/10.1007/s00330-020-07168-1

23. Haghshomar M., Rodrigues D., Kalyan A., Singh S., Han J., Romagnoli J., Cao J. Leveraging radiomics and AI for precision diagnosis and prognostication of liver malignancies. Front. Oncol. 2024; 14: 1362737. https://doi.org/10.3389/fonc.2024.1362737

24. Ronneberger O., Fischer P., Brox T. U-Net: convolutional networks for biomedical image segmentation. arXiv preprint arXiv:1505.04597. 2015. URL: https://arxiv.org/abs/1505.04597

25. Lu F., Wu F., Hu P., Peng Z., Kong D. Automatic 3D liver location and segmentation via convolutional neural network and graph cut. Int. J. Comput. Assist. Radiol. Surg. 2017; 12 (2): 171–182. https://doi.org/10.1007/s11548-016-1489-2

26. Çiçek Ö., Abdulkadir A., Lienkamp S.S., Brox T., Ronneberger O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. Med. Image Comp. Computer-Assisted Intervent. MICCAI 2016. 2016; 9901: 424–432. https://doi.org/10.1007/978-3-319-46723-8_49

27. Milletari F., Navab N., Ahmadi S.A. V-Net: fully convolutional neural networks for volumetric medical image segmentation. 2016 Fourth International Conference on 3D Vision (3DV). 2016: 565–571. https://doi.org/10.1109/3DV.2016.79

28. Isensee F., Jaeger P.F., Kohl S.A.A., Petersen J., Maier-Hein K.H. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods. 2021; 18 (2): 203–211. https://doi.org/10.1038/s41592-020-01008-z

29. Oktay O., Schlemper J., Le Folgoc L., Lee M., Heinrich M., Misawa K., Mori K., McDonagh S., Hammerla N.Y., Kainz B., Glocker B., Rueckert D. Attention U-Net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999. 2018. URL: https://arxiv.org/abs/1804.03999

30. Cao H., Wang Y., Chen J., Jiang D., Zhang X., Tian Q., Wang M. Swin-Unet: Unet-like pure transformer for medical image segmentation. arXiv preprint arXiv:2105.05537. 2021. URL: https://arxiv.org/abs/2105.05537

31. Dostovalova A.M., Gorshenin A.K., Starichkova J.V., Arzamasov K.M. Comparative analysis of modifications of U-Net neural network architectures in the problem of medical image segmentation. Digital Diagnostics. 2024; 5 (4): 833–853. https://doi.org/10.17816/DD629866 (In Russian)

32. Bobrovskaya T.M., Vasiliev Yu.A., Nikitin N.Yu., Arzamasov K.M. Approaches to building radiology datasets. Medical Doctor and Information Technology. 2023; 4: 14–23. https://doi.org/10.25881/18110193_2023_4_14 (In Russian)

33. Vasiliev Yu.A., Arzamasov K.M., Vladzimirskiy A.V., Omelyanskaya O.V., Bobrovskaya T.M., Sharova D.E., Nikitin N.Yu., Kodenko M.R. Podgotovka nabora dannyh dlya obucheniya i testirovaniya programmnogo obespecheniya na osnove tekhnologii iskusstvennogo intellekta. Ridero: Nauchnoprakticheskij klinicheskij centr diagnostiki i telemedicinskih tekhnologij Departamenta zdravoohraneniya goroda Moskvy [Preparation of a dataset for training and testing software based on artificial intelligence technology].* Ridero: Center for Diagnostics and Telemedicine. 2024. 140 p. ISBN 978-5-0062-1244-2. (In Russian)

34. Vasiliev Yu.A., Arzamasov K.M., Pestrenin L.D. et al. Svidetel'stvo o gosudarstvennoj registracii bazy dannyh № 2024625817 Rossijskaya Federaciya. MosMedData: KT organov bryushnoj polosti, dopolnennaya segmentaciej pecheni [Certificate of State Registration of a Database No. 2024625817, Russian Federation. MosMedData: Abdominal CT scans with liver segmentation – No. 2024625742]. Application filed: 02.12.2024. Published: 06.12.2024 / Applicant: Center for Diagnostics and Telemedicine. (In Russian)

35. Vasiliev Yu.A., Arzamasov K.M., Pestrenin L.D. et al. Svidetel'stvo o gosudarstvennoj registracii bazy dannyh № 2024626116 Rossijskaya Federaciya. MosMedData: KT s nalichiem i otsutstviem priznakov obrazovanij pecheni i ih segmentaciej: № 2024626028 [Certificate of State Registration of a Database No. 2024626116, Russian Federation. MosMedData: CT scans with and without signs of liver lesions and their segmentation – No. 2024626028]. Application filed: 13.12.2024. Published: 18.12.2024; Applicants: Center for Diagnostics and Telemedicine, Botkin Hospital. (In Russian).