Keywords
chronic diffuse liver diseases
liver fibrosis
ultrasound diagnostics
echography
artificial intelligence
interpretability
selective classification
medical triage
How to Cite
Abstract
Introduction. Standard two-dimensional B-mode liver ultrasound is the most accessible modality for primary diagnosis; however, its conventional visual interpretation in pediatric chronic diffuse liver diseases is limited by subjectivity and low sensitivity to early-stage fibrosis. Shear wave elastography requires specialized equipment and is frequently unavailable in primary care settings. The development of interpretable artificial intelligence (AI) tools for objective computer-aided analysis of echograms enables automated patient triage and rational identification of priority cohorts for referral to liver elastography.
Aim. To evaluate the diagnostic performance and clinical interpretability of a developed AI-based computer tool designed for the automated triage of children with chronic diffuse liver diseases prior to elastographic examination.
Materials and methods: In a retrospective single-center study, the clinical echogram archive of 105 children aged 5–18 years was analyzed. The total dataset comprised 661 regions of interest (ROIs) extracted from 337 two-dimensional B-mode ultrasound images acquired via expert-class ultrasound systems. Two-dimensional shear wave elastography (2D-SWE) served as the reference standard (stratification into stages F0 vs. F1–F4 based on verified kPa thresholds). A logistic regression model was trained using local grayscale intensity profiles (32 bins) to construct spatial local-support maps and compute an integrated patient score. Validation was performed using a 5-fold cross-validation scheme configured to strictly prevent data leakage (patient-level splitting). Additionally, a selective classification analysis was conducted by introducing an indeterminate/uncertainty zone (rejection option) for equivocal cases.
Results. In the binary task of differentiating normal tissue (F0) from fibrotic changes (F1–F4) at the patient level, the model achieved an area under the ROC curve (AUC) of 0.91 [95% confidence interval: 0.84–0.96], a balanced accuracy of 0.83 [0.76–0.90], a sensitivity of 0.80 [0.68–0.91], and a specificity of 0.86 [0.77–0.95] at a standard operating threshold of 0.50. Implementing a screening threshold of 0.32 increased the sensitivity for detecting fibrotic changes to 0.91. Exploratory selective classification analysis revealed that routing equivocal cases to the indeterminate category captured 15 out of 17 (88%) baseline model errors. After filtering out these indeterminate cases, the balanced accuracy on the retained subset of patients increased to 0.90, and specificity reached 1.00 with a sensitivity of 0.80.
Conclusions. The developed intelligent method provides high triage accuracy for children requiring subsequent elastographic fibrosis stratification. Spatial local-support maps render the model's logic clinically interpretable for clinicians by providing a visual explanation of the calculated score. While the selective classification method effectively routes equivocal cases to an expert review zone, the low coverage (only 31.4% of patients remained outside the indeterminate zone) limits its utility as a standalone screening tool.
References
Younossi, Z. M., Golabi, P., Paik, J. M., Henry, A., Van Dongen, C., & Henry, L. (2023). The global epidemiology of nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH): A systematic review. Hepatology, 77(4), 1335–1347. https://doi.org/10.1002/hep.32723
Hofstraat, S. H. I., Falla, A. M., Duffell, E. F., Hahné, S. J. M., Amato-Gauci, A. J., Veldhuijzen, I. K., & Tavoschi, L. (2017). Current prevalence of chronic hepatitis B and C virus infection in the general population, blood donors and pregnant women in the EU/EEA: A systematic review. Epidemiology and Infection, 145(14), 2873–2885. https://doi.org/10.1017/S0950268817001947
European Association for the Study of the Liver. (2021). EASL Clinical Practice Guidelines on non-invasive tests for evaluation of liver disease severity and prognosis. Journal of Hepatology, 75(3), 659–689. https://doi.org/10.1016/j.jhep.2021.05.025
Rockey, D. C., Caldwell, S. H., Goodman, Z. D., Nelson, R. C., & Smith, A. D. (2009). Liver biopsy. Hepatology, 49(3), 1017–1044. https://doi.org/10.1002/hep.22742
Singh, S., Venkatesh, S. K., Wang, Z., Miller, F. H., Motosugi, U., Low, R. N., Hassanein, T., Asbach, P., Godfrey, E. M., Yin, M., Chen, J., Keaveny, A. P., Bridges, M., Bohte, A., Murad, M. H., Lomas, D. J., Talwalkar, J. A., & Ehman, R. L. (2015). Diagnostic performance of magnetic resonance elastography in staging liver fibrosis: A systematic review and meta-analysis of individual participant data. Clinical Gastroenterology and Hepatology, 13(3), 440–451.e6. https://doi.org/10.1016/j.cgh.2014.09.046
Friedrich-Rust, M., Ong, M. F., Martens, S., Sarrazin, C., Bojunga, J., Zeuzem, S., & Herrmann, E. (2008). Performance of transient elastography for the staging of liver fibrosis: A meta-analysis. Gastroenterology, 134(4), 960–974. https://doi.org/10.1053/j.gastro.2008.01.034
Barr, R. G., Wilson, S. R., Rubens, D., Garcia-Tsao, G., & Ferraioli, G. (2020). Update to the Society of Radiologists in Ultrasound liver elastography consensus statement. Radiology, 296(2), 263–274. https://doi.org/10.1148/radiol.2020192437
Xiao, G., Zhu, S., Xiao, X., Yan, L., Yang, J., & Wu, G. (2017). Comparison of laboratory tests, ultrasound, or magnetic resonance elastography to detect fibrosis in patients with nonalcoholic fatty liver disease: A meta-analysis. Hepatology, 66(5), 1486–1501. https://doi.org/10.1002/hep.29302
Liu, Z., Huang, B., Wen, H., Lu, Z., Huang, Q., Jiang, M., Dong, C., Liu, Y., Chen, X., & Lin, H. (2023). Automatic diagnosis of significant liver fibrosis from ultrasound B-mode images using a handcrafted-feature-assisted deep convolutional neural network. IEEE Journal of Biomedical and Health Informatics, 27(10), 4938–4949. https://doi.org/10.1109/JBHI.2023.3295078
Lee, J. H., Joo, I., Kang, T. W., Paik, Y. H., Sinn, D. H., Ha, S. Y., Kim, K., Choi, C., Lee, G., Yi, J., & Bang, W. C. (2020). Deep learning with ultrasonography: Automated classification of liver fibrosis using a deep convolutional neural network. European Radiology, 30(2), 1264–1273. https://doi.org/10.1007/s00330-019-06407-1
Li, J., Qureshi, M., Gupta, A., Anderson, S. W., Soto, J., & Li, B. (2019). Quantification of degree of liver fibrosis using fibrosis area fraction based on statistical chi-square analysis of heterogeneity of liver tissue texture on routine ultrasound images. Academic Radiology, 26(8), 1001–1007. https://doi.org/10.1016/j.acra.2018.10.004
Wang, K., Lu, X., Zhou, H., Gao, Y., Zheng, J., Tong, M., Wu, C., Liu, C., Huang, L., Jiang, T., Meng, F., Lu, Y., Ai, H., Xie, X.-Y., Yin, L., Liang, P., Tian, J., & Zheng, R. (2019). Deep learning radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: A prospective multicentre study. Gut, 68(4), 729–741. https://doi.org/10.1136/gutjnl-2018-316204
Bossuyt, P. M., Reitsma, J. B., Bruns, D. E., Gatsonis, C. A., Glasziou, P. P., Irwig, L., Lijmer, J. G., Moher, D., Rennie, D., de Vet, H. C. W., Kressel, H. Y., Rifai, N., Golub, R. M., Altman, D. G., Hooft, L., Korevaar, D. A., Cohen, J. F., & STARD Group. (2015). STARD 2015: An updated list of essential items for reporting diagnostic accuracy studies. BMJ, 351, h5527. https://doi.org/10.1136/bmj.h5527
Collins, G. S., Moons, K. G. M., Dhiman, P., Riley, R. D., Beam, A. L., Van Calster, B., Ghassemi, M., Liu, X., Reitsma, J. B., van Smeden, M., Boulesteix, A.-L., Camaradou, J. C., Celi, L. A., Denaxas, S., Denniston, A. K., Glocker, B., Golub, R. M., Harvey, H., Heinze, G., Hoffman, M. M., Kengne, A. P., Lam, E., Lee, N., Loder, E. W., Maier-Hein, L., Mateen, B. A., McCradden, M. D., Oakden-Rayner, L., Ordish, J., Parnell, R., Rose, S., Singh, K., Wynants, L., & Logullo, P. (2024). TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ, 385, e078378. https://doi.org/10.1136/bmj-2023-078378
Babenko, V. O., Nastenko, Ye. A., Solodushchenko, V. V., Pavlov, V. A., & Dykan, I. M. (2024). Iierarkhichnyi alhorytm multyklasyfikatsii stadii fibrozu pechinky z intehrovanym analizom oblastei interesu. Biomedical Engineering and Technology, 14(2). https://doi.org/10.20535/2617-8974.2024.14.301108
Babenko, V. O., Solodushchenko, V. V., Dyba, M. B., Hloba, M. V., & Tarasiuk, B. A. (2026). Efektyvnist multyparametrychnoi ultrazvukovoi diahnostyky z prohramamy shtuchnoho intelektu pry dyfuznykh zakhvoriuvanniakh pechinky u ditei. Clinical and Preventive Medicine, 1(47), 104–112. https://doi.org/10.31612/2616-4868.1.2026.13
Tran, L. C., Ley, D., Bourdon, G., Coopman, S., Lerisson, H., Tillaux, C., Béhal, H., Gottrand, F., & Aumar, M. (2022). Noninvasive pediatric liver fibrosis measurement: Two-dimensional shear wave elastography compared with transient elastography. Frontiers in Pediatrics, 10, 849815. https://doi.org/10.3389/fped.2022.849815
Dyba, M. B., & Berezenko, V. S. (2023). Mozhlyvosti elastohrafii zsuvnoi khvyli v diahnostytsi fibrozu pechinky ta monitorynhu autoimunnykh zakhvoriuvan pechinky u ditei. Modern Pediatrics. Ukraine, 8(136), 34–41. https://doi.org/10.15574/SP.2023.136.34
Dietrich, C. F., Ferraioli, G., Sirli, R., Popescu, A., Sporea, I., Pienar, C., Kunze, C., Taut, H., Schrading, S., Bota, S., Schreiber-Dietrich, D., Fang, C., & Yi, D. (2019). General advice in ultrasound based elastography of pediatric patients. Medical Ultrasonography, 21(3), 315–326. https://doi.org/10.11152/mu-2063
Ferraioli, G., Barr, R. G., Berzigotti, A., Sporea, I., Wong, V. W.-S., Reiberger, T., Karlas, T., Thiele, M., Cardoso, A. C., Ayonrinde, O. T., Castera, L., Dietrich, C. F., Iijima, H., Lee, D. H., Kemp, W., Oliveira, C. P., & Sarin, S. K. (2024). WFUMB Guideline/Guidance on Liver Multiparametric Ultrasound: Part 1. Update to 2018 Guidelines on Liver Ultrasound Elastography. Ultrasound in Medicine & Biology, 50(8), 1071–1087. https://doi.org/10.1016/j.ultrasmedbio.2024.03.013
Nastenko, I., Maksymenko, V., Potashev, S., Pavlov, V., Babenko, V., Rysin, S., Matviichuk, O., & Lazoryshinets, V. (2021). Random Forest Algorithm Construction for the Diagnosis of Coronary Heart Disease Based on Echocardiography Video Data Streams. Innovative Biosystems and Bioengineering, 5(1), 61–69. https://doi.org/10.20535/ibb.2021.5.1.225794
Petrunina, O., Shevaga, D., Babenko, V., Pavlov, V., Rysin, S., & Nastenko, I. (2021). Comparative Analysis of Classification Algorithms in the Analysis of Medical Images From Speckle Tracking Echocardiography Video Data. Innovative Biosystems and Bioengineering, 5(3), 153–166. https://doi.org/10.20535/ibb.2021.5.3.234990
Zwanenburg, A., Vallières, M., Abdalah, M. A., Aerts, H. J. W. L., Andrearczyk, V., Apte, A., Ashrafinia, S., Bakas, S., Beukinga, R., Boellaard, R., Bogowicz, M., Boldrini, L., Buvat, I., Cook, G. J. R., Davatzikos, C., Depeursinge, A., Desseroit, M.-C., Dinapoli, N., Dinh, C. V., Echegaray, S., Lambin, P., Leijenaar, R. T. H., & van Griethuysen, J. (2020). The image biomarker standardization initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology, 295(2), 328–338. https://doi.org/10.1148/radiol.2020191145
van Griethuysen, J. J. M., Fedorov, A., Parmar, C., Hosny, A., Aucoin, N., Narayan, V., Beets-Tan, R. G. H., Fillion-Robin, J.-C., Pieper, S., & Aerts, H. J. W. L. (2017). Computational radiomics system to decode the radiographic phenotype. Cancer Research, 77(21), e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.