Modern methods of computer interpretation of abdominal radiography: Experience of application in diagnostics
DOI:
https://doi.org/10.63341/bmbr/2.2025.60Keywords:
abdominal emergencies, abdominal radiograph, visualisation quality, artificial intelligence, automated analysis, prognostic valueAbstract
The aim of the study was to assess the effectiveness of computer-based methods for interpreting abdominal radiographs in clinical diagnostics. The methodology included a prospective analysis conducted from April 2023 to February 2024 in Kharkiv, Ukraine, involving 312 patients aged 18-75 years with suspected acute abdominal conditions and a control group of 50 patients who underwent abdominal overview radiography due to suspected urological pathology, but in whom neither urological nor abdominal pathology was detected. Image interpretation was performed manually by two radiologists and automatically using two artificial intelligence systems. The results showed that automated interpretation provided slightly higher average sharpness scores (4.7 ± 0.3 vs 4.6 ± 0.4) and contrast (4.6 ± 0.4 vs 4.5 ± 0.5) compared to manual evaluation, as well as fewer artefacts (4.5 ± 0.5 vs 4.2 ± 0.6). The Aidoc system outperformed Zebra Medical Vision in terms of sensitivity (93.6% vs 89.1%), specificity (95.4% vs 94.7%), positive predictive value (91.8% vs 88.2%), and negative predictive value (96.7% vs 92.5%). The area under the receiver operating characteristic curve for Aidoc was 0.972, compared to 0.951 for Zebra Medical Vision. Kappa coefficients indicated higher consistency of Aidoc with expert assessments in diagnosing bowel obstruction (κ = 0.92 vs 0.88) and pneumoperitoneum (κ = 0.91 vs 0.85). The average interpretation time per image significantly decreased with Aidoc (1.4 ± 0.3 minutes) compared to manual analysis (6.8 ± 1.2 minutes) and Zebra Medical Vision (1.9 ± 0.4 minutes). The study demonstrated that the use of artificial intelligence significantly improved the speed, accuracy, and reliability of abdominal radiograph analysis, optimising clinical decision-making in emergency situations. The practical significance of the study lay in the potential to substantially reduce diagnostic time, increase the accuracy of detecting critical pathologies, and optimise healthcare facility resources in providing emergency care
Received: 25.12.2024 | Revised: 11.04.2025 | Accepted: 27.05.2025
References
Grechanyk O, Abdullaiev RY, Lurin I, Humeniuk K, Negoduiko V, Sliesarenko D. Modern aspects of diagnosis of the abdominal gun-shot woundings. Experience of a hybrid war in the East of Ukraine. Ukr J Clin Surg. 2021;88(5-6):42–52. DOI: 10.26779/2522-1396.2021.5-6.42
Stepanova H, Lupyna O. Implementing advanced X-ray technologies at the Third Cherkasy City Emergency Hospital. Curr Issues Mod Med Bull Ukr Med Dent Acad. 2024;24(2):218–25. DOI: 10.31718/2077-1096.24.2.218
Nehria N, Nehria Y, Bukharin T. Radiology during a war – Experience in Ukraine. RöFo. 2025;197(2):145–53. DOI: 10.1055/a-2326-7724
Reis E, Blankemeier L, Chaves J, Jensen M, Yao S, Truyts C, et al. Automated abdominal CT contrast phase detection using an interpretable and open-source artificial intelligence algorithm. Eur Radiol. 2024;34:6680–7. DOI: 10.1007/s00330-024-10769-6
Elek A, Ekizalioğlu D, Güler E. Evaluating Microsoft Bing with ChatGPT-4 for the assessment of abdominal computed tomography and magnetic resonance images. Diagn Interv Radiol. 2025;31(3):196–205. DOI: 10.4274/dir.2024.232680
Sato J, Sugimoto K, Suzuki Y, Wataya T, Kita K, Nishigaki D, et al. Annotation-free multi-organ anomaly detection in abdominal CT using free-text radiology reports: A multi-centre retrospective study. eBioMed. 2024. DOI: 10.1101/2024.06.10.24308633
Liu Z, Zhao H, Fang X, Huo D. Abdominal computed tomography localizer image generation: A deep learning approach. Comput Methods Programs Biomed. 2022;214:106575. DOI: 10.1016/j.cmpb.2021.106575
Blankemeier L, Cohen J, Kumar A, Van Veen D, Gardezi S, Paschali M, et al. Merlin: A vision language foundation model for 3D computed tomography. 2024. DOI: 10.21203/rs.3.rs-4546309/v1
The World Medical Association. Declaration of Helsinki: Ethical Principles for Medical Research Involving Human Subjects [Internet]. [cited 2025 July 5]. Available from: https://www.wma.net/what-we-do/medical-ethics/declaration-of-helsinki/
Pickhardt P, Graffy P, Perez A, Lubner M, Elton D, Summers R. Opportunistic screening at abdominal CT: Use of automated body composition biomarkers for added cardiometabolic value. Radiograph. 2021;41(2):524–42. DOI: 10.1148/rg.2021200056
Means K, Voges A, Ritter N. Students with access to 3D study materials are better able to translate spatial relationships between abdominal organs and correctly interpret abnormal radiographic images. Vet Radiol Ultrasound. 2023;64(3):521–9. DOI: 10.1111/vru.13217
Naik S, Mishra G, Tiwaskar S, Luharia A. Comparative analysis and assessment of radiological investigation reports for abdomen and pelvic computed tomography scans. 2023. DOI: 10.12688/f1000research.138957.1
Li W, Qu C, Chen X, Bassi P, Shi Y, Lai Y, et al. AbdomenAtlas: A large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking. Med Image Anal. 2024;97:103285. DOI: 10.1016/j.media.2024.103285
Xavier B, Chen P. Natural language processing for imaging protocol assignment: Machine learning for multiclass classification of abdominal CT protocols using indication text data. J Digit Imaging. 2022;35:1120-1130. DOI: 10.1007/s10278-022-00633-8
Hamghalam M, Moreland R, Gomez D, Simpson A, Lin H, Jandaghi A, et al. Machine learning detection and characterization of splenic injuries on abdominal computed tomography. Canadian Association of Radiologists Journal. 2024;75(3):534–41. DOI: 10.1177/08465371231221052
Kelm Z, Ron E, Olson M, Welle C, Johnson T, Boyum J. Concurrent chest and abdominal CT: Managing pitfalls of splitting interpretation by subspecialty. Radiograph. 2025;45(3):e240069. DOI: 10.1148/rg.240069
Glazer D, Budiawan E, Burk K, Shinagare A, Lacson R, Boland G, et al. Adoption of a diagnostic certainty scale in abdominal imaging: 2-year experience at an academic institution. Abdom Radiol. 2022;47:1187–95. DOI: 10.1007/s00261-021-03391-3
Stieger-Vanegas S, McKenzie E. Abdominal imaging in small ruminants: Liver, spleen, gastrointestinal tract, and lymph nodes. Vet Clin N Am Food Anim Pract. 2021;37(1), 55–74. DOI: 10.1016/j.cvfa.2020.10.001
Warner J, Hartman R, Blezek D, Thomas J. Abdominal and pelvic MRI protocol prediction using natural language processing. J Imaging Inf Med. 2025. DOI: 10.1007/s10278-025-01395-9
Kaur H, Kaur N, Neeru N. A comparative study of image enhancement algorithms for abdomen CT images. In: International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation. Gwalior: IEEE; 2024. P. 1–6. DOI: 10.1109/IATMSI60426.2024.10502768
Wolfe C, Halsey-Nichols M, Ritter K, McCoin N. Abdominal pain in the emergency department: How to select the correct imaging for diagnosis. Open Access Emerg Med. 2022;14:335–45. DOI: 10.2147/OAEM.S342724
Virarkar M, Jensen C, Klekers A, Wagner-Bartak N, Devine C, Lano E, et al. Clinical importance of second-opinion interpretations of abdominal imaging studies in a cancer hospital and its impact on patient management. Clin Imaging. 2022;86:13–9. DOI: 10.1016/j.clinimag.2022.03.014
Chhabra N, Christian E, Seseri V, George F, Rizvanolli L. Association of patient English proficiency and diagnostic imaging acquisition in emergency department patients with abdominal symptoms. J Emerg Med. 2023;65(3):172–9. DOI: 10.1016/j.jemermed.2023.05.020
Shaish H, Ream J, Huang C, Troost J, Gaur S, Chung R, et al. Diagnostic accuracy of unenhanced computed tomography for evaluation of acute abdominal pain in the emergency department. JAMA Surg. 2023;158(7):e231112. DOI: 10.1001/jamasurg.2023.1112
Hattori S, Yokota H, Takada T, Horikoshi T, Takishima H, Mikami W, et al. Impact of clinical information on CT diagnosis by radiologist and subsequent clinical management by physician in acute abdominal pain. Eur Radiol. 2021;31:5454–63. DOI: 10.1007/s00330-021-07700-8
Lee Y, Yoon S, Paek M, Han D, Choi M, Park S. Advanced MRI techniques in abdominal imaging. Abdom Radiol. 2024;49:3615–36. DOI: 10.1007/s00261-024-04369-7
Kaur H, Kaur N, Neeru N. Evolution of multiorgan segmentation techniques from traditional to deep learning in abdominal CT images – A systematic review. Disp. 2022;73:102223. DOI: 10.1016/j.displa.2022.102223
Moth A, Benning J, Glover J, Brown V, Pittock L, Woznitza N, et al. Concordance between a gastrointestinal consultant radiologist, a consultant radiologist and qualified reporting radiographers interpreting abdominal radiographs. Radiograp. 2023;29(2):408–15. DOI: 10.1016/j.radi.2022.12.008
Jain S, Sikka G, Dhir R. A systematic literature review on pancreas segmentation from traditional to non-supervised techniques in abdominal medical images. Artif Intell Rev. 2024;57:317. DOI: 10.1007/s10462-024-10966-1
Chen W, Zhang Y, Wu W, Yang H, Huang W. Machine learning-based predictive model for abdominal diseases using physical examination datasets. Comput Biol Med. 2024;173:108249. DOI: 10.1016/j.compbiomed.2024.108249
Cull J, Morrow D, Manasco C, Vaughan A, Eicken J, Smith H. A quality assessment tool for focused abdominal sonography for trauma examinations using artificial intelligence. J Trauma Acute Care Surg. 2024;98(1):111–6. DOI: 10.1097/TA.0000000000004425
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Bulletin of Medical and Biological Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
