Download PDF
CC BY 4.0 · Journal of Gastrointestinal and Abdominal Radiology
DOI: 10.1055/s-0043-1778672
Original Article

Hemoperitoneum Quantification in Non-contrast CT: Evaluating Feasibility with the Novel HUVAO Segmentation Algorithm

Rahul Bhagawati
1   Department of Biosciences and Bioengineering, Indian Institute of Technology Guwahati, North Guwahati, Assam, India
,
Suman Hazarika
2   Division of CT, MRI, and Conventional Radiology, Apollo Hospitals Guwahati, Guwahati, Assam, India
,
Cota Navin Gupta
1   Department of Biosciences and Bioengineering, Indian Institute of Technology Guwahati, North Guwahati, Assam, India
,
Souptick Chanda
1   Department of Biosciences and Bioengineering, Indian Institute of Technology Guwahati, North Guwahati, Assam, India
3   Mehta Family School of Data Science and Artificial Intelligence, Indian Institute of Technology Guwahati, North Guwahati, Assam, India
› Author Affiliations Funding None.
› Further Information
   Permissions and Reprints

Abstract

Background Injuries involving substantial bleeding, frequently encountered in victims of road traffic accidents, pose a significant risk to mortality. For abdominal trauma cases, accurately assessing internal bleeding and hematomas becomes crucial. Detecting hemoperitoneum, which indicates both blood loss and organ damage in the abdominal cavity, requires precise evaluation. Timely diagnosis and quantification of hemoperitoneum following road accidents are crucial during the critical golden hour, enabling prioritized medical intervention and potentially saving lives while enhancing overall patient care. However, achieving precise hemoperitoneum quantification in abdominal trauma faces challenges due to the intricate nature of overlapping Hounsfield unit (HU) regions.

Methods In this feasibility study, we sought to assess the efficacy of the novel HUVAO (Hounsfield Unit-based Volume quantification of Asymmetrical Objects) segmentation algorithm for quantifying hemoperitoneum in thoracoabdominal non-contrast computed tomography (CT) images. Using 28 retrospective non-contrast CT scans of thoracoabdominal regions from trauma patients, we analyzed crucial imaging data without necessitating additional scans or contrast-enhanced procedures. The study aimed to compare HUVAO against classical algorithms and visual estimations by trained radiologists for hemoperitoneum segmentation in thoracoabdominal non-contrast CT images.

Results Our findings revealed that although the technical feasibility of employing HUVAO and other segmentation algorithms for hemoperitoneum quantification is evident, the outcomes derived from these algorithms display notable discrepancies.

Conclusion In assessing technical feasibility, we introduced the HUVAO segmentation algorithm for hemoperitoneum quantification, comparing its performance against classical segmentation algorithms and visual estimations from trained radiologists. While our results affirm the technical feasibility of HUVAO for this purpose, the observed variations underscore the task's inherent complexity. This emphasizes the limitations of relying solely on HU-based detection, advocating for integration with clinical data. This insight urges exploration of advanced techniques to boost accuracy and elevate patient care standards.

Keywords

hemoperitoneum - CT scan - image processing - Hounsfield units (HU) - voxel segmentation - trauma care

Ethical Approval Statement

The present study utilized computed tomography (CT) data sourced from the data archive of the hospital. It is important to note that the data used in this study had previously served to diagnose and treat other medical conditions, making the study inherently retrospective.




Publication History

Article published online:
16 January 2024

© 2024. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/)

Thieme Medical and Scientific Publishers Pvt. Ltd.
A-12, 2nd Floor, Sector 2, Noida-201301 UP, India

 

  • References

  • 1 ROAD ACCIDENTS IN INDIA. 2022. morth.nic.in. Accessed November 16, 2023 at: https://morth.nic.in/sites/default/files/RA_2022_30_Oct.pdf
  • 2 ADSI-2021 | Accidental Deaths & Suicides in India Year Wise. ncrb.gov.in. at: https://ncrb.gov.in/accidental-deaths-suicides-in-india-year-wise.html
  • 3 Sahu MR, Mohanty MK, Sasmal PK. et al. Epidemiology and patterns of road traffic fatalities in India pre- and post-motor vehicle (Amendment) act 2019: an autopsy-based study. Int J Crit Illn Inj Sci 2021; 11 (04) 198-203
    CrossrefPubMedGoogle Scholar
  • 4 Road accidents in India - statistics & facts. Statista. Accessed December 26, 2023 at: https://www.statista.com/topics/5982/road-accidents-in-india/
  • 5 Wikipedia Contributors. Golden hour (medicine). Wikipedia. Published January 2, 2019. Accessed December 26, 2023 at: https://en.wikipedia.org/wiki/Golden_hour_(medicine)
  • 6 Johnson AB, Waheed A, Burns B. Hemorrhage. NIH.gov. Published May 29, 2019. Accessed December 26, 2023 at: https://www.ncbi.nlm.nih.gov/books/NBK542273/
  • 7 Federle MP, Jeffrey Jr RB. Hemoperitoneum studied by computed tomography. Radiology 1983; 148 (01) 187-192
    CrossrefPubMedGoogle Scholar
  • 8 Massalou D, Baqué-Juston M, Foti P, Staccini P, Baqué P. CT quantification of hemoperitoneum volume in abdominal haemorrhage: a new method. Surg Radiol Anat 2013; 35 (06) 481-486
    CrossrefPubMedGoogle Scholar
  • 9 Bloom BA, Gibbons RC. Focused Assessment with Sonography for Trauma. StatPearls [Internet]. Treasure Island, FL: StatPearls Publishing; 2023
    Google Scholar
  • 10 Rudralingam V, Footitt C, Layton B. Ascites matters. Ultrasound 2017; 25 (02) 69-79
    CrossrefPubMedGoogle Scholar
  • 11 UpToDate. Published 2020. Accessed December 26, 2023 at: https://www.uptodate.com/contents/initial-evaluation-and-management-of-blunt-abdominal-trauma-in-adults
  • 12 Shanmuganathan K, Mirvis SE, Sover ER. Value of contrast-enhanced CT in detecting active hemorrhage in patients with blunt abdominal or pelvic trauma. AJR Am J Roentgenol 1993; 161 (01) 65-69
    CrossrefPubMedGoogle Scholar
  • 13 Diagnostic Ultrasound or CT Scan. What's the Difference? Cardiovascular Solutions. Published April 21, 2015. Accessed December 26, 2023 at: http://www.cardiovascularsolutionsinstitute.com/diagnostic-ultrasound-or-ct-scan-whats-the-difference/
  • 14 Wertz JR, Lopez JM, Olson D, Thompson WM. Comparing the diagnostic accuracy of ultrasound and CT in evaluating acute cholecystitis. AJR Am J Roentgenol 2018; 211 (02) W92-W97
    CrossrefPubMedGoogle Scholar
  • 15 Stengel D, Leisterer J, Ferrada P, Ekkernkamp A, Mutze S, Hoenning A. Point-of-care ultrasonography for diagnosing thoracoabdominal injuries in patients with blunt trauma. Cochrane Database Syst Rev 2018; 12 (12) CD012669
    PubMedGoogle Scholar
  • 16 DenOtter TD, Schubert J. Hounsfield Unit. Treasure Island, FL: StatPearls Publishing; 2023
    Google Scholar
  • 17 Kothari RU, Brott T, Broderick JP. et al. The ABCs of measuring intracerebral hemorrhage volumes. Stroke 1996; 27 (08) 1304-1305
    CrossrefPubMedGoogle Scholar
  • 18 Huttner HB, Steiner T, Hartmann M. et al. Comparison of ABC/2 estimation technique to computer-assisted planimetric analysis in warfarin-related intracerebral parenchymal hemorrhage. Stroke 2006; 37 (02) 404-408
    CrossrefPubMedGoogle Scholar
  • 19 Zhao B, Jia WB, Zhang LY, Wang TZ. 1/2SH: A simple, accurate, and reliable method of calculating the hematoma volume of spontaneous intracerebral hemorrhage. Stroke 2020; 51 (01) 193-201
    CrossrefPubMedGoogle Scholar
  • 20 Wikipedia Contributors. Cluster analysis. Wikipedia. Published April 20, 2019. Accessed December 26, 2023 at: https://en.wikipedia.org/wiki/Cluster_analysis
  • 21 Clustering in Machine Learning. GeeksforGeeks. Published January 15, 2018. Accessed December 26, 2023 at: https://www.geeksforgeeks.org/clustering-in-machine-learning
  • 22 Hojjatoleslami SA, Kittler J. Region growing: a new approach. IEEE Trans Image Process 1998; 7 (07) 1079-1084
    CrossrefPubMedGoogle Scholar
  • 23 Adams R, Bischof L. Seeded region growing. IEEE Trans Pattern Anal Mach Intell 1994; 16 (06) 641-647
    CrossrefGoogle Scholar
  • 24 Contour finding—skimage 0.22.0 documentation. Accessed December 26, 2023 at: https://scikit-image.org/docs/stable/auto_examples/edges/plot_contours.html
  • 25 Active Contours - A Method for Image Segmentation in Computer Vision. Analytics Vidhya. Published September 13, 2021. Accessed December 26, 2023 at: https://www.analyticsvidhya.com/blog/2021/09/active-contours-a-method-for-image-segmentation-in-computer-vision/
  • 26 Hemalatha RJ, Thamizhvani TR, Dhivya AJA, Joseph JE, Babu B, Chandrasekaran R. Active contour based segmentation techniques for medical image analysis. In: Medical and Biological Image Analysis. InTech; 2018
    CrossrefGoogle Scholar
  • 27 Fedorov A, Beichel R, Kalpathy-Cramer J. et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging 2012; 30 (09) 1323-1341
    CrossrefPubMedGoogle Scholar
  • 28 Hillal A, Sultani G, Ramgren B, Norrving B, Wassélius J, Ullberg T. Accuracy of automated intracerebral hemorrhage volume measurement on non-contrast computed tomography: a Swedish Stroke Register cohort study. Neuroradiology 2023; 65 (03) 479-488
    CrossrefPubMedGoogle Scholar
  • 29 Wu TY, Sobowale O, Hurford R. et al. Software output from semi-automated planimetry can underestimate intracerebral haemorrhage and peri-haematomal oedema volumes by up to 41. Neuroradiology 2016; 58 (09) 867-876
    CrossrefPubMedGoogle Scholar
  • 30 Freeman WD, Barrett KM, Bestic JM, Meschia JF, Broderick DF, Brott TG. Computer-assisted volumetric analysis compared with ABC/2 method for assessing warfarin-related intracranial hemorrhage volumes. Neurocrit Care 2008; 9 (03) 307-312
    CrossrefPubMedGoogle Scholar
  • 31 Haley MD, Gregson BA, Mould WA, Hanley DF, Mendelow AD. Retrospective methods analysis of semiautomated intracerebral hemorrhage volume quantification from a selection of the STICH II cohort (Early Surgery Versus Initial Conservative Treatment in Patients With Spontaneous Supratentorial Lobar Intracerebral Haematomas). Stroke 2018; 49 (02) 325-332
    CrossrefPubMedGoogle Scholar
  • 32 Osiri X. DICOM Viewer | Technical Sheet. Accessed December 26, 2023 at: https://www.osirix-viewer.com/resources/technical-sheet
  • 33 Battey TWK, Dreizin D, Bodanapally UK. et al. A comparison of segmented abdominopelvic fluid volumes with conventional CT signs of abdominal compartment syndrome in a trauma population. Abdom Radiol (NY) 2019; 44 (07) 2648-2655
    CrossrefPubMedGoogle Scholar
  • 34 Chen M, Li Z, Ding J, Lu X, Cheng Y, Lin J. Comparison of common methods for precision volume measurement of hematoma. Comput Math Methods Med 2020; 2020: 6930836
    CrossrefPubMedGoogle Scholar
  • 35 Dreizin D, Zhou Y, Zhang Y, Tirada N, Yuille AL. Performance of a deep learning algorithm for automated segmentation and quantification of traumatic pelvic hematomas on CT. J Digit Imaging 2020; 33 (01) 243-251
    CrossrefPubMedGoogle Scholar
  • 36 Dreizin D, Bodanapally UK, Neerchal N, Tirada N, Patlas M, Herskovits E. Volumetric analysis of pelvic hematomas after blunt trauma using semi-automated seeded region growing segmentation: a method validation study. Abdom Radiol (NY) 2016; 41 (11) 2203-2208
    CrossrefPubMedGoogle Scholar
  • 37 Lee JY, Kim JS, Kim TY, Kim YS. Detection and classification of intracranial haemorrhage on CT images using a novel deep-learning algorithm. Sci Rep 2020; 10 (01) 20546
    CrossrefPubMedGoogle Scholar
  • 38 Dreizin D, Nixon B, Hu J. et al. A pilot study of deep learning-based CT volumetry for traumatic hemothorax. Emerg Radiol 2022; 29 (06) 995-1002
    CrossrefPubMedGoogle Scholar
  • 39 Sabour S. Interrater reliability among radiologists reading PET/contrast-enhanced CT scans using NI-RADS: methodologic issues. Radiol Imaging Cancer 2021; 3 (05) e210062
    CrossrefPubMedGoogle Scholar
  • 40 Blake KE, Beffa LR, Petro CC, Krpata DM, Prabhu AS, Rosen MJ. Surgeon accuracy and interrater reliability when interpreting CT scans after ventral hernia repair. Hernia 2023; 27 (02) 347-351
    CrossrefPubMedGoogle Scholar
  • 41 Bechstein M, McDonough R, Fiehler J. et al. Radiological evaluation criteria for chronic subdural hematomas: review of the literature. Clin Neuroradiol 2022; 32 (04) 923-929
    CrossrefPubMedGoogle Scholar
  • 42 Yan JL, Chen YL, Chen MY. et al. A robust, fully automatic detection method and calculation technique of midline shift in intracranial hemorrhage and its clinical application. Diagnostics (Basel) 2022; 12 (03) 693
    CrossrefPubMedGoogle Scholar
  • 43 Furlan A, Fakhran S, Federle MP. Spontaneous abdominal hemorrhage: causes, CT findings, and clinical implications. AJR Am J Roentgenol 2009; 193 (04) 1077-1087
    CrossrefPubMedGoogle Scholar
  • 44 Levine CD, Patel UJ, Silverman PM, Wachsberg RH. Low attenuation of acute traumatic hemoperitoneum on CT scans. AJR Am J Roentgenol 1996; 166 (05) 1089-1093
    CrossrefPubMedGoogle Scholar
  • 45 Ahn JH, Yoo DG, Choi SJ. et al. Hemoperitoneum caused by hepatic necrosis and rupture following a snakebite: a case report with rare CT findings and successful embolization. Korean J Radiol 2007; 8 (06) 556-560
    CrossrefPubMedGoogle Scholar
  • 46 Maxime St-Amant. Hemoperitoneum | Radiology Reference Article | Radiopaedia.org. Radiopaedia.org. Published 2012. Accessed November 17, 2023 at: https://radiopaedia.org/articles/haemoperitoneum
  • 47 Robinson JD, Sandstrom CK, Lehnert BE, Gross JA. Imaging of blunt abdominal solid organ trauma. Semin Roentgenol 2016; 51 (03) 215-229 DOI: 10.1053/j.ro.2015.12.003.
    CrossrefPubMedGoogle Scholar
  • 48 Gayer G, Hertz M, Manor H, Strauss S, Klinowski E, Zissin R. Dense ascites: CT manifestations and clinical implications. Emerg Radiol 2004; 10 (05) 262-267
    CrossrefPubMedGoogle Scholar
  • 49 Lee MS, Moon MH, Woo H, Sung CK, Jeon HW, Lee TS. Ruptured corpus luteal cyst: prediction of clinical outcomes with CT. Korean J Radiol 2017; 18 (04) 607-614
    CrossrefPubMedGoogle Scholar
  • 50 Rogowska J. Overview and fundamentals of medical image segmentation. In: Handbook of Medical Imaging. Elsevier; 2000: 69-85
    Google Scholar
  • 51 Davies ER. Thresholding Techniques. In: Computer and Machine Vision. Elsevier; 2012: 82-110
    Google Scholar
  • 52 Abera KA, Manahiloh KN, Motalleb Nejad M. The effectiveness of global thresholding techniques in segmenting two-phase porous media. Constr Build Mater 2017; 142: 256-267
    CrossrefGoogle Scholar
  • 53 Multi-Otsu Thresholding—skimage v0.19.2 docs. scikit-image.org. Accessed December 26, 2023 at: https://scikit-image.org/docs/stable/auto_examples/segmentation/plot_multiotsu.html
  • 54 Zhang P, Lu S, Li J. et al. Multi-component segmentation of X-ray computed tomography (CT) image using multi-Otsu thresholding algorithm and scanning electron microscopy. Energy Explor Exploit 2017; 35 (03) 281-294
    CrossrefGoogle Scholar
  • 55 Skimage.Filters—skimage 0.22.0 documentation. Scikit-image.org. Accessed November 16, 2023 at: https://scikit-image.org/docs/stable/api/skimage.filters.html