Toxicological Research

Korean Society of Toxicology & Korea Environmental Mutagen Society (한국독성학회)
권호 표지
DOI QR코드

DOI QR Code

Evaluation of radiation-induced bone marrow toxicity using artificial intelligence-based image analysis in mice

  • Yoon Ji Choi (Department of Biomedical Laboratory Science, Namseoul University) ;
  • Da Song Back (Department of Biomedical Laboratory Science, Namseoul University) ;
  • Kwang Ho Jang (Department of Biomedical Laboratory Science, Namseoul University) ;
  • Mijeong Park (Radiological and Medical Support Center, Korea Institute of Radiological and Medical Sciences) ;
  • Jimin Ha (Radiological and Medical Support Center, Korea Institute of Radiological and Medical Sciences) ;
  • Youn Kyoung Jeong (Radiological and Medical Support Center, Korea Institute of Radiological and Medical Sciences) ;
  • Jin Seok Kang (Department of Biomedical Laboratory Science, Namseoul University)
  • Received : 2024.12.05
  • Accepted : 2025.03.13
  • Published : 2025.07.15
⟨ Previous Next ⟩

Abstract

Radiation exposure profoundly affects bone marrow, with even low-dose exposure inducing notable biological changes. Traditional pathology methods often face challenges in detecting subtle alterations. However, artificial intelligence (AI) offers enhanced sensitivity and precision, enabling a more detailed analysis. This study aimed to evaluate the effect of whole-body irradiation (WBI) on blood parameters, bone marrow density, and apoptosis in mice, employing AI-based image analysis for accurate and efficient quantification of cell density and apoptosis. Female C57BL/6 mice (n=120) were divided into four groups: a control group (Group 1) and three irradiated groups (Groups 2, 3, and 4), exposed to 0.5 Gy, 1 Gy, and 2 Gy of WBI, respectively. Mice were sacrificed at 1, 3, and 7 days post-irradiation for analysis. Blood samples were assessed for hematological changes, and the sternum was histopathologically evaluated. Despite stable body weights, WBI significantly altered blood parameters, reducing white blood cell and red blood cell counts while increasing platelet counts. Histopathological examination revealed a marked reduction in bone marrow cellularity in Groups 3 and 4 on day 1 post-irradiation; however, cellularity appeared to recover in these groups by days 3 and 7. AI-based image analysis of the sternum provided precise quantification, confirming a significant decrease in bone marrow cellularity in Groups 3 and 4 compared to Group 1 on day 1 (p<0.01). Apoptosis analysis also demonstrated a significant increase in the apoptotic index in Group 4 sternum samples on days 1, 3 (p<0.01), and day 7 (p<0.05) relative to Group 1. In summary, WBI induced hematological and histopathological alterations in mice, characterized by changes in blood cell parameters, bone marrow cellularity, and apoptosis. The integration of AI-based image analysis provides a robust and efficient tool for quantifying these changes, offering considerable potential for advancing radiation biology and pathology research.

Keywords

Acknowledgement

We would like to thank Ms. Ju Eun Lim and Ye Rin Kim for their technical assistance (Namseoul University). This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2019R1F1A1058721 and No. 2022R1F1A1071039).

References

  1. Costa S, Reagan MR (2019) Therapeutic irradiation: consequences for bone and bone marrow adipose tissue. Front Endocrinol 10:587. https://doi.org/10.3389/fendo.2019.00587
  2. Tang FR, Loke WK, Khoo BC (2017) Low-dose or low-dose-rate ionizing radiation-induced bioeffects in animal models. J Radiat Res 58:165–182. https://doi.org/10.1093/jrr/rrw120
  3. Mauch P, Constine L, Greenberger J, Knospe W, Sullivan J, Liesveld JL, Deeg HJ (1995) Hematopoietic stem cell compartment: acute and late effects of radiation therapy and chemotherapy. Int J Radiat Oncol Biol Phys 31:1319–1339. https://doi.org/10.1016/0360-3016(94)00430-S
  4. Green DE, Rubin CT (2014) Consequences of irradiation on bone and marrow phenotypes, and its relation to disruption of hematopoietic precursors. Bone 63:87–94. https://doi.org/10.1016/j.bone.2014.02.018
  5. Mann PC, Vahle J, Keenan CM, Baker JF, Bradley AE, Goodman DG, Harada T, Herbert R, Kaufmann W, Kellner R, Nolte T, Rittinghausen S, Tanaka T (2012) International harmonization of toxicologic pathology nomenclature: an overview and review of basic principles. Toxicol Pathol 40:7S-13S. https://doi.org/10.1177/0192623312438738
  6. Shafi S, Parwani AV (2023) Artificial intelligence in diagnostic pathology. Diagn Pathol 18:109. https://doi.org/10.1186/s13000-023-01375-z
  7. Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, Cui C, Corrado G, Thrun S, Dean J (2019) A guide to deep learning in healthcare. Nat Med 25:24–29. https://doi.org/10.1038/s41591-018-0316-z
  8. Tizhoosh HR, Pantanowitz L (2018) Artificial intelligence and digital pathology: challenges and opportunities. J Pathol Inform 9:38. https://doi.org/10.4103/jpi.jpi_53_18
  9. Turner OC, Aeffner F, Bangari DS, High W, Knight B, Forest T, Cossic B, Himmel LE, Rudmann DG, Bawa B, Muthuswamy A, Aina OH, Edmondson EF, Saravanan C, Brown DL, Sing T, Sebastian MM (2020) Society of toxicologic pathology digital pathology and image analysis special interest group article*: opinion on the application of artificial intelligence and machine learning to digital toxicologic pathology. Toxicol Pathol 48:277–294. https://doi.org/10.1177/0192623319881401
  10. Brent R, Boucheron L (2018) Deep learning to predict microscope images. Nat Methods 15:868–870. https://doi.org/10.1038/s41592-018-0194-9
  11. Hamilton PW, Wang Y, McCullough SJ (2012) Virtual microscopy and digital pathology in training and education. APMIS acta pathologica microbiologica et immunologica Scandinavica 120:305–315. https://doi.org/10.1111/j.1600-0463.2011.02869.x
  12. Bradley A, Jacobsen M (2019) Toxicologic pathology forum*: forum*: opinion on considerations for the use of whole slide images in GLP pathology peer review. Toxicol Pathol 47:100–107. https://doi.org/10.1177/0192623318818790
  13. Kozlowski C, Brumm J, Cain G (2018) An automated image analysis method to quantify veterinary bone marrow cellularity on H&E sections. Toxicol Pathol 46:324–335. https://doi.org/10.1177/0192623318766457
  14. Bankhead P, Loughrey MB, Fernandez JA, Dombrowski Y, McArt DG, Dunne PD, McQuaid S, Gray RT, Murray LJ, Coleman HG, James JA, Salto-Tellez M, Hamilton PW (2017) QuPath: open source software for digital pathology image analysis. Sci Rep 7:16878. https://doi.org/10.1038/s41598-017-17204-5
  15. Akeem S, Lukman O, Eltahir K, Fatai O, Abiola B, Khadijat O (2019) Bone marrow and peripheral blood cells toxicity of a single 2.0 Gy cobalt(60) ionizing radiation: an animal model. Ethiop J Health Sci 29:195–202. https://doi.org/10.4314/ejhs.v29i2.6
  16. Reagan WJ, Irizarry-Rovira A, Poitout-Belissent F, Bolliger AP, Ramaiah SK, Travlos G, Walker D, Bounous D, Walter G (2011) Best practices for evaluation of bone marrow in nonclinical toxicity studies. Toxicol Pathol 39:435–448. https://doi.org/10.1177/0192623310396907
  17. Singh VK, Parekh VI, Brown DS, Kao TC, Mog SR (2011) Tocopherol succinate: modulation of antioxidant enzymes and oncogene expression, and hematopoietic recovery. Int J Radiat Oncol Biol Phys 79:571–578. https://doi.org/10.1016/j.ijrobp.2010.08.019
  18. Lewis JE, Pozdnyakova O (2024) Advances in bone marrow evaluation. Clin Lab Med 44:431–440. https://doi.org/10.1016/j.cll.2024.04.005
  19. Farahani N, Parwani AV, Pantanowitz L (2015) Whole slide imaging in pathology: advantages, limitations, and emerging perspectives. Pathol Laboratory Med Int 7:23–33
  20. Aeffner F, Zarella MD, Buchbinder N, Bui MM, Goodman MR, Hartman DJ, Lujan GM, Molani MA, Parwani AV, Lillard K, Turner OC, Vemuri VNP, Yuil-Valdes AG, Bowman D (2019) Introduction to digital image analysis in whole-slide imaging: a white paper from the digital pathology association. J Pathol Inform 10:9. https://doi.org/10.4103/jpi.jpi_82_18
  21. Guerrero RED, Carvalho L, Bocklitz T, Popp J, Oliveirab JL (2022) Software tools and platforms in Digital Pathology: a review for clinicians and computer scientists. J Pathol Inform 13:100103. https://doi.org/10.1016/j.jpi.2022.100103
  22. Willard-Mack CL, Elmore SA, Hall WC, Harleman J, Kuper CF, Losco P, Rehg JE, Ruhl-Fehlert C, Ward JM, Weinstock D, Bradley A, Hosokawa S, Pearse G, Mahler BW, Herbert RA, Keenan CM (2019) Nonproliferative and proliferative lesions of the rat and mouse hematolymphoid system. Toxicol Pathol 47:665–783. https://doi.org/10.1177/0192623319867053
  23. O'Connell KE, Mikkola AM, Stepanek AM, Vernet A, Hall CD, Sun CC, Yildirim E, Staropoli JF, Lee JT, Brown DE (2015) Practical murine hematopathology: a comparative review and implications for research. Comp Med 65:96–113
  24. Carter CM, Cregar LC, Aulbach AD (2017) Cytological bone marrow cell differential counts and morphologic findings in healthy cynomolgus monkeys (Macaca fascicularis) from nonclinical toxicology studies. Toxicol Pathol 45:267–274. https://doi.org/10.1177/0192623316677067
  25. Rehg JE, Bush D, Ward JM (2012) The utility of immunohistochemistry for the identification of hematopoietic and lymphoid cells in normal tissues and interpretation of proliferative and inflammatory lesions of mice and rats. Toxicol Pathol 40:345–374. https://doi.org/10.1177/0192623311430695
  26. Haley P, Perry R, Ennulat D, Frame S, Johnson C, Lapointe JM, Nyska A, Snyder P, Walker D, Walter G (2005) STP position paper: best practice guideline for the routine pathology evaluation of the immune system. Toxicol Pathol 33:404–407; discussion 408. https://pubmed.ncbi.nlm.nih.gov/15805080/ https://doi.org/10.1080/01926230590934304