대한의생명과학회지 (Biomedical Science Letters)

  • 제29권2호
  • /
  • Pages.53-57
  • /
  • 2023
  • /
  • 1738-3226(pISSN)
  • /
  • 2288-7415(eISSN)
대한의생명과학회 (The Korean Society for Biomedical Laboratory Sciences)
권호 표지
DOI QR코드

DOI QR Code

Application of Artificial Intelligence-based Digital Pathology in Biomedical Research

  • Jin Seok Kang (Department of Biomedical Laboratory Science, Namseoul University)
  • 투고 : 2023.04.05
  • 심사 : 2023.06.27
  • 발행 : 2023.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The main objective of pathologists is to achieve accurate lesion diagnoses, which has become increasingly challenging due to the growing number of pathological slides that need to be examined. However, using digital technology has made it easier to complete this task compared to older methods. Digital pathology is a specialized field that manages data from digitized specimen slides, utilizing image processing technology to automate and improve analysis. It aims to enhance the precision, reproducibility, and standardization of pathology-based researches, preclinical, and clinical trials through the sophisticated techniques it employs. The advent of whole slide imaging (WSI) technology is revolutionizing the pathology field by replacing glass slides as the primary method of pathology evaluation. Image processing technology that utilizes WSI is being implemented to automate and enhance analysis. Artificial intelligence (AI) algorithms are being developed to assist pathologic diagnosis and detection and segmentation of specific objects. Application of AI-based digital pathology in biomedical researches is classified into four areas: diagnosis and rapid peer review, quantification, prognosis prediction, and education. AI-based digital pathology can result in a higher accuracy rate for lesion diagnosis than using either a pathologist or AI alone. Combining AI with pathologists can enhance and standardize pathology-based investigations, reducing the time and cost required for pathologists to screen tissue slides for abnormalities. And AI-based digital pathology can identify and quantify structures in tissues. Lastly, it can help predict and monitor disease progression and response to therapy, contributing to personalized medicine.

키워드

과제정보

Funding for this paper was provided by Namseoul University 2022.

참고문헌

  1. 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. Introduction to digital image analysis in whole-slide imaging: A white paper from the digital pathology association. J Pathol Inform. 2019. 10: 9.
  2. Bradley A, Jacobsen M. Toxicologic pathology forum*: Opinion on considerations for the use of whole slide images in glp pathology peer review. Toxicol Pathol. 2019. 47: 100-107. https://doi.org/10.1177/0192623318818790
  3. Brent R, Boucheron L. Deep learning to predict microscope images. Nat Methods. 2018. 15: 868-870. https://doi.org/10.1038/s41592-018-0194-9
  4. Coudray N, Ocampo PS, Sakellaropoulos T, Narula N, Snuderl M, Fenyo D, Moreira AL, Razavian N, Tsirigos A. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med. 2018. 24: 1559-1567. https://doi.org/10.1038/s41591-018-0177-5
  5. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017. 542: 115-118. https://doi.org/10.1038/nature21056
  6. Farahani N, Parwani AV, Pantanowitz L. Whole slide imaging in pathology: Advantages, limitations, and emerging perspectives. Pathology and Laboratory Medicine International. 2015. 7: 23-33. https://doi.org/10.2147/PLMI.S59826
  7. Hamilton PW, Wang Y, McCullough SJ. Virtual microscopy and digital pathology in training and education. APMIS. 2012. 120: 305-315. https://doi.org/10.1111/j.1600-0463.2011.02869.x
  8. Hoefling H, Sing T, Hossain I, Boisclair J, Doelemeyer A, Flandre T, Piaia A, Romanet V, Santarossa G, Saravanan C, Sutter E, Turner O, Wuersch K, Moulin P. Histonet: A deep learning-based model of normal histology. Toxicol Pathol. 2021. 49: 784-797. https://doi.org/10.1177/0192623321993425
  9. Janowczyk A, Madabhushi A. Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases. J Pathol Inform. 2016. 7: 29.
  10. Kannan S, Morgan LA, Liang B, Cheung MG, Lin CQ, Mun D, Nader RG, Belghasem ME, Henderson JM, Francis JM, Chitalia VC, Kolachalama VB. Segmentation of glomeruli within trichrome images using deep learning. Kidney Int Rep. 2019. 4: 955-962. https://doi.org/10.1016/j.ekir.2019.04.008
  11. Kather JN, Pearson AT, Halama N, Jager D, Krause J, Loosen SH, Marx A, Boor P, Tacke F, Neumann UP, Grabsch HI, Yoshikawa T, Brenner H, Chang-Claude J, Hoffmeister M, Trautwein C, Luedde T. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med. 2019. 25: 1054-1056. https://doi.org/10.1038/s41591-019-0462-y
  12. Kozlowski C, Brumm J, Cain G. An automated image analysis method to quantify veterinary bone marrow cellularity on h&e sections. Toxicol Pathol. 2018a. 46: 324-335. https://doi.org/10.1177/0192623318766457
  13. Kozlowski C, Fullerton A, Cain G, Katavolos P, Bravo J, Tarrant JM. Proof of concept for an automated image analysis method to quantify rat bone marrow hematopoietic lineages on h&e sections. Toxicol Pathol. 2018b. 46: 336-347. https://doi.org/10.1177/0192623318766458
  14. Kuo KH, Leo JM. Optical versus virtual microscope for medical education: A systematic review. Anat Sci Educ. 2019. 12: 678-685. https://doi.org/10.1002/ase.1844
  15. Liang L, Liu M, Sun W. A deep learning approach to estimate chemically-treated collagenous tissue nonlinear anisotropic stress-strain responses from microscopy images. Acta Biomater. 2017. 63: 227-235. https://doi.org/10.1016/j.actbio.2017.09.025
  16. Mazer BL, Homer RJ, Rimm DL. False-positive pathology: Improving reproducibility with the next generation of pathologists. Lab Invest. 2019. 99: 1260-1265. https://doi.org/10.1038/s41374-019-0257-2
  17. Morton D, Sellers RS, Barale-Thomas E, Bolon B, George C, Hardisty JF, Irizarry A, McKay JS, Odin M, Teranishi M. Recommendations for pathology peer review. Toxicol Pathol. 2010. 38: 1118-1127. https://doi.org/10.1177/0192623310383991
  18. Pell R, Oien K, Robinson M, Pitman H, Rajpoot N, Rittscher J, Snead D, Verrill C. The use of digital pathology and image analysis in clinical trials. J Pathol Clin Res. 2019. 5: 81-90. https://doi.org/10.1002/cjp2.127
  19. Radiya-Dixit E, Zhu D, Beck AH. Automated classification of benign and malignant proliferative breast lesions. Sci Rep. 2017. 7: 9900.
  20. Saco A, Bombi JA, Garcia A, Ramirez J, Ordi J. Current status of whole-slide imaging in education. Pathobiology. 2016. 83: 79-88. https://doi.org/10.1159/000442391
  21. Schaer R, Otalora S, Jimenez-Del-Toro O, Atzori M, Muller H. Deep learning-based retrieval system for gigapixel histopathology cases and the open access literature. J Pathol Inform. 2019. 10: 19.
  22. Segnani C, Ippolito C, Antonioli L, Pellegrini C, Blandizzi C, Dolfi A, Bernardini N. Histochemical detection of collagen fibers by sirius red/fast green is more sensitive than van gieson or sirius red alone in normal and inflamed rat colon. PLoS One. 2015. 10: e0144630.
  23. Sheehan SM, Korstanje R. Automatic glomerular identification and quantification of histological phenotypes using image analysis and machine learning. Am J Physiol Renal Physiol. 2018. 315: F1644-F1651. https://doi.org/10.1152/ajprenal.00629.2017
  24. Sheikhzadeh F, Ward RK, van Niekerk D, Guillaud M. Automatic labeling of molecular biomarkers of immunohistochemistry images using fully convolutional networks. PLoS One. 2018. 13: e0190783.
  25. Tizhoosh HR, Pantanowitz L. Artificial intelligence and digital pathology: Challenges and opportunities. J Pathol Inform. 2018. 9: 38.
  26. 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. Society of toxicologic pathology digital pathology and image analysis special interest group article*: article*: Opinion on the application of artificial intelligence and machine learning to digital toxicologic pathology. Toxicol Pathol. 2020. 48: 277-294. https://doi.org/10.1177/0192623319881401
  27. Zarella MD, Bowman D, Aeffner F, Farahani N, Xthona A, Absar SF, Parwani A, Bui M, Hartman DJ. A practical guide to whole slide imaging: A white paper from the digital pathology association. Arch Pathol Lab Med. 2019. 143: 222-234.  https://doi.org/10.5858/arpa.2018-0343-RA