Toxicological Research

  • 제40권4호
  • /
  • Pages.551-559
  • /
  • 2024
  • /
  • 1976-8257(pISSN)
  • /
  • 2234-2753(eISSN)
한국독성학회 (Korean Society of Toxicology & Korea Environmental Mutagen Society)
권호 표지
DOI QR코드

DOI QR Code

Comparative analysis of chronic progressive nephropathy (CPN) diagnosis in rat kidneys using an artificial intelligence deep learning model

  • Yeji Bae (Department of Pharmaceutical Engineering, Life Health College, Hoseo University) ;
  • Jongsu Byun (Pathology Team, Microscopic Examination, Dt&CRO) ;
  • Hangyu Lee (Program Development Team, DeepSoft) ;
  • Beomseok Han (Department of Pharmaceutical Engineering, Life Health College, Hoseo University)
  • 투고 : 2023.12.25
  • 심사 : 2024.05.15
  • 발행 : 2024.10.15
⟨ 이전 논문 다음 논문 ⟩

초록

With the development of artificial intelligence (AI), technologies based on machines and deep learning are being used in many academic fields. In toxicopathology, research is actively underway to analyze whole slide image (WSI)-level images using AI deep-learning models. However, few studies have been conducted on models for diagnosing complex lesions comprising multiple lesions. Therefore, this study used deep learning segmentation models (YOLOv8, Mask R-CNN, and SOLOv2) to identify three representative lesions (tubular basophilia with atrophy, mononuclear cell infiltration, and hyaline casts) of chronic progressive nephropathy of the kidney, a complex lesion observed in a non-clinical test using rats and selected an initial model appropriate for diagnosing complex lesions by analyzing the characteristics of each algorithm. Approximately 2000 images containing three lesions were extracted using 33 WSI of rat kidneys with chronic progressive nephropathy. Among them, 1701 images were divided into first and second rounds of learning. The loss and mAP50 values were measured twice to confirm the performances of the three algorithms. Loss measurements were stopped at an appropriate epoch to prevent overfitting, and the loss value decreased in the second round based on the data learned in the first round. After measuring the accuracy twice, detection using Mask R-CNN showed the highest mAP50 in all lesions among the three models and was considered sufficient as an initial model for diagnosing complex lesions. By contrast, the YOLOv8 and SOLOv2 models showed low accuracy for all three lesions and had difficulty with segmentation tasks. Therefore, this paper proposes a Mask R-CNN as the initial model for segmenting complex lesions. Precise diagnosis is possible if the model can be trained by increasing the input data, thereby providing greater accuracy in diagnosing pathological images.

키워드

과제정보

This research was supported by the Ministry of the Environment's "Chemical Material Safety Management Professional Training Project." The authors are deeply grateful to Dr. Dong Deuk Jang from HLB BioStep Co., Ltd. (Incheon, Korea) for technical support of the whole slide image and CentralBio Co., Ltd. (Incheon, Korea) for providing the tissue slides.

참고문헌

  1. Shinde PP, Shah S (2018) A review of machine learning and deep learning applications. In: 2018 Fourth international conference on computing communication control and automation (ICCUBEA). Pune, India, pp 1-6. https://doi.org/10.1109/ICCUBEA.2018.8697857 
  2. Park SH (2018) Artificial intelligence in medicine: beginner's guide. J Korean Soc Radiol 78:301-308. https://doi.org/10.3348/jksr.2018.78.5.301 
  3. Xing F, Xie Y, Su H, Liu F, Yang L (2018) Deep learning in microscopy image analysis: a survey. IEEE Trans Neural Netw Learn Syst 29:4550-4568. https://doi.org/10.1109/TNNLS.2017.2766168 
  4. Zhao Z-Q, Zheng P, Xu S-T, Wu X (2019) Object detection with deep learning: a review. IEEE Trans Neural Netw Learn Syst 30:3212-3232. https://doi.org/10.1109/TNNLS.2018.2876865 
  5. Nam S, Chong Y, Jung CK, Kwak T-Y et al (2020) Introduction to digital pathology and computer-aided pathology. J Pathol Transl Med 54:125-134. https://doi.org/10.4132/jptm.2019.12.31 
  6. Byun JS, Lee JH, Kang JS, Han BS (2022) Comparative analysis of imaging diagnostic models for tubular basophilia and mineralization of kidney. Lab Anim Res 38:29. https://doi.org/10.1186/s42826-022-00139-y 
  7. Pantanowitz L, Sinard JH, Henricks WH, Fatheree LA, Carter AB, Contis L, Beckwith BA, Evans AJ, Christopher N et al (2013) Validating whole slide imaging for diagnostic purposes in pathology: guideline from the college of American pathologists pathology and laboratory quality center. Arch Pathol Lab Med 137:1710-1722. https://doi.org/10.5858/arpa.2013-0093-CP 
  8. Zarella MD, Bowman D, Aefner F, Farahani N, Xthona A, Absar SF, Parwani A, Bui M, Hartman DJ (2019) A practical guide to whole slide imaging: a white paper from the digital pathology association. Arch Pathol Lab Med 143:222-234. https://doi.org/10.5858/arpa.2018-0343-RA 
  9. Niazi MKK, Parwani AV, Gurcan MN (2019) Digital pathology and artificial intelligence. Lancet Oncol 20:e253-e261. https://doi.org/10.1016/S1470-2045(19)30154-8 
  10. Shaoxu Wu, Hong G, Abai Xu, Zeng H, Chen X, Wang Y, Luo Y, Peng Wu, Liu C, Jiang N et al (2023) Artificial intelligence-based model for lymph node metastases detection on whole slide images in bladder cancer: a retrospective, multicentre, diagnostic study. Lancet Oncol 24:360-370. https://doi.org/10.1016/S1470-2045(23)00061-X 
  11. Mehrvar S, Himmel LE, Babburi P, Goldberg AL, Guffroy M, Janardhan K, Krempley AL, Bawa B (2021) Deep learning approaches and applications in toxicologic histopathology: current status and future perspectives. J Pathol Inform 12:42. https://doi.org/10.4103/jpi.jpi_36_21 
  12. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436-444. https://doi.org/10.1038/nature14539 
  13. Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84-90. https://doi.org/10.1145/3065386 
  14. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1-9. https://doi.org/10.1109/CVPR.2015.7298594 
  15. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 770-778. https://doi.org/10.48550/arXiv.1512.03385 
  16. Boukhriss RR, Fendri E, Hammami M (2020) Moving object detection under different weather conditions using full-spectrum light sources. Pattern Recogn Lett 129:205-212. https://doi.org/10.1016/j.patrec.2019.11.004 
  17. Park S, Ji M, Chun J (2018) 2D human pose estimation based on object detection using RGB-D information. KSII Trans Internet Inf Syst 12:800-816. https://doi.org/10.3837/tiis.2018.02.015 
  18. Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). pp 779-788. https://doi.org/10.48550/arXiv.1506.02640 
  19. He K, Gkioxari G, Dollar P, Girshick R (2017) Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision (ICCV). pp 2961-2969. https://doi.org/10.48550/arXiv.1703.06870 
  20. Reis D, Kupec J, Hong J, Daoudi A (2023) Real-time flying object detection with YOLOv8. ArXiv 2023, arXiv:2305.09972. https://doi.org/10.48550/arXiv.2305.09972 
  21. Ge Z, Liu S, Wang F, Li Z, Sun J (2021) YOLOX: exceeding YOLO series in 2021. ArXiv 2021, arXiv:2107.08430. https://doi.org/10.48550/arXiv.2107.08430 
  22. RangeKing (2023) Brief summary of YOLOv8 model structure #189. Github. https://github.com/ultralytics/ultralytics/issues/189#issue-1527158137. Accessed 10 Jan 2023 
  23. Wang X, Kong T, Shen C, Jiang Y, Li L (2019) SOLO: segmenting objects by locations. ArXiv 2019, arXiv:1912.04488. https://doi.org/10.48550/arXiv.1912.04488 
  24. Cheng B, Misra I, Schwing AG, Kirillov A, Girdhar R (2021) Masked-attention mask transformer for universal image segmentation. ArXiv 2021, arXiv:2112.01527. https://doi.org/10.48550/arXiv.2112.01527 
  25. Wang X, Zhang R, Kong T, Li L, Shen C (2020) SOLOv2: dynamic and fast instance segmentation. ArXiv 2020, arXiv:2003.10152. https://doi.org/10.48550/arXiv.2003.10152 
  26. Bouteldja N, Klinkhammer BM, Bulow RD, Droste P, Otten SW, von Stillfried SF et al (2021) Deep learning-based segmentation and quantification in experimental kidney histopathology. J Am Soc Nephrol 32:52-68. https://doi.org/10.1681/ASN.2020050597 
  27. Hermsen M, de Bel T, den Boer M, Steenbergen EJ, Kers J, Florquin S, Roelofs JJTH et al (2019) Deep learning-based histopathologic assessment of kidney tissue. J Am Soc Nephrol 10:1968-1979. https://doi.org/10.1681/ASN.2019020144 
  28. Hwang J-H, Lim M, Han G, Park H, Kim Y-B, Park J, Jun S-Y, Lee J, Cho J-W (2023) A comparative study on the implementation of deep learning algorithms for detection of hepatic necrosis in toxicity studies. Toxicol Res 39:399-408. https://doi.org/10.1007/s43188-023-00173-5 
  29. Wang KS, Yu G, Xu C, Meng XH, Zhou J, Zheng C, Deng Z, Shang L, Liu R, Su S, Zhou X et al (2021) Accurate diagnosis of colorectal cancer based on histopathology images using artificial intelligence. BMC Med 19:76. https://doi.org/10.1186/s12916-021-01942-5 
  30. Hwang J-H, Kim H-J, Park H, Lee B-S, Son H-Y, Kim Y-B, Jun S-Y, Park J-H, Lee J, Cho J-W (2022) Implementation and practice of deep learning-based instance segmentation algorithm for quantification of hepatic fibrosis at whole slide level in Sprague-Dawley rats. Toxicol Pathol 50:186-196. https://doi.org/10.1177/01926233211057128 
  31. Vuola AO, Akram SU, Kannala J (2019) Mask-RCNN and U-Net ensembled for nuclei segmentation. In: 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019). Venice, Italy, pp 208-212. https://doi.org/10.1109/ISBI.2019.8759574 
  32. Meng J, Xue L, Chang Y, Zhang J, Chang S, Liu K, Liu S, Wang B, Yang K (2020) Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using mask R-CNN. Open Life Sci 15:588-596. https://doi.org/10.1515/biol-2020-0055 
  33. Chiao J-Y, Chen K-Y, Liao KY-K, Hsieh P-H, Zhang G, Huang T-C (2019) Detection and classification the breast tumors using mask R-CNN on sonograms. Medicine (Baltimore) 98:e15200. https://doi.org/10.1097/MD.0000000000015200 
  34. Baek EB, Lee J, Hwang J-H, Park H, Lee B-S, Kim Y-B, Jun S-Y, Her J, Son H-Y, Cho J-W (2023) Application of multiple-finding segmentation utilizing mask R-CNN-based deep learning in a rat model of drug-induced liver injury. Sci Rep 13:17555. https://doi.org/10.1038/s41598-023-44897-8 
  35. Antus B, Yao Y, Liu S, Song E, Lutz J, Heemann U (2001) Contribution of androgens to chronic allograft nephropathy is mediated by dihydrotestoster. Kidney Int 60:1955-1963. https://doi.org/10.1046/j.1523-1755.2001.00007.x 
  36. Parente Filho SLA, de Carvalho Gomes PEA, Forte GA, Lima LLL et al (2020) Kidney disease associated with androgenic - anabolic steroids and vitamin supplements abuse: be aware! Nefrologia (Engl Ed) 40:26-31. https://doi.org/10.1016/j.nefro.2019.06.003 
  37. Barthold SW (1979) Chronic progressive nephropathy in aging rats. Toxicologic Pathol 7:1-6. https://doi.org/10.1177/019262337900700101 
  38. Haschek WM, Rousseaux CG, Wallig MA (2013) Haschek and Rousseaux's handbook of toxicologic pathology. Academic Press, United States. ISBN: 9780124157590 
  39. Lin T-Y, Maire M, Belongie S, Bourdev L, Girshick R, Hays J, Perona P, Ramanan D, Lawrence Zitnick C, Dollar P (2014) Microsoft COCO: common objects in context. ArXiv 2014, arXiv:1405.0312. https://doi.org/10.48550/arXiv.1405.0312 
  40. Ying X (2019) An overview of overfitting and its solutions. J Phys Conf Ser 1168:022022. https://doi.org/10.1088/1742-6596/1168/2/022022 
  41. Jia W, Wei J, Zhang Q, Pan N, Niu Y, Yin X, Ding Y, Ge X (2022) Accurate segmentation of green fruit based on optimized mask RCNN application in complex orchard. Front Plant Sci 13:955256. https://doi.org/10.3389/fpls.2022.955256 
  42. Kulkarni A, Chong D, Batarseh FA (2020) Foundations of data imbalance and solutions for a data democracy. In: Data democracy. Academic Press, pp 83-106. https://doi.org/10.1016/B978-0-12-818366-3.00005-8 
  43. He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21:1263-1284. https://doi.org/10.1109/TKDE.2008.239