Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

From Pixel to Slide image: Polarization Modality-based Pathological Diagnosis Using Representation Learning (2401.01496v1)

Published 3 Jan 2024 in eess.IV, cs.AI, and cs.CV

Abstract: Thyroid cancer is the most common endocrine malignancy, and accurately distinguishing between benign and malignant thyroid tumors is crucial for developing effective treatment plans in clinical practice. Pathologically, thyroid tumors pose diagnostic challenges due to improper specimen sampling. In this study, we have designed a three-stage model using representation learning to integrate pixel-level and slice-level annotations for distinguishing thyroid tumors. This structure includes a pathology structure recognition method to predict structures related to thyroid tumors, an encoder-decoder network to extract pixel-level annotation information by learning the feature representations of image blocks, and an attention-based learning mechanism for the final classification task. This mechanism learns the importance of different image blocks in a pathological region, globally considering the information from each block. In the third stage, all information from the image blocks in a region is aggregated using attention mechanisms, followed by classification to determine the category of the region. Experimental results demonstrate that our proposed method can predict microscopic structures more accurately. After color-coding, the method achieves results on unstained pathology slides that approximate the quality of Hematoxylin and eosin staining, reducing the need for stained pathology slides. Furthermore, by leveraging the concept of indirect measurement and extracting polarized features from structures correlated with lesions, the proposed method can also classify samples where membrane structures cannot be obtained through sampling, providing a potential objective and highly accurate indirect diagnostic technique for thyroid tumors.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. B. S. Chhikara and K. Parang, “Global cancer statistics 2022: the trends projection analysis,” Chemical Biology Letters, vol. 10, no. 1, pp. 451–451, 2023.
  2. Z. W. Baloch, S. L. Asa, J. A. Barletta, R. A. Ghossein, C. C. Juhlin, C. K. Jung, V. A. LiVolsi, M. G. Papotti, M. Sobrinho-Simoes, G. Tallini et al., “Overview of the 2022 who classification of thyroid neoplasms,” Endocrine pathology, vol. 33, no. 1, pp. 27–63, 2022.
  3. M. Wróblewski, J. Wróblewska, J. Nuszkiewicz, M. Pawłowska, R. Wesołowski, and A. Woźniak, “The role of selected trace elements in oxidoreductive homeostasis in patients with thyroid diseases,” International Journal of Molecular Sciences, vol. 24, no. 5, p. 4840, 2023.
  4. Q. T. Nguyen, E. J. Lee, M. G. Huang, Y. I. Park, A. Khullar, and R. A. Plodkowski, “Diagnosis and treatment of patients with thyroid cancer,” American health & drug benefits, vol. 8, no. 1, p. 30, 2015.
  5. D. W. Chen, B. H. Lang, D. S. McLeod, K. Newbold, and M. R. Haymart, “Thyroid cancer,” The Lancet, vol. 401, no. 10387, pp. 1531–1544, 2023.
  6. M. E. Cabanillas, D. G. McFadden, and C. Durante, “Thyroid cancer,” The Lancet, vol. 388, no. 10061, pp. 2783–2795, 2016.
  7. C. M. Kitahara and J. A. Sosa, “The changing incidence of thyroid cancer,” Nature Reviews Endocrinology, vol. 12, no. 11, pp. 646–653, 2016.
  8. Y. H. Sharifovna, “Thyroid cancer diagnostics, classification, staging,” Ijtimoiy fanlarda innovasiya onlayn ilmiy jurnali, vol. 1, no. 5, pp. 63–69, 2021.
  9. M. Schlumberger and S. Leboulleux, “Current practice in patients with differentiated thyroid cancer,” Nature Reviews Endocrinology, vol. 17, no. 3, pp. 176–188, 2021.
  10. M. Cui and D. Y. Zhang, “Artificial intelligence and computational pathology,” Laboratory Investigation, vol. 101, no. 4, pp. 412–422, 2021.
  11. B. Acs, M. Rantalainen, and J. Hartman, “Artificial intelligence as the next step towards precision pathology,” Journal of internal medicine, vol. 288, no. 1, pp. 62–81, 2020.
  12. K. Bera, K. A. Schalper, D. L. Rimm, V. Velcheti, and A. Madabhushi, “Artificial intelligence in digital pathology—new tools for diagnosis and precision oncology,” Nature reviews Clinical oncology, vol. 16, no. 11, pp. 703–715, 2019.
  13. A. H. Song, G. Jaume, D. F. Williamson, M. Y. Lu, A. Vaidya, T. R. Miller, and F. Mahmood, “Artificial intelligence for digital and computational pathology,” Nature Reviews Bioengineering, vol. 1, no. 12, pp. 930–949, 2023.
  14. J. Dong, Y. Yao, L. Lin, Y. Dong, J. Wan, R. Peng, C. Li, and H. Ma, “A polarization and radiomics feature fusion network for the classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma,” arXiv preprint arXiv:2312.16607, 2023.
  15. F. Ghaznavi, A. Evans, A. Madabhushi, and M. Feldman, “Digital imaging in pathology: whole-slide imaging and beyond,” Annual Review of Pathology: Mechanisms of Disease, vol. 8, pp. 331–359, 2013.
  16. C. D. Gatenbee, A.-M. Baker, S. Prabhakaran, O. Swinyard, R. J. Slebos, G. Mandal, E. Mulholland, N. Andor, A. Marusyk, S. Leedham et al., “Virtual alignment of pathology image series for multi-gigapixel whole slide images,” Nature communications, vol. 14, no. 1, p. 4502, 2023.
  17. C.-W. Wang, Y.-C. Lee, E. Calista, F. Zhou, H. Zhu, R. Suzuki, D. Komura, S. Ishikawa, and S.-P. Cheng, “A benchmark for comparing precision medicine methods in thyroid cancer diagnosis using tissue microarrays,” Bioinformatics, vol. 34, no. 10, pp. 1767–1773, 2018.
  18. D. Dov, S. Z. Kovalsky, J. Cohen, D. E. Range, R. Henao, and L. Carin, “Thyroid cancer malignancy prediction from whole slide cytopathology images,” in Machine Learning for Healthcare Conference.   PMLR, 2019, pp. 553–570.
  19. D. D. Elliott Range, D. Dov, S. Z. Kovalsky, R. Henao, L. Carin, and J. Cohen, “Application of a machine learning algorithm to predict malignancy in thyroid cytopathology,” Cancer cytopathology, vol. 128, no. 4, pp. 287–295, 2020.
  20. A. S. El-Hossiny, W. Al-Atabany, O. Hassan, A. M. Soliman, and S. A. Sami, “classification of thyroid carcinoma in whole slide images using cascaded cnn,” IEEE Access, vol. 9, pp. 88 429–88 438, 2021.
  21. A. Gupta, P. J. Harrison, H. Wieslander, N. Pielawski, K. Kartasalo, G. Partel, L. Solorzano, A. Suveer, A. H. Klemm, O. Spjuth et al., “Deep learning in image cytometry: a review,” Cytometry Part A, vol. 95, no. 4, pp. 366–380, 2019.
  22. H. Wieslander, G. Forslid, E. Bengtsson, C. Wahlby, J.-M. Hirsch, C. Runow Stark, and S. Kecheril Sadanandan, “Deep convolutional neural networks for detecting cellular changes due to malignancy,” in Proceedings of the IEEE international conference on computer vision workshops, 2017, pp. 82–89.
  23. E. Du, H. He, N. Zeng, M. Sun, Y. Guo, J. Wu, S. Liu, and H. Ma, “Mueller matrix polarimetry for differentiating characteristic features of cancerous tissues,” Journal of biomedical optics, vol. 19, no. 7, pp. 076 013–076 013, 2014.
  24. C. He, H. He, J. Chang, B. Chen, H. Ma, and M. J. Booth, “Polarisation optics for biomedical and clinical applications: a review,” Light: Science & Applications, vol. 10, no. 1, p. 194, 2021.
  25. N. Ghosh and I. A. Vitkin, “Tissue polarimetry: concepts, challenges, applications, and outlook,” Journal of biomedical optics, vol. 16, no. 11, pp. 110 801–110 801, 2011.
  26. H. He, R. Liao, N. Zeng, P. Li, Z. Chen, X. Liu, and H. Ma, “Mueller matrix polarimetry—an emerging new tool for characterizing the microstructural feature of complex biological specimen,” Journal of Lightwave Technology, vol. 37, no. 11, pp. 2534–2548, 2018.
  27. Y. Dong, J. Wan, L. Si, Y. Meng, Y. Dong, S. Liu, H. He, and H. Ma, “Deriving polarimetry feature parameters to characterize microstructural features in histological sections of breast tissues,” IEEE Transactions on Biomedical Engineering, vol. 68, no. 3, pp. 881–892, 2020.
  28. Y. Liu, Y. Dong, L. Si, R. Meng, Y. Dong, and H. Ma, “Comparison between image texture and polarization features in histopathology,” Biomedical Optics Express, vol. 12, no. 3, pp. 1593–1608, 2021.
  29. K. Sindhoora, K. Spandana, D. Ivanov, E. Borisova, U. Raghavendra, S. Rai, S. Kabekkodu, K. Mahato, and N. Mazumder, “Machine-learning-based classification of stokes-mueller polarization images for tissue characterization,” in Journal of Physics: Conference Series, vol. 1859, no. 1.   IOP Publishing, 2021, p. 012045.
  30. X. Zhou, L. Ma, W. Brown, J. V. Little, A. Y. Chen, L. L. Myers, B. D. Sumer, and B. Fei, “Automatic detection of head and neck squamous cell carcinoma on pathologic slides using polarized hyperspectral imaging and machine learning,” in Medical Imaging 2021: Digital Pathology, vol. 11603.   SPIE, 2021, pp. 165–173.
  31. Y. Dong, J. Wan, X. Wang, J.-H. Xue, J. Zou, H. He, P. Li, A. Hou, and H. Ma, “A polarization-imaging-based machine learning framework for quantitative pathological diagnosis of cervical precancerous lesions,” IEEE Transactions on Medical Imaging, vol. 40, no. 12, pp. 3728–3738, 2021.
  32. Y. Chen, Y. Dong, L. Si, W. Yang, S. Du, X. Tian, C. Li, Q. Liao, and H. Ma, “Dual polarization modality fusion network for assisting pathological diagnosis,” IEEE Transactions on Medical Imaging, vol. 42, no. 1, pp. 304–316, 2022.
  33. Y. Yao, M. Zuo, Y. Dong, L. Shi, Y. Zhu, L. Si, X. Ye, and H. Ma, “Polarization imaging feature characterization of different endometrium phases by machine learning,” OSA Continuum, vol. 4, no. 6, pp. 1776–1791, 2021.
  34. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Advances in neural information processing systems, vol. 25, 2012.
  35. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  36. Y. Zhao, M. Reda, K. Feng, P. Zhang, G. Cheng, Z. Ren, S. G. Kong, S. Su, H. Huang, and J. Zang, “Detecting giant cell tumor of bone lesions using mueller matrix polarization microscopic imaging and multi-parameters fusion network,” IEEE Sensors Journal, vol. 20, no. 13, pp. 7208–7215, 2020.
  37. Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspectives,” IEEE transactions on pattern analysis and machine intelligence, vol. 35, no. 8, pp. 1798–1828, 2013.
  38. C. Northcutt, L. Jiang, and I. Chuang, “Confident learning: Estimating uncertainty in dataset labels,” Journal of Artificial Intelligence Research, vol. 70, pp. 1373–1411, 2021.
  39. K. He, X. Zhang, S. Ren, and J. Sun, “Identity mappings in deep residual networks,” in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14.   Springer, 2016, pp. 630–645.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now