Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 43 tok/s
Gemini 2.5 Pro 49 tok/s Pro
GPT-5 Medium 17 tok/s Pro
GPT-5 High 19 tok/s Pro
GPT-4o 96 tok/s Pro
Kimi K2 197 tok/s Pro
GPT OSS 120B 455 tok/s Pro
Claude Sonnet 4 37 tok/s Pro
2000 character limit reached

Leveraging Medical Foundation Model Features in Graph Neural Network-Based Retrieval of Breast Histopathology Images (2405.04211v3)

Published 7 May 2024 in cs.CV

Abstract: Breast cancer is the most common cancer type in women worldwide. Early detection and appropriate treatment can significantly reduce its impact. While histopathology examinations play a vital role in rapid and accurate diagnosis, they often require experienced medical experts for proper recognition and cancer grading. Automated image retrieval systems have the potential to assist pathologists in identifying cancerous tissues, thereby accelerating the diagnostic process. Nevertheless, proposing an accurate image retrieval model is challenging due to considerable variability among the tissue and cell patterns in histological images. In this work, we leverage the features from foundation models in a novel attention-based adversarially regularized variational graph autoencoder model for breast histological image retrieval. Our results confirm the superior performance of models trained with foundation model features compared to those using pre-trained convolutional neural networks (up to 7.7% and 15.5% for mAP and mMV, respectively), with the pre-trained general-purpose self-supervised model for computational pathology (UNI) delivering the best overall performance. By evaluating two publicly available histology image datasets of breast cancer, our top-performing model, trained with UNI features, achieved average mAP/mMV scores of 96.7%/91.5% and 97.6%/94.2% for the BreakHis and BACH datasets, respectively. Our proposed retrieval model has the potential to be used in clinical settings to enhance diagnostic performance and ultimately benefit patients.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. doi:https://doi.org/10.1007/s10916-021-01786-9.
  2. doi:https://doi.org/10.1016/j.breast.2022.08.010.
  3. doi:https://doi.org/10.3322/caac.21824.
  4. doi:https://doi.org/10.1109/ISITIA52817.2021.9502205.
  5. doi:https://doi.org/10.1093/annonc/mdz235.
  6. doi:https://doi.org/10.1109/IVMSP54334.2022.9816325.
  7. doi:https://doi.org/10.1109/IVMSP54334.2022.9816352.
  8. doi:https://doi.org/10.1007/978-981-16-8892-8_33.
  9. doi:https://doi.org/10.1109/TPAMI.2018.2889473.
  10. doi:https://doi.org/10.1016/J.MEDIA.2017.09.007.
  11. doi:https://doi.org/10.1038/s41746-019-0131-z.
  12. doi:https://doi.org/10.1016/j.cmpb.2020.105637.
  13. doi:https://doi.org/10.1007/978-3-030-32239-7_61.
  14. doi:https://doi.org/10.1038/s41551-022-00929-8.
  15. doi:https://doi.org/10.2967/jnumed.123.266080.
  16. doi:https://doi.org/10.1007/s13244-018-0639-9.
  17. doi:https://doi.org/10.24963/ijcai.2018/362.
  18. doi:https://doi.org/10.1088/1742-6596/2171/1/012068.
  19. doi:https://doi.org/10.1109/TKDE.2022.3150300.
  20. doi:https://doi.org/10.1109/ACCESS.2020.3018033.
  21. doi:https://doi.org/10.1016/j.knosys.2023.110456.
  22. doi:https://doi.org/10.1016/j.media.2022.102645.
  23. doi:https://doi.org/10.1109/TBME.2015.2496264.
  24. doi:https://doi.org/10.1016/j.media.2019.05.010.
  25. doi:https://doi.org/10.1016/j.compeleceng.2022.108450.
  26. doi:https://doi.org/10.1136/gutjnl-2023-329512.
  27. doi:https://doi.org/10.1109/ICAISS58487.2023.10250462.
  28. doi:https://doi.org/10.3390/app122211375.
  29. doi:https://doi.org/10.3390/diagnostics12051152.
  30. doi:https://doi.org/10.1007/978-3-030-68763-2_26.
  31. doi:https://doi.org/10.1109/ICSCN.2017.8085676.
  32. doi:https://doi.org/10.1016/J.MEDIA.2020.101757.
  33. doi:https://doi.org/10.1109/CVPR.2009.5206848.
  34. doi:https://doi.org/10.3390/s21144758.
  35. doi:https://doi.org/10.1117/12.2550114.
  36. doi:https://doi.org/10.1016/j.compmedimag.2021.102027.
  37. doi:https://doi.org/10.1016/j.media.2019.101563.
  38. doi:https://doi.org/10.3389/fmed.2022.978146.
  39. doi:https://doi.org/10.1109/TMI.2018.2796130.
  40. doi:https://doi.org/10.1109/CVPR.2018.00474.
  41. doi:https://doi.org/10.1109/CVPR.2017.243.
  42. doi:https://doi.org/10.1109/CVPR.2017.195.
  43. doi:https://doi.org/10.1109/CVPR.2016.308.
  44. doi:https://doi.org/10.1109/CVPR.2018.00907.
  45. arXiv:2004.07399, doi:https://doi.org/10.1109/CVPRW50498.2020.00502.
  46. doi:https://doi.org/10.3390/e25040567.
  47. doi:https://doi.org/10.1109/TMI.2020.3046636.
  48. doi:https://doi.org/10.1109/JBHI.2022.3153671.
  49. doi:https://doi.org/10.1016/j.media.2021.102308.
  50. doi:https://doi.org/10.1109/tnnls.2020.2978386.
  51. doi:https://doi.org/10.1016/j.eswa.2021.115649.
  52. doi:https://doi.org/10.1016/j.neunet.2022.05.026.
  53. doi:https://doi.org/10.1109/TBDATA.2019.2921572.
  54. doi:https://doi.org/10.1038/s41598-020-61808-3.
  55. doi:https://doi.org/10.1016/j.csbj.2023.12.042.
Citations (1)
View on Semantic Scholar
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

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

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

Follow-Up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets