Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Case-level Breast Cancer Prediction for Real Hospital Settings (2310.12677v2)

Published 19 Oct 2023 in cs.CV

Abstract: Breast cancer prediction models for mammography assume that annotations are available for individual images or regions of interest (ROIs), and that there is a fixed number of images per patient. These assumptions do not hold in real hospital settings, where clinicians provide only a final diagnosis for the entire mammography exam (case). Since data in real hospital settings scales with continuous patient intake, while manual annotation efforts do not, we develop a framework for case-level breast cancer prediction that does not require any manual annotation and can be trained with case labels readily available at the hospital. Specifically, we propose a two-level multi-instance learning (MIL) approach at patch and image level for case-level breast cancer prediction and evaluate it on two public and one private dataset. We propose a novel domain-specific MIL pooling observing that breast cancer may or may not occur in both sides, while images of both breasts are taken as a precaution during mammography. We propose a dynamic training procedure for training our MIL framework on a variable number of images per case. We show that our two-level MIL model can be applied in real hospital settings where only case labels, and a variable number of images per case are available, without any loss in performance compared to models trained on image labels. Only trained with weak (case-level) labels, it has the capability to point out in which breast side, mammography view and view region the abnormality lies.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. World Health Organization, “Cancer,” https://www.who.int/news-room/fact-sheets/detail/cancer, 2022, accessed: 15/06/2023.
  2. L. Tabár, B. Vitak, H.-H. T. Chen, M.-F. Yen, S. W. Duffy, and R. A. Smith, “Beyond randomized controlled trials: organized mammographic screening substantially reduces breast carcinoma mortality,” Cancer: Interdisciplinary International Journal of the American Cancer Society, vol. 91, no. 9, pp. 1724–1731, 2001.
  3. L. Tabár, B. Vitak, T. H.-H. Chen, A. M.-F. Yen, A. Cohen, T. Tot, S. Y.-H. Chiu, S. L.-S. Chen, J. C.-Y. Fann, J. Rosell et al., “Swedish two-county trial: impact of mammographic screening on breast cancer mortality during 3 decades,” Radiology-Radiological Society of North America, vol. 260, no. 3, p. 658, 2011.
  4. L. Shen, L. R. Margolies, J. H. Rothstein, E. Fluder, R. McBride, and W. Sieh, “Deep learning to improve breast cancer detection on screening mammography,” Scientific reports, vol. 9, no. 1, pp. 1–12, 2019.
  5. N. Wu, J. Phang, J. Park, Y. Shen, Z. Huang, M. Zorin, S. Jastrzebski, T. Févry, J. Katsnelson, E. Kim, S. Wolfson, U. Parikh, S. Gaddam, L. L. Y. Lin, K. Ho, J. D. Weinstein, B. Reig, Y. Gao, H. Toth, K. Pysarenko, A. Lewin, J. Lee, K. Airola, E. Mema, S. Chung, E. Hwang, N. Samreen, S. G. Kim, L. Heacock, L. Moy, K. Cho, and K. J. Geras, “Deep neural networks improve radiologists’ performance in breast cancer screening,” IEEE Transactions on Medical Imaging, vol. 39, no. 4, p. 1184–1194, Apr 2020.
  6. T. Kyono, F. J. Gilbert, and M. van der Schaar, “Improving workflow efficiency for mammography using machine learning,” Journal of the American College of Radiology, vol. 17, no. 1, pp. 56–63, 2020.
  7. X. Shu, L. Zhang, Z. Wang, Q. Lv, and Z. Yi, “Deep neural networks with region-based pooling structures for mammographic image classification,” IEEE transactions on medical imaging, vol. 39, no. 6, pp. 2246–2255, 2020.
  8. Y. Shen, N. Wu, J. Phang, J. Park, K. Liu, S. Tyagi, L. Heacock, S. G. Kim, L. Moy, K. Cho et al., “An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization,” Medical image analysis, vol. 68, p. 101908, 2021.
  9. A. Rampun, B. W. Scotney, P. J. Morrow, and H. Wang, “Breast mass classification in mammograms using ensemble convolutional neural networks,” in 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom).   IEEE, 2018, pp. 1–6.
  10. Z. Wang, L. Zhang, X. Shu, Q. Lv, and Z. Yi, “An end-to-end mammogram diagnosis: A new multi-instance and multiscale method based on single-image feature,” IEEE Transactions on Cognitive and Developmental Systems, vol. 13, no. 3, p. 535–545, Sep 2021.
  11. D. Lévy and A. Jain, “Breast mass classification from mammograms using deep convolutional neural networks,” arXiv:1612.00542 [cs], Dec 2016, arXiv: 1612.00542.
  12. W. Zhu, Q. Lou, Y. S. Vang, and X. Xie, “Deep multi-instance networks with sparse label assignment for whole mammogram classification,” in International conference on medical image computing and computer-assisted intervention.   Springer, 2017, pp. 603–611.
  13. C. Zhang, J. Zhao, J. Niu, and D. Li, “New convolutional neural network model for screening and diagnosis of mammograms,” PLoS One, vol. 15, no. 8, p. e0237674, 2020.
  14. A. Akselrod-Ballin, M. Chorev, Y. Shoshan, A. Spiro, A. Hazan, R. Melamed, E. Barkan, E. Herzel, S. Naor, E. Karavani et al., “Predicting breast cancer by applying deep learning to linked health records and mammograms,” Radiology, vol. 292, no. 2, pp. 331–342, 2019.
  15. E.-K. Kim, H.-E. Kim, K. Han, B. J. Kang, Y.-M. Sohn, O. H. Woo, and C. W. Lee, “Applying data-driven imaging biomarker in mammography for breast cancer screening: preliminary study,” Scientific reports, vol. 8, no. 1, pp. 1–8, 2018.
  16. G. Carneiro, J. Nascimento, and A. P. Bradley, “Unregistered multiview mammogram analysis with pre-trained deep learning models,” in International Conference on Medical Image Computing and Computer-Assisted Intervention.   Springer, 2015, pp. 652–660.
  17. K. Liu, Y. Shen, N. Wu, J. Chłędowski, C. Fernandez-Granda, and K. J. Geras, “Weakly-supervised high-resolution segmentation of mammography images for breast cancer diagnosis,” Proceedings of machine learning research, vol. 143, p. 268, 2021.
  18. K. Rangarajan, A. Gupta, S. Dasgupta, U. Marri, A. K. Gupta, S. Hari, S. Banerjee, and C. Arora, “Ultra-high resolution, multi-scale, context-aware approach for detection of small cancers on mammography,” Scientific Reports, vol. 12, no. 1, p. 11622, 2022.
  19. L. Tsochatzidis, L. Costaridou, and I. Pratikakis, “Deep learning for breast cancer diagnosis from mammograms—a comparative study,” Journal of Imaging, vol. 5, no. 33, p. 37, Mar 2019.
  20. D. A. Ragab, O. Attallah, M. Sharkas, J. Ren, and S. Marshall, “A framework for breast cancer classification using multi-dcnns,” Computers in Biology and Medicine, vol. 131, p. 104245, 2021.
  21. H. N. Khan, A. R. Shahid, B. Raza, A. H. Dar, and H. Alquhayz, “Multi-view feature fusion based four views model for mammogram classification using convolutional neural network,” IEEE Access, vol. 7, pp. 165 724–165 733, 2019.
  22. T. Wei, A. I. Aviles-Rivero, S. Wang, Y. Huang, F. J. Gilbert, C.-B. Schönlieb, and C. W. Chen, “Beyond fine-tuning: Classifying high resolution mammograms using function-preserving transformations,” Medical Image Analysis, vol. 82, p. 102618, 2022.
  23. D. G. Petrini, C. Shimizu, R. A. Roela, G. V. Valente, M. A. A. K. Folgueira, and H. Y. Kim, “Breast cancer diagnosis in two-view mammography using end-to-end trained efficientnet-based convolutional network,” Ieee Access, vol. 10, pp. 77 723–77 731, 2022.
  24. G. Quellec, M. Lamard, M. Cozic, G. Coatrieux, and G. Cazuguel, “Multiple-instance learning for anomaly detection in digital mammography,” Ieee transactions on medical imaging, vol. 35, no. 7, pp. 1604–1614, 2016.
  25. S. M. McKinney, M. Sieniek, V. Godbole, J. Godwin, N. Antropova, H. Ashrafian, T. Back, M. Chesus, G. S. Corrado, A. Darzi et al., “International evaluation of an ai system for breast cancer screening,” Nature, vol. 577, no. 7788, pp. 89–94, 2020.
  26. T. G. Dietterich, R. H. Lathrop, and T. Lozano-Pérez, “Solving the multiple instance problem with axis-parallel rectangles,” Artificial intelligence, vol. 89, no. 1-2, pp. 31–71, 1997.
  27. O. Maron and T. Lozano-Pérez, “A framework for multiple-instance learning,” Advances in neural information processing systems, vol. 10, 1997.
  28. S. Andrews, I. Tsochantaridis, and T. Hofmann, “Support vector machines for multiple-instance learning,” Advances in neural information processing systems, vol. 15, 2002.
  29. C. Zhang, J. Platt, and P. Viola, “Multiple instance boosting for object detection,” Advances in neural information processing systems, vol. 18, 2005.
  30. R. Sawyer-Lee, F. Gimenez, A. Hoogi, and D. Rubin, “Curated breast imaging subset of digital database for screening mammography (cbis-ddsm) (version 1) [data set],” 2016, accessed: 28/04/2022. [Online]. Available: https://doi.org/10.7937/K9/TCIA.2016.7O02S9CY
  31. M. Heath, K. Bowyer, D. Kopans, P. Kegelmeyer Jr, R. Moore, K. Chang, and S. Munishkumaran, “Current status of the digital database for screening mammography,” in Digital Mammography: Nijmegen, 1998.   Springer, 1998, pp. 457–460.
  32. H. T. Nguyen, H. Q. Nguyen, H. H. Pham, K. Lam, L. T. Le, M. Dao, and V. Vu, “Vindr-mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography,” medRxiv, 2022.
  33. D. Ribli, A. Horváth, Z. Unger, P. Pollner, and I. Csabai, “Detecting and classifying lesions in mammograms with deep learning,” Scientific reports, vol. 8, no. 1, p. 4165, 2018.
  34. R. Agarwal, O. Diaz, X. Lladó, M. H. Yap, and R. Martí, “Automatic mass detection in mammograms using deep convolutional neural networks,” Journal of Medical Imaging, vol. 6, no. 3, pp. 031 409–031 409, 2019.
  35. T. Hu, L. Zhang, L. Xie, and Z. Yi, “A multi-instance networks with multiple views for classification of mammograms,” Neurocomputing, vol. 443, pp. 320–328, 2021.
  36. E. Raff, “A step toward quantifying independently reproducible machine learning research,” Advances in Neural Information Processing Systems, vol. 32, 2019.
  37. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” CoRR, vol. abs/1512.03385, 2015.
  38. M. Ilse, J. Tomczak, and M. Welling, “Attention-based deep multiple instance learning,” in International conference on machine learning.   PMLR, 2018, pp. 2127–2136.
  39. Y. Chen, J. Bi, and J. Z. Wang, “Miles: Multiple-instance learning via embedded instance selection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 1931–1947, 2006.
  40. X.-S. Wei, J. Wu, and Z.-H. Zhou, “Scalable algorithms for multi-instance learning,” IEEE transactions on neural networks and learning systems, vol. 28, no. 4, pp. 975–987, 2016.
  41. J. Foulds and E. Frank, “A review of multi-instance learning assumptions,” The Knowledge Engineering Review, vol. 25, no. 1, p. 1–25, Mar 2010.
  42. J. Amores, “Multiple instance classification: Review, taxonomy and comparative study,” Artificial intelligence, vol. 201, pp. 81–105, 2013.
  43. X. Wang, Y. Yan, P. Tang, X. Bai, and W. Liu, “Revisiting multiple instance neural networks,” Pattern Recognition, vol. 74, pp. 15–24, 2018.
  44. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” 2017.
  45. E. A. Sickles, C. J. D’Orsi, L. W. Bassett, C. M. Appleton, W. A. Berg, E. S. Burnside et al., “Acr bi-rads® mammography,” ACR BI-RADS® atlas, breast imaging reporting and data system, vol. 5, p. 2013, 2013.
  46. D. Ulmer, E. Bassignana, M. Müller-Eberstein, D. Varab, M. Zhang, R. van der Goot, C. Hardmeier, and B. Plank, “Experimental standards for deep learning in natural language processing research,” in Findings of the Association for Computational Linguistics: EMNLP 2022.   Association for Computational Linguistics, Dec 2022, p. 2673–2692.
Citations (2)
View on Semantic Scholar

Summary

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

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