Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 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

Resource-Limited Automated Ki67 Index Estimation in Breast Cancer (2401.00014v1)

Published 22 Dec 2023 in q-bio.QM, cs.CV, cs.LG, and eess.IV

Abstract: The prediction of tumor progression and chemotherapy response has been recently tackled exploiting Tumor Infiltrating Lymphocytes (TILs) and the nuclear protein Ki67 as prognostic factors. Recently, deep neural networks (DNNs) have been shown to achieve top results in estimating Ki67 expression and simultaneous determination of intratumoral TILs score in breast cancer cells. However, in the last ten years the extraordinary progress induced by deep models proliferated at least as much as their resource demand. The exorbitant computational costs required to query (and in some cases also to store) a deep model represent a strong limitation in resource-limited contexts, like that of IoT-based applications to support healthcare personnel. To this end, we propose a resource consumption-aware DNN for the effective estimate of the percentage of Ki67-positive cells in breast cancer screenings. Our approach reduced up to 75% and 89% the usage of memory and disk space respectively, up to 1.5x the energy consumption, and preserved or improved the overall accuracy of a benchmark state-of-the-art solution. Encouraged by such positive results, we developed and structured the adopted framework so as to allow its general purpose usage, along with a public software repository to support its usage.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. I-Health: Leveraging Edge Computing and Blockchain for Epidemic Management. ArXiv abs/2012.14294 (2020).
  2. Computer-aided diagnosis for breast cancer classification using deep neural networks and transfer learning. Comput. Methods. Programs. Biomed. 223 (2022), 106951.
  3. Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers. In Advances in Neural Inf. Process. Syst., Vol. 32. Curran Associates, Inc.
  4. Deep learning. Vol. 1. MIT press, Massachusetts, USA.
  5. PathML: A unified framework for whole-slide image analysis with deep learning. medRxiv (2021). https://doi.org/10.1101/2021.07.07.21260138
  6. Universal Deep Neural Network Compression. IEEE J. Sel. Topics Signal Process. 14, 4 (2020), 715–726.
  7. Entropy-constrained vector quantization. IEEE Trans. Acoust.  Speech, Signal Process. 37, 1 (1989), 31–42.
  8. Interobserver variability of Ki-67 measurement in breast cancer. J. Pathol. Transl. Med. 50, 2 (2016), 129.
  9. Intra-and interobserver reproducibility assessment of PD-L1 biomarker in Non–Small cell lung cancer. Clin. Cancer Res. 23, 16 (2017), 4569–4577.
  10. Survey of deep learning in breast cancer image analysis. Evolving Systems 11 (2020), 143–163.
  11. Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey. Proc. IEEE 108, 4 (2020), 485–532.
  12. Assessment of Ki67 in breast cancer: recommendations from the International Ki67 in Breast Cancer working group. J. Natl. Cancer Inst. 103, 22 (2011), 1656–1664.
  13. Medical deep learning–a systematic meta-review. Comput. Methods Programs Biomed. (2022), 106874.
  14. U-Net: deep learning for cell counting, detection, and morphometry. Nat. Methods 16, 1 (2019), 67–70.
  15. Current prognostic and predictive biomarkers for gastrointestinal tumors in clinical practice. Pathologica 112, 3 (2020), 248.
  16. Assessment of Ki-67 proliferation index with deep learning in DCIS (ductal carcinoma in situ). Sci. Rep. 12, 1 (2022), 3166.
  17. Pembrolizumab plus chemotherapy in metastatic non–small-cell lung cancer. N. Engl. J. Med. 378, 22 (2018), 2078–2092.
  18. An m-health application for cerebral stroke detection and monitoring using cloud services. Int. J. Inf. Manag. 45 (2019), 319–327.
  19. H Gish and J Pierce. 1968. Asymptotically efficient quantizing. IEEE Trans. Inf. Theory 14, 5 (1968), 676–683.
  20. Inter-observer variability between general pathologists and a specialist in breast pathology in the diagnosis of lobular neoplasia, columnar cell lesions, atypical ductal hyperplasia and ductal carcinoma in situ of the breast. Diagn. Pathol. 9, 1 (2014), 1–9.
  21. Jonathan Guo and Bin Li. 2018. The Application of Medical Artificial Intelligence Technology in Rural Areas of Developing Countries. Health Equity 2, 1 (2018), 174–181. PMID: 30283865.
  22. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings. San Juan, Puerto Rico. http://arxiv.org/abs/1510.00149
  23. Integrating digital pathology into clinical practice. Mod. Pathol. 35, 2 (Oct 2021), 152–164.
  24. Breast cancer. Nat. Rev. Dis. Primers 5, 1 (2019), 1–31.
  25. Effect of the pixel interpolation method for downsampling medical images on deep learning accuracy. J. comput. commun. 9, 11 (2021).
  26. Sebastian Klein and Dan G Duda. 2021. Machine Learning for Future Subtyping of the Tumor Microenvironment of Gastro-Esophageal Adenocarcinomas. Cancers 13, 19 (2021), 4919.
  27. Deep Learning of Histopathology Images at the Single Cell Level. Front. Artif. Intell. 4 (2021), 137.
  28. A systematic collection of medical image datasets for deep learning. arXiv preprint arXiv:2106.12864 (2021).
  29. Federated Learning: Challenges, Methods, and Future Directions. IEEE Signal Process. Mag. 37, 3 (2020), 50–60.
  30. Action2Activity: Recognizing Complex Activities from Sensor Data. In Proceedings of the 24th International Conference on Artificial Intelligence (Buenos Aires, Argentina) (IJCAI’15). AAAI Press, 1617–1623.
  31. The prognostic value of tumor-infiltrating lymphocytes in breast cancer: a systematic review and meta-analysis. PloS ONE 11, 4 (2016), e0152500.
  32. Giosuè Cataldo Marinò et al. 2021. Reproducing the Sparse Huffman Address Map Compression for Deep Neural Networks. In Reproducible Research in Pattern Recognition. Springer International Publishing, Cham, 161–166.
  33. Giosuè Cataldo Marinò et al. 2021. Compression strategies and space-conscious representations for deep neural networks. In 2020 25th Int. Conf. on Pattern Recognition (ICPR). IEEE, Milan, Italy, 9835–9842.
  34. Deep neural networks compression: A comparative survey and choice recommendations. Neurocomputing 520 (2023), 152–170.
  35. J. B. McQueen. 1967. Some methods of classification and analysis in multivariate observations. In Proc. of fifth Barkley symp. on math. statist. and prob. 281–297.
  36. Effective active learning in digital pathology: A case study in tumor infiltrating lymphocytes. Comput. Methods Programs Biomed. 220 (2022), 106828.
  37. A comprehensive survey on deep-learning-based breast cancer diagnosis. Cancers 13, 23 (2021), 6116.
  38. Multi-class breast cancer classification using deep learning convolutional neural network. Int. J. Adv. Comput. Sci. Appl 9, 6 (2018), 316–332.
  39. PathoNet introduced as a deep neural network backend for evaluation of Ki-67 and tumor-infiltrating lymphocytes in breast cancer. Sci. Rep. 11, 1 (2021), 1–13.
  40. The history of pathology informatics: A global perspective. J. Pathol. Inform. 4 (2013), 7.
  41. Gil Patrus Pena and Joséde Souza Andrade-Filho. 2009. How does a pathologist make a diagnosis? Arch. Pathol. Lab. Med. 133, 1 (2009), 124–132.
  42. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res. 21, 1, Article 140 (jan 2020), 67 pages.
  43. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Springer International Publishing, Cham, 234–241.
  44. An advanced deep learning approach for Ki-67 stained hotspot detection and proliferation rate scoring for prognostic evaluation of breast cancer. Sci. Rep. 7, 1 (2017), 3213.
  45. The evaluation of tumor-infiltrating lymphocytes (TILs) in breast cancer: recommendations by an International TILs Working Group 2014. Ann. Oncol. 26, 2 (2015), 259–271.
  46. A dataset for breast cancer histopathological image classification. IEEE Trans. Biomed. Eng. 63, 7 (2015), 1455–1462.
  47. Sasha E Stanton and Mary L Disis. 2016. Clinical significance of tumor-infiltrating lymphocytes in breast cancer. J. ImmunoTher. Cancer 4, 1 (2016), 1–7.
  48. Classical and novel prognostic markers for breast cancer and their clinical significance. Clin. Med. Insights: Oncol. 4 (2010).
  49. Ki-67 labeling index is a predictive marker for a pathological complete response to neoadjuvant chemotherapy in breast cancer: a meta-analysis. Medicine 96, 51 (2017), e9384.
  50. Dual-scale categorization based deep learning to evaluate programmed cell death ligand 1 expression in non-small cell lung cancer. Medicine 100, 20 (2021), p e25994.
  51. Deep learning based analysis of histopathological images of breast cancer. Front. Genet. 10 (2019), 80.
  52. Machine Learning and Artificial Intelligence-driven Spatial Analysis of the Tumor Immune Microenvironment in Pathology Slides. Eur. Urol. Focus 7, 4 (Jul 2021), 706–709.
  53. Cell counting by regression using convolutional neural network. In Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part I 14. Springer, Springer, Cham, Amsterdam, The Netherlands, 274–290.
  54. Tumor cell identification in ki-67 images on deep learning. Mol. Cell. Biol. 15, 3 (2018), 177.
  55. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR).
  56. An extended type cell detection and counting method based on FCN. In 2017 IEEE 17th Int. Conf. on Bioinformatics and Bioengineering (BIBE). IEEE, Washington, DC, USA, 51–56.
  57. Independent prognostic value of intratumoral heterogeneity and immune response features by automated digital immunohistochemistry analysis in early hormone receptor-positive breast carcinoma. Front. Oncol. 10 (2020), 950.

Summary

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

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