Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

LESS: Label-efficient Multi-scale Learning for Cytological Whole Slide Image Screening (2306.03407v2)

Published 6 Jun 2023 in eess.IV and cs.CV

Abstract: In computational pathology, multiple instance learning (MIL) is widely used to circumvent the computational impasse in giga-pixel whole slide image (WSI) analysis. It usually consists of two stages: patch-level feature extraction and slide-level aggregation. Recently, pretrained models or self-supervised learning have been used to extract patch features, but they suffer from low effectiveness or inefficiency due to overlooking the task-specific supervision provided by slide labels. Here we propose a weakly-supervised Label-Efficient WSI Screening method, dubbed LESS, for cytological WSI analysis with only slide-level labels, which can be effectively applied to small datasets. First, we suggest using variational positive-unlabeled (VPU) learning to uncover hidden labels of both benign and malignant patches. We provide appropriate supervision by using slide-level labels to improve the learning of patch-level features. Next, we take into account the sparse and random arrangement of cells in cytological WSIs. To address this, we propose a strategy to crop patches at multiple scales and utilize a cross-attention vision transformer (CrossViT) to combine information from different scales for WSI classification. The combination of our two steps achieves task-alignment, improving effectiveness and efficiency. We validate the proposed label-efficient method on a urine cytology WSI dataset encompassing 130 samples (13,000 patches) and FNAC 2019 dataset with 212 samples (21,200 patches). The experiment shows that the proposed LESS reaches 84.79%, 85.43%, 91.79% and 78.30% on a urine cytology WSI dataset, and 96.88%, 96.86%, 98.95%, 97.06% on FNAC 2019 dataset in terms of accuracy, AUC, sensitivity and specificity. It outperforms state-of-the-art MIL methods on pathology WSIs and realizes automatic cytological WSI cancer screening.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (73)
  1. Deep learning based digital cell profiles for risk stratification of urine cytology images. Cytometry Part A 99, 732–742.
  2. Layer normalization. arXiv preprint arXiv:1607.06450 .
  3. Experiment tracking with weights and biases. URL: https://www.wandb.com/. software available from wandb.com.
  4. Semi-supervised novelty detection. The Journal of Machine Learning Research 11, 2973–3009.
  5. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nature medicine 25, 1301–1309.
  6. A novel attention-guided convolutional network for the detection of abnormal cervical cells in cervical cancer screening. Medical image analysis 73, 102197.
  7. Emerging properties in self-supervised vision transformers, in: Proceedings of the IEEE/CVF international conference on computer vision, pp. 9650–9660.
  8. Automatic cervical cell segmentation and classification in pap smears. Computer methods and programs in biomedicine 113, 539–556.
  9. Crossvit: Cross-attention multi-scale vision transformer for image classification, in: Proceedings of the IEEE/CVF international conference on computer vision, pp. 357–366.
  10. A variational approach for learning from positive and unlabeled data. Advances in Neural Information Processing Systems 33, 14844–14854.
  11. Scaling vision transformers to gigapixel images via hierarchical self-supervised learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16144–16155.
  12. Self-supervised vision transformers learn visual concepts in histopathology. arXiv preprint arXiv:2203.00585 .
  13. A simple framework for contrastive learning of visual representations, in: International conference on machine learning, PMLR. pp. 1597–1607.
  14. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 .
  15. Robust whole slide image analysis for cervical cancer screening using deep learning. Nature communications 12, 5639.
  16. An analysis of single-layer networks in unsupervised feature learning, in: Proceedings of the fourteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings. pp. 215–223.
  17. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nature medicine 24, 1559–1567.
  18. Effect of study design and quality on unsatisfactory rates, cytology classifications, and accuracy in liquid-based versus conventional cervical cytology: a systematic review. The Lancet 367, 122–132.
  19. Self-supervision closes the gap between weak and strong supervision in histology. arXiv preprint arXiv:2012.03583 .
  20. Imagenet: A large-scale hierarchical image database, in: 2009 IEEE conference on computer vision and pattern recognition, Ieee. pp. 248–255.
  21. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 .
  22. Basic and advanced laboratory techniques in histopathology and cytology. Springer.
  23. Solving the multiple instance problem with axis-parallel rectangles. Artificial intelligence 89, 31–71.
  24. Optimal z-axis scanning parameters for gynecologic cytology specimens. Journal of pathology informatics 4, 38.
  25. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 .
  26. Analysis of learning from positive and unlabeled data. Advances in neural information processing systems 27.
  27. Uci machine learning repository .
  28. High-magnification multi-views based classification of breast fine needle aspiration cytology cell samples using fusion of decisions from deep convolutional networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 76–81.
  29. Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778.
  30. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 .
  31. Generative adversarial positive-unlabelled learning. arXiv preprint arXiv:1711.08054 .
  32. Attention-based deep multiple instance learning, in: International conference on machine learning, PMLR. pp. 2127–2136.
  33. Deep learning for computational cytology: A survey. Medical Image Analysis , 102691.
  34. A survey on deep learning-based cervical cytology screening: from cell identification to whole slide image analysis .
  35. Positive-unlabeled learning with non-negative risk estimator. Advances in neural information processing systems 30.
  36. Achievements and limitations of cervical cytology screening. Vaccine 24, S63–S70.
  37. Learning multiple layers of features from tiny images .
  38. Deep multi-scale u-net architecture and label-noise robust training strategies for histopathological image segmentation, in: 2022 IEEE 22nd International Conference on Bioinformatics and Bioengineering (BIBE), IEEE. pp. 91–96.
  39. Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 14318–14328.
  40. Hybrid supervision learning for pathology whole slide image classification, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VIII, Springer. pp. 309–318.
  41. Graph cnn for survival analysis on whole slide pathological images, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 174–182.
  42. Sensitivity and specificity of commonly available bladder tumor markers versus cytology: results of a comprehensive literature review and meta-analyses. Urology 61, 109–118.
  43. Data-efficient and weakly supervised computational pathology on whole-slide images. Nature biomedical engineering 5, 555–570.
  44. A framework for multiple-instance learning. Advances in neural information processing systems 10.
  45. The efficacy of oral brush biopsy with computer-assisted analysis in identifying precancerous and cancerous lesions. Head & neck oncology 3, 1–8.
  46. Advantages and disadvantages of cytology and histopathology for the diagnosis of cancer., in: Seminars in veterinary medicine and surgery (small animal), pp. 222–227.
  47. A deep learning system to diagnose the malignant potential of urothelial carcinoma cells in cytology specimens. Cancer Cytopathology 129, 984–995.
  48. Automated detection of cell nuclei in pap stained cervical smear images using fuzzy clustering, in: 4th European Conference of the International Federation for Medical and Biological Engineering: ECIFMBE 2008 23–27 November 2008 Antwerp, Belgium, Springer. pp. 637–641.
  49. Comparative assessment of cnn architectures for classification of breast fnac images. Tissue and Cell 57, 8–14.
  50. Performance of an artificial intelligence algorithm for reporting urine cytopathology. Cancer Cytopathology 127, 658–666.
  51. Modeling relational data with graph convolutional networks, in: The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3–7, 2018, Proceedings 15, Springer. pp. 593–607.
  52. Transmil: Transformer based correlated multiple instance learning for whole slide image classification. Advances in neural information processing systems 34, 2136–2147.
  53. Diagnostic value of a comprehensive, urothelial carcinoma–specific next-generation sequencing panel in urine cytology and bladder tumor specimens. Cancer Cytopathology 129, 537–547.
  54. Automated classification of lung cancer types from cytological images using deep convolutional neural networks. BioMed research international 2017.
  55. High-accuracy prostate cancer pathology using deep learning. Nature Machine Intelligence 2, 411–418.
  56. Attention is all you need. Advances in neural information processing systems 30.
  57. Annotation-free deep learning-based prediction of thyroid molecular cancer biomarker braf (v600e) from cytological slides. International Journal of Molecular Sciences 24, 2521.
  58. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 .
  59. Multi-positive and unlabeled learning., in: IJCAI, pp. 3182–3188.
  60. Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks. Medical Image Analysis 65, 101789.
  61. Local-to-global spatial learning for whole-slide image representation and classification. Computerized Medical Imaging and Graphics , 102230.
  62. Anatomy-guided weakly-supervised abnormality localization in chest x-rays, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part V, Springer. pp. 658–668.
  63. Multi-scale enhanced graph convolutional network for early mild cognitive impairment detection, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part VII 23, Springer. pp. 228–237.
  64. Deep hybrid architectures for binary classification of medical breast cancer images. Biomedical Signal Processing and Control 71, 103226.
  65. Classifying breast cytological images using deep learning architectures., in: HEALTHINF, pp. 557–564.
  66. Positive and unlabeled learning with label disambiguation., in: IJCAI, pp. 4250–4256.
  67. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 .
  68. Dtfd-mil: Double-tier feature distillation multiple instance learning for histopathology whole slide image classification, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18802–18812.
  69. Whole slide cervical cancer screening using graph attention network and supervised contrastive learning, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part II, Springer. pp. 202–211.
  70. Predicting lymph node metastasis using histopathological images based on multiple instance learning with deep graph convolution, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4837–4846.
  71. Positive-unlabeled learning for cell detection in histopathology images with incomplete annotations, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VIII 24, Springer. pp. 509–518.
  72. Wsisa: Making survival prediction from whole slide histopathological images, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7234–7242.
  73. Learning from only positive and unlabeled data to detect lesions in vascular ct images, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2011: 14th International Conference, Toronto, Canada, September 18-22, 2011, Proceedings, Part III 14, Springer. pp. 9–16.

Summary

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

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