Papers
Topics
Authors
Recent
AI Research Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and 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 79 tok/s
Gemini 2.5 Pro 30 tok/s Pro
GPT-5 Medium 29 tok/s Pro
GPT-5 High 25 tok/s Pro
GPT-4o 116 tok/s Pro
Kimi K2 191 tok/s Pro
GPT OSS 120B 468 tok/s Pro
Claude Sonnet 4 36 tok/s Pro
2000 character limit reached

Coupling AI and Citizen Science in Creation of Enhanced Training Dataset for Medical Image Segmentation (2409.03087v1)

Published 4 Sep 2024 in eess.IV and cs.CV

Abstract: Recent advancements in medical imaging and AI have greatly enhanced diagnostic capabilities, but the development of effective deep learning (DL) models is still constrained by the lack of high-quality annotated datasets. The traditional manual annotation process by medical experts is time- and resource-intensive, limiting the scalability of these datasets. In this work, we introduce a robust and versatile framework that combines AI and crowdsourcing to improve both the quality and quantity of medical image datasets across different modalities. Our approach utilises a user-friendly online platform that enables a diverse group of crowd annotators to label medical images efficiently. By integrating the MedSAM segmentation AI with this platform, we accelerate the annotation process while maintaining expert-level quality through an algorithm that merges crowd-labelled images. Additionally, we employ pix2pixGAN, a generative AI model, to expand the training dataset with synthetic images that capture realistic morphological features. These methods are combined into a cohesive framework designed to produce an enhanced dataset, which can serve as a universal pre-processing pipeline to boost the training of any medical deep learning segmentation model. Our results demonstrate that this framework significantly improves model performance, especially when training data is limited.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. The role of generative adversarial networks in brain mri: a scoping review. Insights into imaging, 13(1):98, 2022.
  2. A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. Journal of Big Data, 10(1):46, 2023.
  3. Generative adversarial networks: An overview. IEEE signal processing magazine, 35(1):53–65, 2018.
  4. Huggin Face Enterprise. Huggin face spaces, 2024. Available at: https://huggingface.co/; Accessed on 17th January 2024.
  5. Gan-based synthetic medical image augmentation for increased cnn performance in liver lesion classification. Neurocomputing, 321:321–331, 2018.
  6. Image annotation and curation in radiology: an overview for machine learning practitioners. European Radiology Experimental, 8(1):11, 2024.
  7. Generative adversarial nets. Advances in neural information processing systems, 27, 2014.
  8. Generative adversarial networks. Communications of the ACM, 63(11):139–144, 2020.
  9. Guest editorial deep learning in medical imaging: Overview and future promise of an exciting new technique. IEEE transactions on medical imaging, 35(5):1153–1159, 2016.
  10. How to collect segmentations for biomedical images? a benchmark evaluating the performance of experts, crowdsourced non-experts, and algorithms. In 2015 IEEE winter conference on applications of computer vision, pages 1169–1176. IEEE, 2015.
  11. Large-scale medical image annotation with crowd-powered algorithms. Journal of Medical Imaging, 5(3):034002–034002, 2018.
  12. Statistical shape models for 3d medical image segmentation: a review. Medical image analysis, 13(4):543–563, 2009.
  13. Amazon Mechanical Turk Inc. Amazon mechanical turk (mturk), 2024. Available at: https://www.mturk.com/; Accessed on 7th April 2024.
  14. Google Inc. Duolingo fraud detection, 2024. Available at: https://www.duolingo.com/; Accessed on 7th April 2024.
  15. Human Signal Inc. Open source data labelling platform, 2023. Available at: https://labelstud.io/; Accessed on 3rd November 2023.
  16. National Cancer Institute. Cip cancer imaging program, cancer imaging archive, 2015. Available at: https://www.cancerimagingarchive.net/; Accessed on 27th December 2023.
  17. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134, 2017.
  18. Segment anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4015–4026, 2023.
  19. Google LLC. Google recaptcha, 2024. Available at: https://www.google.com/recaptcha/about/; Accessed on 7th April 2024.
  20. Appen ltd. Appen figure eight, 2024. Available at: https://www.appen.com/ai-data; Accessed on 7th April 2024.
  21. Jun Ma. Miccai flare22 challenge dataset (50 labeled abdomen ct scans), 2022. Available at: https://zenodo.org/records/7860267; Accessed on 10th December 2023.
  22. Segment anything in medical images. Nature Communications, 15(1):654, 2024.
  23. Can masses of non-experts train highly accurate image classifiers? a crowdsourcing approach to instrument segmentation in laparoscopic images. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2014: 17th International Conference, Boston, MA, USA, September 14-18, 2014, Proceedings, Part II 17, pages 438–445. Springer, 2014.
  24. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014.
  25. Learning data augmentation for brain tumor segmentation with coarse-to-fine generative adversarial networks. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part I 4, pages 70–80. Springer, 2019.
  26. Generative ai for medical imaging analysis and applications. Future Medicine AI, 1(0):FMAI5, 2023.
  27. Crowdsourcing human-based computation for medical image analysis: A systematic literature review. Health Informatics Journal, 26(4):2446–2469, 2020.
  28. Learning from crowds. Journal of machine learning research, 11(4), 2010.
  29. Iqbal H Sarker. Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions. SN Computer Science, 2(6):420, 2021.
  30. A survey on image data augmentation for deep learning. Journal of Big Data, 6(1):60, Jul 2019.
  31. Thorvald Sorensen. A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on danish commons. Biologiske skrifter, 5:1–34, 1948.
  32. Imaging research in fibrotic lung disease; applying deep learning to unsolved problems. The Lancet Respiratory Medicine, 8(11):1144–1153, 2020.
  33. Addressing challenges in radiomics research: systematic review and repository of open-access cancer imaging datasets. Insights into Imaging, 14(1):216, 2023.
  34. When ai eats itself: On the caveats of data pollution in the era of generative ai, 2024.
  35. Xiahai Zhuang. Mm-whs: Multi-modality whole heart segmentation, 2019. Available at: https://zmiclab.github.io/zxh/0/mmwhs/; Accessed on 14th September 2023.
  36. Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge. Medical image analysis, 58:101537, 2019.

Summary

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

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

Continue Learning

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

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