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

Achieving Reliable and Fair Skin Lesion Diagnosis via Unsupervised Domain Adaptation (2307.03157v2)

Published 6 Jul 2023 in cs.CV, cs.CY, and cs.LG

Abstract: The development of reliable and fair diagnostic systems is often constrained by the scarcity of labeled data. To address this challenge, our work explores the feasibility of unsupervised domain adaptation (UDA) to integrate large external datasets for developing reliable classifiers. The adoption of UDA with multiple sources can simultaneously enrich the training set and bridge the domain gap between different skin lesion datasets, which vary due to distinct acquisition protocols. Particularly, UDA shows practical promise for improving diagnostic reliability when training with a custom skin lesion dataset, where only limited labeled data are available from the target domain. In this study, we investigate three UDA training schemes based on source data utilization: single-source, combined-source, and multi-source UDA. Our findings demonstrate the effectiveness of applying UDA on multiple sources for binary and multi-class classification. A strong correlation between test error and label shift in multi-class tasks has been observed in the experiment. Crucially, our study shows that UDA can effectively mitigate bias against minority groups and enhance fairness in diagnostic systems, while maintaining superior classification performance. This is achieved even without directly implementing fairness-focused techniques. This success is potentially attributed to the increased and well-adapted demographic information obtained from multiple sources.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Gan-based data augmentation and anonymization for skin-lesion analysis: A critical review. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1847–1856, 2021.
  2. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. European Journal of Cancer, 111:148–154, 2019.
  3. Mitigating the influence of domain shift in skin lesion classification: A benchmark study of unsupervised domain adaptation methods. Informatics in Medicine Unlocked, 44:101430, 2024.
  4. Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). In 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018), pages 168–172. IEEE, 2018.
  5. Use of teledermatology to improve dermatological access in rural areas. Telemedicine journal and e-health : the official journal of the American Telemedicine Association, 2019.
  6. Disparities in dermatology ai performance on a diverse, curated clinical image set. Science Advances, 2022.
  7. Fairness in deep learning: A computational perspective, 2020.
  8. Fairdisco: Fairer ai in dermatology via disentanglement contrastive learning, 2022.
  9. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542:115–118, 2017.
  10. Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation. New Biotechnology, 76:106–117, 2023.
  11. Unsupervised domain adaptation by backpropagation. In International conference on machine learning, pages 1180–1189. PMLR, 2015a.
  12. Unsupervised domain adaptation by backpropagation. In Proceedings of the 32nd International Conference on Machine Learning, pages 1180–1189, Lille, France, 2015b. PMLR.
  13. DermGAN: Synthetic Generation of Clinical Skin Images with Pathology. In Proceedings of the Machine Learning for Health NeurIPS Workshop, pages 155–170. PMLR, 2020.
  14. Evaluating deep neural networks trained on clinical images in dermatology with the fitzpatrick 17k dataset. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1820–1828, 2021.
  15. Progressive transfer learning and adversarial domain adaptation for cross-domain skin disease classification. IEEE journal of biomedical and health informatics, 24(5):1379–1393, 2019.
  16. YOLO by Ultralytics, 2023.
  17. Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE journal of biomedical and health informatics, 23(2):538–546, 2018.
  18. Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proceedings of the National Academy of Sciences of the United States of America, 117:12592 – 12594, 2020.
  19. A deep learning system for differential diagnosis of skin diseases. Nature Medicine, 26(6):900–908, 2020.
  20. Analysis of task transferability in large pre-trained classifiers. arXiv preprint arXiv:2307.00823, 2023.
  21. Can you trust your model’s uncertainty? evaluating predictive uncertainty under dataset shift. In Neural Information Processing Systems, 2019.
  22. PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones. Data in Brief, 32:106221, 2020.
  23. Moment matching for multi-source domain adaptation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1406–1415, 2019.
  24. Computational optimal transport: With applications to data science. Foundations and Trends® in Machine Learning, 11(5-6):355–607, 2019.
  25. Improve image-based skin cancer diagnosis with generative self-supervised learning. In 2021 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), pages 23–34. IEEE, 2021.
  26. A patient-centric dataset of images and metadata for identifying melanomas using clinical context. Scientific Data, 8(1):34, 2021.
  27. Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nature medicine, 27(12):2176–2182, 2021.
  28. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  29. Otce: A transferability metric for cross-domain cross-task representations. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15779–15788, 2021.
  30. The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data, 5(1):1–9, 2018.
  31. Adversarial discriminative domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7167–7176, 2017.
  32. How transferable are features in deep neural networks? ArXiv, abs/1411.1792, 2014.
  33. Adversarial multiple source domain adaptation. Advances in neural information processing systems, 31, 2018.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Janet Wang (7 papers)
  2. Yunbei Zhang (10 papers)
  3. Zhengming Ding (49 papers)
  4. Jihun Hamm (28 papers)
Citations (2)
View on Semantic Scholar