Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Optimizing Skin Lesion Classification via Multimodal Data and Auxiliary Task Integration (2402.10454v1)

Published 16 Feb 2024 in cs.CV

Abstract: The rising global prevalence of skin conditions, some of which can escalate to life-threatening stages if not timely diagnosed and treated, presents a significant healthcare challenge. This issue is particularly acute in remote areas where limited access to healthcare often results in delayed treatment, allowing skin diseases to advance to more critical stages. One of the primary challenges in diagnosing skin diseases is their low inter-class variations, as many exhibit similar visual characteristics, making accurate classification challenging. This research introduces a novel multimodal method for classifying skin lesions, integrating smartphone-captured images with essential clinical and demographic information. This approach mimics the diagnostic process employed by medical professionals. A distinctive aspect of this method is the integration of an auxiliary task focused on super-resolution image prediction. This component plays a crucial role in refining visual details and enhancing feature extraction, leading to improved differentiation between classes and, consequently, elevating the overall effectiveness of the model. The experimental evaluations have been conducted using the PAD-UFES20 dataset, applying various deep-learning architectures. The results of these experiments not only demonstrate the effectiveness of the proposed method but also its potential applicability under-resourced healthcare environments.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (25)
  1. Camacho et al., “Multi-class skin lesion classification using prism-and segmentation-based fractal signatures,” vol. 197, pp. 116671, 2022.
  2. “On the impact of self-supervised learning in skin cancer diagnosis,” ISBI, pp. 1–5, 2022.
  3. “Multi-task explainable skin lesion classification,” arXiv preprint arXiv:2310.07209, 2023.
  4. Wang et al., “Intra-class consistency and inter-class discrimination feature learning for automatic skin lesion classification,” Medical Image Analysis, vol. 85, pp. 102746, 2023.
  5. Dong et al., “Learning from dermoscopic images in association with clinical metadata for skin lesion segmentation and classification,” CBM, vol. 152, pp. 106321, 2023.
  6. Iscen et al., “Improving image recognition by retrieving from web-scale image-text data,” CVPR, pp. 19295–19304, 2023.
  7. He et al., “Dme-net: Diabetic macular edema grading by auxiliary task learning,” MICCAI, pp. 788–796, 2019.
  8. Chen et al., “Auxiliary learning with joint task and data scheduling,” ICML, pp. 3634–3647, 2022.
  9. Pacheco et al., “Pad-ufes-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones,” Data in brief, vol. 32, pp. 106221, 2020.
  10. “Shades of gray and colour constancy,” Color and Imaging Conference, vol. 2004, no. 1, pp. 37–41, 2004.
  11. Pizer et al., “Adaptive histogram equalization and its variations,” Computer Vision, Graphics, and Image Processing, vol. 39, no. 3, pp. 355–368, 1987.
  12. Jaisakthi et al., “Automated skin lesion segmentation of dermoscopic images using grabcut and k-means algorithms,” IET Computer Vision, vol. 12, no. 8, pp. 1088–1095, 2018.
  13. Pundhir et al., “Towards improved skin lesion classification using metadata supervision,” ICPR, pp. 4313–4320, 2022.
  14. Pundhir et al., “Visually aware metadata-guided supervision for improved skin lesion classification using deep learning,” Workshop on the Ethical and Philosophical Issues in Medical Imaging, pp. 65–76, 2022.
  15. Simonyan et al., “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
  16. He et al., “Deep residual learning for image recognition,” CVPR, pp. 770–778, 2016.
  17. Sandler et al., “Mobilenetv2: Inverted residuals and linear bottlenecks,” CVPR, pp. 4510–4520, 2018.
  18. “Efficientnet: Rethinking model scaling for convolutional neural networks,” ICML, pp. 6105–6114, 2019.
  19. Huang et al., “Densely connected convolutional networks,” CVPR, pp. 4700–4708, 2017.
  20. Deng et al., “Imagenet: A large-scale hierarchical image database,” CVPR, pp. 248–255, 2009.
  21. Li et al., “Fusing metadata and dermoscopy images for skin disease diagnosis,” ISBI, pp. 1996–2000, 2020.
  22. Pacheco et al., “An attention-based mechanism to combine images and metadata in deep learning models applied to skin cancer classification,” IEEE Journal BHI, vol. 25, pp. 3554–3563, 2021.
  23. Pacheco et al., “The impact of patient clinical information on automated skin cancer detection,” CBM, vol. 116, pp. 103545, 2020.
  24. Gabriel Gouvine, “Ninasr: Efficient small and large convnets for super-resolution,” https://github.com/Coloquinte/torchSR/blob/main/doc/NinaSR.md, 2021.
  25. Lim et al., “Enhanced deep residual networks for single image super-resolution,” CVPR Workshops, pp. 136–144, 2017.

Summary

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

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