Open Access iconOpen Access

ARTICLE

PLDMLT: Multi-Task Learning of Diabetic Retinopathy Using the Pixel-Level Labeled Fundus Images

Hengyang Liu, Chuncheng Huang*

Department of Computer Science and Engineering, Chongqing University of Technology, Chongqing, 400054, China

* Corresponding Author: Chuncheng Huang. Email: email

(This article belongs to the Special Issue: Recent Advances in Ophthalmic Diseases Diagnosis using AI)

Computers, Materials & Continua 2023, 76(2), 1745-1761. https://doi.org/10.32604/cmc.2023.040710

Abstract

In the field of medical images, pixel-level labels are time-consuming and expensive to acquire, while image-level labels are relatively easier to obtain. Therefore, it makes sense to learn more information (knowledge) from a small number of hard-to-get pixel-level annotated images to apply to different tasks to maximize their usefulness and save time and training costs. In this paper, using Pixel-Level Labeled Images for Multi-Task Learning (PLDMLT), we focus on grading the severity of fundus images for Diabetic Retinopathy (DR). This is because, for the segmentation task, there is a finely labeled mask, while the severity grading task is without classification labels. To this end, we propose a two-stage multi-label learning weakly supervised algorithm, which generates initial classification pseudo labels in the first stage and visualizes heat maps at all levels of severity using Grad-Cam to further provide medical interpretability for the classification task. A multi-task model framework with U-net as the baseline is proposed in the second stage. A label update network is designed to alleviate the gradient balance between the classification and segmentation tasks. Extensive experimental results show that our PLDMLT method significantly outperforms other state-of-the-art methods in DR segmentation on two public datasets, achieving up to 98.897% segmentation accuracy. In addition, our method achieves comparable competitiveness with single-task fully supervised learning in the DR severity grading task.

Keywords


Cite This Article

APA Style
Liu, H., Huang, C. (2023). PLDMLT: multi-task learning of diabetic retinopathy using the pixel-level labeled fundus images. Computers, Materials & Continua, 76(2), 1745-1761. https://doi.org/10.32604/cmc.2023.040710
Vancouver Style
Liu H, Huang C. PLDMLT: multi-task learning of diabetic retinopathy using the pixel-level labeled fundus images. Comput Mater Contin. 2023;76(2):1745-1761 https://doi.org/10.32604/cmc.2023.040710
IEEE Style
H. Liu and C. Huang, "PLDMLT: Multi-Task Learning of Diabetic Retinopathy Using the Pixel-Level Labeled Fundus Images," Comput. Mater. Contin., vol. 76, no. 2, pp. 1745-1761. 2023. https://doi.org/10.32604/cmc.2023.040710



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 420

    View

  • 235

    Download

  • 1

    Like

Share Link