Related Experiment Video
Updated: Jun 6, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
A Multi-task learning U-Net model for end-to-end HEp-2 cell image analysis
Gennaro Percannella1, Umberto Petruzzello1, Francesco Tortorella1
1Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, Via Giovanni Paolo II 132, Fisciano, 84084, Salerno, Italy.
Insights
This study introduces a novel deep learning model for Antinuclear Antibody (ANA) testing. The multi-task learning approach enhances accuracy in classifying HEp-2 cell staining patterns, aiding autoimmune disease diagnosis.
Area of Science:
- Immunology
- Medical Diagnostics
- Computational Biology
Background:
- Antinuclear Antibody (ANA) testing is crucial for diagnosing autoimmune diseases.
- Indirect Immunofluorescence (IIF) microscopy using HEp-2 cells is the gold standard for ANA screening.
- Automated analysis of HEp-2 cell images is gaining traction for improved diagnostic efficiency.
Purpose of the Study:
- To develop a deep neural network model for simultaneous multi-task learning in HEp-2 cell image analysis.
- To address the need for integrated approaches managing interrelated diagnostic tasks.
- To improve the accuracy and efficiency of ANA testing through automated image analysis.
Main Methods:
- A novel deep neural network model extending U-Net architecture was proposed.
- The model employed a Multi-Task Learning (MTL) approach for an end-to-end solution.
- Experiments were conducted on a large, publicly available dataset of HEp-2 images.
Main Results:
- The proposed MTL model significantly outperformed existing state-of-the-art methods.
- The model demonstrated superior performance across all three tasks: intensity classification, cell segmentation, and pattern classification.
- The approach achieved high accuracy in identifying various HEp-2 cell staining patterns.
Conclusions:
- The developed deep learning model offers a powerful, integrated solution for ANA testing.
- This MTL approach enhances the diagnostic accuracy of HEp-2 cell-based immunofluorescence assays.
- The findings suggest a promising direction for automated, efficient, and accurate autoimmune disease diagnostics.
Abstract:
Antinuclear Antibody (ANA) testing is pivotal to help diagnose patients with a suspected autoimmune disease. The Indirect Immunofluorescence (IIF) microscopy performed with human epithelial type 2 (HEp-2) cells as the substrate is the reference method for ANA screening. It allows for the detection of antibodies binding to specific intracellular targets, resulting in various staining patterns that should be identified for diagnosis purposes. In recent years, there has been an increasing interest in devising deep learning methods for automated cell segmentation and classification of staining patterns, as well as for other tasks related to this diagnostic technique (such as intensity classification). However, little attention has been devoted to architectures aimed at simultaneously managing multiple interrelated tasks, via a shared representation. In this paper, we propose a deep neural network model that extends U-Net in a Multi-Task Learning (MTL) fashion, thus offering an end-to-end approach to tackle three fundamental tasks of the diagnostic procedure, i.e., HEp-2 cell specimen intensity classification, specimen segmentation, and pattern classification. The experiments were conducted on one of the largest publicly available datasets of HEp-2 images. The results showed that the proposed approach significantly outperformed the competing state-of-the-art methods for all the considered tasks.
