• Home
  • Search
  • Part-Aware Mask-Guided Attention for Thorax Disease Classification
  • Open Access IconOpen Access
  • Cite Icon8
  • https://doi.org/10.3390/e23060653Copy DOI Icon

Part-Aware Mask-Guided Attention for Thorax Disease Classification

  • May 23, 2021
  • Entropy
  • Ruihua Zhang +5 more
Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Thorax disease classification is a challenging task due to complex pathologies and subtle texture changes, etc. It has been extensively studied for years largely because of its wide application in computer-aided diagnosis. Most existing methods directly learn global feature representations from whole Chest X-ray (CXR) images, without considering in depth the richer visual cues lying around informative local regions. Thus, these methods often produce sub-optimal thorax disease classification performance because they ignore the very informative pathological changes around organs. In this paper, we propose a novel Part-Aware Mask-Guided Attention Network (PMGAN) that learns complementary global and local feature representations from all-organ region and multiple single-organ regions simultaneously for thorax disease classification. Specifically, multiple innovative soft attention modules are designed to progressively guide feature learning toward the global informative regions of whole CXR image. A mask-guided attention module is designed to further search for informative regions and visual cues within the all-organ or single-organ images, where attention is elegantly regularized by automatically generated organ masks and without introducing computation during the inference stage. In addition, a multi-task learning strategy is designed, which effectively maximizes the learning of complementary local and global representations. The proposed PMGAN has been evaluated on the ChestX-ray14 dataset and the experimental results demonstrate its superior thorax disease classification performance against the state-of-the-art methods.

Loading PDF

Similar Papers
  • Research Article
  • Citations35

Local and global self-attention enhanced graph convolutional network for skeleton-based action recognition

  • Oct 31, 2024
  • Pattern Recognition
  • Zhize Wu +4
  • Research Article
  • Citations1

ILAM: Cross-Fusion of Latent and Attention Features for Explainable Medical Image Classification.

  • Jan 01, 2025
  • IEEE journal of biomedical and health informatics
  • Anshul Sharma +5
  • Conference Article
  • Citations8

Multi-Head Deep Metric Learning Using Global and Local Representations

  • Jan 01, 2022
  • Mohammad K Ebrahimpour +2
  • Research Article
  • Citations50

No-Reference Quality Assessment for Screen Content Images Based on Hybrid Region Features Fusion

  • Aug 01, 2019
  • IEEE Transactions on Multimedia
  • Linru Zheng +4
  • Research Article
  • Citations11

LCGNet: Local Sequential Feature Coupling Global Representation Learning for Functional Connectivity Network Analysis With fMRI.

  • Dec 01, 2024
  • IEEE transactions on medical imaging
  • Jie Zhou +7
  • Conference Article

Global and Local Deep Feature Representation Fusion for Vehicle Re-Identification

  • Dec 01, 2019
  • Xing Zhao Lee +5
  • Research Article
  • Citations14

Person re-identification based on improved attention mechanism and global pooling method

  • May 13, 2023
  • Journal of Visual Communication and Image Representation
  • Ruyu Xu +3
  • Research Article
  • Citations29

BDNet: A BERT-based dual-path network for text-to-image cross-modal person re-identification

  • Apr 24, 2023
  • Pattern Recognition
  • Qiang Liu +4
  • PDF
  • Research Article

Contrastive learning based feature optimization for person Re-ID

  • Nov 08, 2024
  • Applied and Computational Engineering
  • Xuancheng Zhao
  • Research Article
  • Citations1

Local and global character representation enhanced model for Chinese medical named entity recognition

  • Aug 24, 2023
  • Journal of Intelligent & Fuzzy Systems
  • Yan Xiang +3
  • Research Article
  • Citations3

CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion

  • Jul 04, 2025
  • AI Sensors
  • Trinh Quoc Nguyen +4
  • Research Article
  • Citations28

LGCNet: A local-to-global context-aware feature augmentation network for salient object detection

  • Nov 07, 2021
  • Information Sciences
  • Yuzhu Ji +6
  • Research Article

Multi-label tongue image classification via label semantics-driven feature interaction enhancement.

  • Feb 01, 2026
  • Computational biology and chemistry
  • Xiang Lu +3
  • PDF
  • Research Article
  • Citations1

Transformer-Based Recognition Model for Ground-Glass Nodules from the View of Global 3D Asymmetry Feature Representation

  • Dec 12, 2023
  • Symmetry
  • Jun Miao +3
  • Research Article
  • Citations8

Cross-modal video moment retrieval based on visual-textual relationship alignment

  • Jun 01, 2020
  • SCIENTIA SINICA Informationis
  • Tong Xu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.