Learning disentangled representations for explainable chest X-ray classification using Dirichlet VAEs

被引:0
|
作者
Harkness, Rachael [1 ,2 ]
Frangi, Alejandro F. [1 ,2 ]
Zucker, Kieran [2 ,3 ]
Ravikumar, Nishant [1 ,2 ]
机构
[1] Univ Leeds, Sch Comp, CISTIB Ctr Computat Imaging & Simulat Technol Bio, Leeds, W Yorkshire, England
[2] Univ Leeds, Leeds, W Yorkshire, England
[3] LIMR Leeds Inst Med Res, Leeds, W Yorkshire, England
来源
MEDICAL IMAGING 2023 | 2023年 / 12464卷
关键词
Multi-label classification; chest X-ray images; variational autoencoders; Dirichlet distribution; disentanglement; explainability;
D O I
10.1117/12.2654345
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This study explores the use of the Dirichlet Variational Autoencoder (DirVAE) for learning disentangled latent representations of chest X-ray (CXR) images. Our working hypothesis is that distributional sparsity, as facilitated by the Dirichlet prior, will encourage disentangled feature learning for the complex task of multi-label classification of CXR images. The DirVAE is trained using CXR images from the CheXpert database, and the predictive capacity of multi-modal latent representations learned by DirVAE models is investigated through implementation of an auxiliary multi-label classification task, with a view to enforce separation of latent factors according to class-specific features. The predictive performance and explainability of the latent space learned using the DirVAE were quantitatively and qualitatively assessed, respectively, and compared with a standard Gaussian prior-VAE (GVAE). We introduce a new approach for explainable multi-label classification in which we conduct gradient-guided latent traversals for each class of interest. Study findings indicate that the DirVAE is able to disentangle latent factors into class-specific visual features, a property not afforded by the GVAE, and achieve a marginal increase in predictive performance relative to GVAE. We generate visual examples to show that our explainability method, when applied to the trained DirVAE, is able to highlight regions in CXR images that are clinically relevant to the class(es) of interest and additionally, can identify cases where classification relies on spurious feature correlations.
引用
收藏
页数:13
相关论文
共 50 条
  • [31] Image synthesis with disentangled attributes for chest X-ray nodule augmentation and detection
    Shen, Zhenrong
    Ouyang, Xi
    Xiao, Bin
    Cheng, Jie-Zhi
    Shen, Dinggang
    Wang, Qian
    MEDICAL IMAGE ANALYSIS, 2023, 84
  • [32] Semantics Guided Disentangled GAN for Chest X-Ray Image Rib Segmentation
    Huang, Lili
    Ma, Dexin
    Zhao, Xiaowei
    Li, Chenglong
    Zhao, Haifeng
    Tang, Jin
    Li, Chuanfu
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2024, PT XIV, 2025, 15044 : 46 - 60
  • [33] Automatic Classification of Healthy/TB Chest X-ray using DeepLearning
    Vijayakumar, K.
    Maziz, Mohammad Nazmul Hasan
    Ramadasan, Swaetha
    Prabha, S.
    Kumaar, K. Sri Nirmal
    2024 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATION AND APPLIED INFORMATICS, ACCAI 2024, 2024,
  • [34] Classification of X-Ray Images of the Chest Using Convolutional Neural Networks
    Mochurad, Lesia
    Dereviannyi, Andrii
    Antoniv, Uliana
    IDDM 2021: INFORMATICS & DATA-DRIVEN MEDICINE: PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON INFORMATICS & DATA-DRIVEN MEDICINE (IDDM 2021), 2021, 3038 : 269 - 282
  • [35] Understanding Automatic Pneumonia Classification Using Chest X-Ray Images
    Bruno, Pierangela
    Calimeri, Francesco
    AIXIA 2020 - ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 12414 : 37 - 50
  • [36] Using Convolutional Neural Network for Chest X-ray Image classification
    Soric, Matija
    Pongrac, Danijela
    Inza, Inaki
    2020 43RD INTERNATIONAL CONVENTION ON INFORMATION, COMMUNICATION AND ELECTRONIC TECHNOLOGY (MIPRO 2020), 2020, : 1771 - 1776
  • [37] Pneumonia Detection from Chest X-Ray Using Binary Classification
    Alqasemi, Umar
    Chowdhury, Shabbir
    Ahmad, Istiak
    JOURNAL OF ELECTRICAL SYSTEMS, 2024, 20 (09) : 1477 - 1481
  • [38] Classification of Thoracic Abnormalities from Chest X-Ray Images with Deep Learning
    Nawaz, Usman
    Ashraf, Muhammad Ummar
    Iqbal, Muhammad Junaid
    Asaf, Muhammad
    Mir, Mariam Munsif
    Raza, Usman Ahmed
    Sharif, Bilal
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (04) : 9 - 14
  • [39] Discriminative Feature Learning for Thorax Disease Classification in Chest X-ray Images
    Guan, Qingji
    Huang, Yaping
    Luo, Yawei
    Liu, Ping
    Xu, Mingliang
    Yang, Yi
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 2476 - 2487
  • [40] Pseudo Bias-Balanced Learning for Debiased Chest X-Ray Classification
    Luo, Luyang
    Xu, Dunyuan
    Chen, Hao
    Wong, Tien-Tsin
    Heng, Pheng-Ann
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT VIII, 2022, 13438 : 621 - 631