Lesion Location Attention Guided Network for Multi-Label Thoracic Disease Classification in Chest X-Rays
The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Traditional clinical experiences have shown the benefit of lesion location attention for improving clinical diagnosis tasks. Inspired by this point of interest, in this paper we propose a novel lesion location attention guided network named LLAGnet to focus on the discriminative features from lesion locations for multi-label thoracic disease classification in chest X-rays (CXRs). By revealing the equivalence of the region-level attention (RLA) and channel-level attention (CLA), we find that the RLA is available as priors for object localization while the CLA implicitly provides high weights to the attractive channels, which both enable lesion location attention excitation. To integrate the advantages from both mechanisms, the proposed LLAGnet is structured with two corresponding attention modules, i.e., the RLA and CLA modules. Specifically, the RLA module consists of the global and local branches. And the weakly supervised attention mechanism embedded in the global branch can obtain visual regions of lesion locations by back-propagating gradients. Then the optimal attention region is amplified and applied to the local branch to provide more fine-grained features for the image classification. Finally, the CLA module adaptively enhances the weights of channel-wise features from the lesion locations by modeling interdependencies among channels. Extensive experiments on the ChestX-ray14 dataset clearly substantiate the effectiveness of LLAGnet as compared with the state-of-the-art baselines.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“Forinstance,Wang et al. [1] first announced the ChestX-ray14 dataset and utilized the ImageNet pre-trained deep CNN models, i.e., AlexNet [19], VGGNet [20], GoogLeNet [21], ResNet [5], to perform multi-label thoracic disease classification, which led to mass enthusiasm for the automated CXR image…”
MethodLarge-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795 · cited 1×
“During the training stage, we optimize the network using stochastic gradient descent (SGD) [36] with momentum 0.9 and a mini-batch size of 8.”
MethodInfluentialWang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.369 · Cited by 4,616 · cited 2×
“[1] first announced the ChestX-ray14 dataset and utilized the ImageNet pre-trained deepCNNmodels, i.”
MethodAUC: A misleading measure of the performance of predictive distribution models
Lobo, J. M., Jiménez‐Valverde, A., & Real, R. (2008) · Global Ecology and Biogeography · doi:10.1111/j.1466-8238.2007.00358.x · Cited by 3,499
Long short-term memory recurrent neural network architectures for large scale acoustic modeling
Sak, H., Senior, A., & Beaufays, F. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-80 · Cited by 2,973
Tell Me Where to Look: Guided Attention Inference Network
Li, K., Wu, Z., Peng, K.-C., Ernst, J., & Fu, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00960 · Cited by 647
Self-taught object localization with deep networks
Bazzani, L., Bergamo, A., Anguelov, D., & Torresani, L. (2016) · 2016 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2016.7477688 · Cited by 140 · cited 1×
“For example, Bergamo et al. [25] explored a self-taught object localization approach to identify relevant regions, by artificially masking out different image regions to generate bounding boxes causing the maximal activations.”
Background
Research works printed but not linked: 25
- 10.1109/ICME.2017.8019436 · DOI
- 10.1093/bjaceaccp/mkn041 · DOI · Paper page
- 10.1007/978-3-030-13469-3_88 · DOI · Paper page
- 10.1109/JBHI.2017.2705583 · DOI · Paper page
- 10.1007/978-3-030-00919-9_29 · DOI
- 10.1109/CVPR.2016.319 · DOI · Paper page
- 10.1109/CVPR.2017.476 · DOI · Paper page
- 10.1109/TIP.2017.2774041 · DOI · Paper page
- 10.1109/ICCV.2017.74 · DOI · Paper page
- 10.1109/CVPR.2018.00412 · DOI · Paper page
- 10.1109/CVPR.2018.00081 · DOI · Paper page
- zhang, 0, Image super-resolution using very deep residual channel attention networks, Proc Eur Conf Comput Vision, 286
- 10.1016/j.patrec.2018.10.027 · DOI · Paper page
- 10.1109/JBHI.2018.2818620 · DOI · Paper page
- 10.1109/CVPR.2017.243 · DOI · Paper page
- 10.1109/JBHI.2019.2897338 · doi:10.1109/jbhi.2019.2897338
- 10.1109/CVPR.2018.00745 · DOI · Paper page
- 10.1148/radiol.2018172656 · DOI · Paper page
- 10.1109/CVPR.2010.5540120 · DOI · Paper page
- 10.1016/j.patrec.2013.10.017 · DOI · Paper page
- 10.1007/978-3-030-00919-9_45 · DOI
- 10.1109/CVPR.2015.7298594 · DOI · Paper page
- 10.1109/CVPR.2018.00865 · DOI · Paper page
- 10.1109/CVPR.2018.00943 · DOI · Paper page
- 10.1109/ICCV.2015.338 · DOI · Paper page
Cited by
Explainable artificial intelligence (XAI) in deep learning-based medical image analysis
van der Velden, B. H. M., Kuijf, H. J., Gilhuijs, K. G. A., & Viergever, M. A. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102470 · Cited by 1,328
“Chen et al. (2019) proposed to use typical examples as explanation (i.”
MethodNazir, S., Dickson, D. M., & Akram, M. U. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106668 · Cited by 283
“An attention guided network was proposed for lesion locations for multi-label thoracic disease classification in CXR images [168].”
BackgroundClinical-BERT: Vision-Language Pre-training for Radiograph Diagnosis and Reports Generation
Yan, B., & Pei, M. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20204 · Cited by 94
“The existing methods are divided into hierarchical models (Jing, Xie, and Xing 2018; Li et al. 2019a; Zhang et al. 2020b; Jing, Wang, and Xing 2019; Liu et al. 2019; Ni et al. 2020; Yang et al. 2021; Liu, Ge, and Wu 2021) and Transformer-based models (Chen et al. 2020b; Liu et al. 2021) .”
BackgroundMethodResultInfluential
Metadata
- Authors
- Chen, B., Li, J., Lu, G., & Zhang, D.
- Venue
- IEEE Journal of Biomedical and Health Informatics
- Published
- 2020-07
- Volume
- 24
- Issue
- 7
- Pages
- 2016-2027
- ISSN
- 2168-2194 (ISSN-L)
- 2168-2208
- OpenAlex
- W2988214655
- Cited by
- 84
- References
- 8
- FWCI
- 3.75
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Funders
- National Natural Science Foundation of China (61906162)
- Shenzhen Fundamental Research and Discipline Layout project (JCYJ20180306172023949, JCYJ20170811155442454)
- China Postdoctoral Science Foundation (2019TQ0316, 2019M662198)
- Shenzhen Research Institute of Big Data
- Shenzhen Institute of Artificial Intelligence and Robotics for Society
- the Medical Biometrics Perception and Analysis Engineering Laboratory
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.