Metraipolis › archive › dc_8dd320230cd2
Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles — Europe PMC PMID:32211231
- Source
- Europe PMC (en)
- Original
- https://europepmc.org/article/MED/32211231
- DOI
- 10.7717/peerj.8693
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T05:29:09.745Z
- SHA-256 of the archived text
7be1140335ea7bfa9810445381cf8619b688ff28b0737c049af189d005d7b6d6- Stable URL of this page
https://metraipolis.com/documento/dc_8dd320230cd2
How to cite
Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles — Europe PMC PMID:32211231 — Europe PMC (en), https://europepmc.org/article/MED/32211231 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8dd320230cd2 (Metraipolis archive dc_8dd320230cd2, sha256 7be1140335ea7bfa9810445381cf8619b688ff28b0737c049af189d005d7b6d6)
BibTeX
@misc{dc8dd320230cd2,
title = {Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles — Europe PMC PMID:32211231},
howpublished = {Europe PMC (en)},
url = {https://europepmc.org/article/MED/32211231},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8dd320230cd2; sha256 7be1140335ea7bfa9810445381cf8619b688ff28b0737c049af189d005d7b6d6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/32211231. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Convolutional neural networks (CNNs) trained on natural images are extremely successful in image classification and localization due to superior automated feature extraction capability. In extending their use to biomedical recognition tasks, it is important to note that visual features of medical images tend to be uniquely different than natural images. There are advantages offered through training these networks on large scale medical common modality image collections pertaining to the recognition task. Further, improved generalization in transferring knowledge across similar tasks is possible when the models are trained to learn modality-specific features and then suitably repurposed for the target task. In this study, we propose modality-specific ensemble learning toward improving abnormality detection in chest X-rays (CXRs). CNN models are trained on a large-scale CXR collection to learn modality-specific features and then repurposed for detecting and localizing abnormalities. Model predictions are combined using different ensemble strategies toward reducing prediction variance and sensitivity to the training data while improving overall performance and generalization. Class-selective relevance mapping (CRM) is used to visualize the learned behavior of the individual models and their ensembles. It localizes discriminative regions of interest (ROIs) showing abnormal regions and offers an improved explanation of model predictions. It was observed that the model ensembles demonstrate superior localization performance in terms of Intersection of Union (IoU) and mean Average Precision (mAP) metrics than any individual constituent model. Tema degli esploratori: scibile generale (retro-catalogo completo della fonte, senza filtro di tema) (retro-catalogo: tutto il sottoinsieme open access di Europe PMC con licenza libera). Pubblicazione: PeerJ, 2020 (prima pubblicazione 2020-03-17). Identificativi: PMID 32211231 · PMCID PMC7083159 · DOI 10.7717/peerj.8693. Parole chiave degli autori: Visualization; localization; Modality-specific Knowledge; Chest X-rays; Ensemble Learning; Deep Learning; Convolutional Neural Networks; Class-selective Relevance Mapping. Pagina: https://europepmc.org/article/MED/32211231 — https://doi.org/10.7717/peerj.8693. Autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza dell'articolo dichiarata da Europe PMC: CC0 (la versione è indicata dall'editore sulla pagina). Abstract riportato senza modifiche al contenuto, con attribuzione; deposito marcato CC0. Letto il 2026-11-09T05:25:56.221Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.