COVID-19 detection from chest X-rays using transfer learning with deep convolutional neural networks

Naronglerdrit, Prasitthichai; Mporas, Iosif; Sheikh-Akbari, Akbar

doi:10.1016/b978-0-12-824536-1.00031-9

Cited by 8 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the purpose of illustrating the effectiveness of our method in medical image retrieval, we validated our model on an additional COVID-19 datasets. 46 As we all know, the vector space model is needed to calculate the similarity of visual features between query and images. Usually, visual features are regarded as points in a vector space, and the proximity between two points is calculated to measure the similarity between image features, that is, the smaller the value of L2, the higher the similarity.…”

Section: F I G U R Ementioning

confidence: 99%

Centralized contrastive loss with weakly supervised progressive feature extraction for fine‐grained common thorax disease retrieval in chest x‐ray

et al. 2023

View full text Add to dashboard Cite

Background Medical images have already become an essential tool for the diagnosis of many diseases. Thus a large number of medical images are being generated due to the daily routine inspection. An efficient image‐based disease retrieval system will not only make full use of existing data, but also help physicians to prognosis the diseases. Medical image retrieval is represented by the classification and localization of common thorax diseases in x‐ray images. Although extensive efforts have been put into this field, there are still many challenges. Purpose Most of the existing fine‐grained image research methods just apply existing deep learning frameworks in extracting the image features. However, these high‐level features mainly focus on the global representations of the object, rather than simultaneously considering the local ones. It requires fine‐grained details to classify the images with similar lesion areas. Thus, it is necessary to combine the global features and local ones to make the features more discriminative. On the other hand, training CNN models based on current existing strategies have a high time complexity, and is hard to get the discriminative features mentioned above. In addition, the visual retrieval method of fine‐grained medical images still has the problem of insufficient sample data with accurate annotation information. Methods To address above challenges, we introduced a novel fine‐grained medical images retrieval method. First, a centralized contrastive loss (CCLoss) is proposed as our metric learning loss function. Parameters are updated by using the center point, which not only improves the distinguishing performance of features, but also effectively reduces the time complexity of the algorithm. In addition, a weakly supervised progressive feature extraction method is proposed to gradually extract the combined features. And the attention mechanism module is applied to screen the target information after the initial positioning for fine refinement, so as to separate the features with a high degree of discrimination. The retrieval of 14 different chest diseases is evaluated on the chest x‐ray datasets. Results Compared with the existing research methods, the proposed method shows a better retrieval result for Recall@8 by 2.26%∼4.6%$\%{\sim }4.6\%$ and achieves a very efficient training speed which is 100 times faster than the pair‐wise loss‐based training strategy. We also assessed the effects of Recall@k (k = 2, 4, 6, 8) for progressive features extracted from different steps to obtain a model with the best retrieval performance. Conclusions The proposed model is capable of learning discriminative representations from chest x‐ray datasets, and it achieves better performance compared with other state‐of‐the‐art methods. Therefore, the developed model would be useful in the diagnosis of common thorax disease or unknown chest disease.

show abstract

Section: F I G U R Ementioning

confidence: 99%

Centralized contrastive loss with weakly supervised progressive feature extraction for fine‐grained common thorax disease retrieval in chest x‐ray

et al. 2023

View full text Add to dashboard Cite

show abstract

“…However, the initial parameters of this system have to be tuned through several methods for enhancing the visibility of CX-R images ( Panwar et al, 2020 ). In accordance with this, a TL method ( Naronglerdrit et al, 2021 ) has been employed in the study ( Zebin and Rezvy, 2021 ). Various renowned pre-trained deep convolutional neural network (CNN) models have been assessed to detect COVID-19 from CX-R images.…”

Section: Review Of Existing Workmentioning

confidence: 99%

E-GCS: Detection of COVID-19 through classification by attention bottleneck residual network

Ahila

Subhajini

2022

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…Deep convolutional neural networks (DCNNs), which are typical of deep learning, have achieved great success in many practical problems, revealing the powerful expressive ability of multi-layer structure in representing complex models, 12,13 but remain an overly complicated model with poor interpretability. 14 On the contrary, fuzzy systems (FSs) are constructed by a series of If-then rules, 15 which is more interpretable. Due to the fact that FSs often suffer from the curse of structural and parameter dimensionality, as a result, hierarchical fuzzy systems (HFSs) were developed, which may get rid of the curse of dimensionality problem fundamentally.…”

Section: Introductionmentioning

confidence: 99%

“…The ‘black box’ machine learning algorithms, represented by deep learning techniques, are widely applied in image recognition, 4 automatic speech recognition, 5 natural language processing, 6 medical diagnosis, 7 voice and handwriting recognition, 8 classification of skin cancer, 9 COVID‐19 detection from chest X‐rays 10 and detection of Alzheimer's disease, 11 and so forth. Deep convolutional neural networks (DCNNs), which are typical of deep learning, have achieved great success in many practical problems, revealing the powerful expressive ability of multi‐layer structure in representing complex models, 12,13 but remain an overly complicated model with poor interpretability 14 . On the contrary, fuzzy systems (FSs) are constructed by a series of If–then rules, 15 which is more interpretable.…”

Section: Introductionmentioning

confidence: 99%

Deep patch learning algorithms with high interpretability for regression problems

Huang

Chen

Zhao

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

COVID-19 detection from chest X-rays using transfer learning with deep convolutional neural networks

Cited by 8 publications

References 7 publications

Centralized contrastive loss with weakly supervised progressive feature extraction for fine‐grained common thorax disease retrieval in chest x‐ray

Centralized contrastive loss with weakly supervised progressive feature extraction for fine‐grained common thorax disease retrieval in chest x‐ray

E-GCS: Detection of COVID-19 through classification by attention bottleneck residual network

Deep patch learning algorithms with high interpretability for regression problems

Contact Info

Product

Resources

About