Dataset Information

ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans.

ABSTRACT: Automated diagnostic techniques based on computed tomography (CT) scans of the chest for the coronavirus disease (COVID-19) help physicians detect suspected cases rapidly and precisely, which is critical in providing timely medical treatment and preventing the spread of epidemic outbreaks. Existing capsule networks have played a significant role in automatic COVID-19 detection systems based on small datasets. However, extracting key slices is difficult because CT scans typically show many scattered lesion sections. In addition, existing max pooling sampling methods cannot effectively fuse the features from multiple regions. Therefore, in this study, we propose an attention capsule sampling network (ACSN) to detect COVID-19 based on chest CT scans. A key slices enhancement method is used to obtain critical information from a large number of slices by applying attention enhancement to key slices. Then, the lost active and background features are retained by integrating two types of sampling. The results of experiments on an open dataset of 35,000 slices show that the proposed ACSN achieve high performance compared with state-of-the-art models and exhibits 96.3% accuracy, 98.8% sensitivity, 93.8% specificity, and 98.3% area under the receiver operating characteristic curve.

SUBMITTER: Wen C

PROVIDER: S-EPMC9678829 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans.

Wen Cuihong C Liu Shaowu S Liu Shuai S Heidari Ali Asghar AA Hijji Mohammad M Zarco Carmen C Muhammad Khan K

Computers in biology and medicine 20221122

Automated diagnostic techniques based on computed tomography (CT) scans of the chest for the coronavirus disease (COVID-19) help physicians detect suspected cases rapidly and precisely, which is critical in providing timely medical treatment and preventing the spread of epidemic outbreaks. Existing capsule networks have played a significant role in automatic COVID-19 detection systems based on small datasets. However, extracting key slices is difficult because CT scans typically show many scatte ...[more]

PMID: 36640529

Similar Datasets

Project description:Automatic lung lesion segmentation of chest computer tomography (CT) scans is considered a pivotal stage toward accurate diagnosis and severity measurement of COVID-19. Traditional U-shaped encoder-decoder architecture and its variants suffer from diminutions of contextual information in pooling/upsampling operations with increased semantic gaps among encoded and decoded feature maps as well as instigate vanishing gradient problems for its sequential gradient propagation that result in suboptimal performance. Moreover, operating with 3-D CT volume poses further limitations due to the exponential increase of computational complexity making the optimization difficult. In this article, an automated COVID-19 lesion segmentation scheme is proposed utilizing a highly efficient neural network architecture, namely CovSegNet, to overcome these limitations. Additionally, a two-phase training scheme is introduced where a deeper 2-D network is employed for generating region-of-interest (ROI)-enhanced CT volume followed by a shallower 3-D network for further enhancement with more contextual information without increasing computational burden. Along with the traditional vertical expansion of Unet, we have introduced horizontal expansion with multistage encoder-decoder modules for achieving optimum performance. Additionally, multiscale feature maps are integrated into the scale transition process to overcome the loss of contextual information. Moreover, a multiscale fusion module is introduced with a pyramid fusion scheme to reduce the semantic gaps between subsequent encoder/decoder modules while facilitating the parallel optimization for efficient gradient propagation. Outstanding performances have been achieved in three publicly available datasets that largely outperform other state-of-the-art approaches. The proposed scheme can be easily extended for achieving optimum segmentation performances in a wide variety of applications. Impact Statement-With lower sensitivity (60-70%), elongated testing time, and a dire shortage of testing kits, traditional RTPCR based COVID-19 diagnostic scheme heavily relies on postCT based manual inspection for further investigation. Hence, automating the process of infected lesions extraction from chestCT volumes will be major progress for faster accurate diagnosis of COVID-19. However, in challenging conditions with diffused, blurred, and varying shaped edges of COVID-19 lesions, conventional approaches fail to provide precise segmentation of lesions that can be deleterious for false estimation and loss of information. The proposed scheme incorporating an efficient neural network architecture (CovSegNet) overcomes the limitations of traditional approaches that provide significant improvement of performance (8.4% in averaged dice measurement scale) over two datasets. Therefore, this scheme can be an effective, economical tool for the physicians for faster infection analysis to greatly reduce the spread and massive death toll of this deadly virus through mass-screening.

Project description:Background The standard for diagnosis of SARS-CoV-2 virus is reverse transcription polymerase chain reaction (RT-PCR) test, but chest CT may play a complimentary role in the early detection of COVID-19 pneumonia. Purpose To investigate CT features of patients with COVID-19 in Rome, Italy, and to compare the accuracy of CT with RT-PCR. Methods In this prospective study from March 4, 2020, until March 19, 2020, consecutive patients with suspected COVID-19 infection and respiratory symptoms were enrolled. Exclusion criteria were: chest CT with contrast medium performed for vascular indications, patients who refused chest CT or hospitalization, and severe CT motion artifact. All patients underwent RT-PCR and chest CT. Diagnostic performance of CT was calculated using RT-PCR as reference. Chest CT features were calculated in a subgroup of RT-PCR-positive and CT-positive patients. CT features of hospitalized patients and patient in home isolation were compared by using Pearson chi squared test. Results Our study population comprised 158 consecutive study participants (83 male and 75 female, mean age 57 y ±17). Fever was observed in 97/158 (61%), cough in 88/158 (56%), dyspnea in 52/158 (33%), lymphocytopenia in 95/158 (60%), increased C-reactive protein level in 139/158 (88%), and elevated lactate dehydrogenase in 128/158 (81%) study participants. Sensitivity, specificity, and accuracy of CT were 97% (60/62)[95% IC, 88-99%], 56% (54/96)[95% IC,45-66%] and 72% (114/158)[95% IC 64-78%], respectively. In the subgroup of RT-PCR-positive and CT-positive patients, ground-glass opacities (GGO) were present in 58/58 (100%), multilobe and posterior involvement were both present in 54/58 (93%), bilateral pneumonia in 53/58 (91%), and subsegmental vessel enlargement (> 3 mm) in 52/58 (89%) of study participants. Conclusion The typical pattern of COVID-19 pneumonia in Rome, Italy, was peripherally ground-glass opacities with multilobe and posterior involvement, bilateral distribution, and subsegmental vessel enlargement (> 3 mm). Chest CT sensitivity was high (97%) but with lower specificity (56%).

Dataset Information

ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans.

Publications

ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets