Ai-corona: Radiologist-assistant deep learning framework for COVID-19 diagnosis in chest CT scans.
Ontology highlight
ABSTRACT:
SUBMITTER: Yousefzadeh M
PROVIDER: S-EPMC8104381 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:COVID-19 is an infectious and contagious virus. As of this writing, more than 160 million people have been infected since its emergence, including more than 125,000 in Algeria. In this work, We first collected a dataset of 4986 COVID and non-COVID images confirmed by RT-PCR tests at Tlemcen hospital in Algeria. Then we performed a transfer learning on deep learning models that got the best results on the ImageNet dataset, such as DenseNet121, DenseNet201, VGG16, VGG19, Inception Resnet-V2, and Xception, in order to conduct a comparative study. Therefore, We have proposed an explainable model based on the DenseNet201 architecture and the GradCam explanation algorithm to detect COVID-19 in chest CT images and explain the output decision. Experiments have shown promising results and proven that the introduced model can be beneficial for diagnosing and following up patients with COVID-19.
| S-EPMC8455169 | biostudies-literature
Project description:The diagnosis of COVID-19 is of vital demand. Several studies have been conducted to decide whether the chest X-ray and computed tomography (CT) scans of patients indicate COVID-19. While these efforts resulted in successful classification systems, the design of a portable and cost-effective COVID-19 diagnosis system has not been addressed yet. The memory requirements of the current state-of-the-art COVID-19 diagnosis systems are not suitable for embedded systems due to the required large memory size of these systems (e.g., hundreds of megabytes). Thus, the current work is motivated to design a similar system with minimal memory requirements. In this paper, we propose a diagnosis system using a Raspberry Pi Linux embedded system. First, local features are extracted using local binary pattern (LBP) algorithm. Second, the global features are extracted from the chest X-ray or CT scans using multi-channel fractional-order Legendre-Fourier moments (MFrLFMs). Finally, the most significant features (local and global) are selected. The proposed system steps are integrated to fit the low computational and memory capacities of the embedded system. The proposed method has the smallest computational and memory resources,less than the state-of-the-art methods by two to three orders of magnitude, among existing state-of-the-art deep learning (DL)-based methods.
| S-EPMC8112662 | biostudies-literature
Project description:PurposeTo develop and validate a computed tomography (CT) harmonization technique by combining noise-stabilization and autocalibration methodologies to provide reliable densitometry measurements in heterogeneous acquisition protocols.MethodsWe propose to reduce the effects of spatially variant noise such as nonuniform patterns of noise and biases. The method combines the statistical characterization of the signal-to-noise relationship in the CT image intensities, which allows us to estimate both the signal and spatially variant variance of noise, with an autocalibration technique that reduces the nonuniform biases caused by noise and reconstruction techniques. The method is firstly validated with anthropomorphic synthetic images that simulate CT acquisitions with variable scanning parameters: different dosage, nonhomogeneous variance of noise, and various reconstruction methods. We finally evaluate these effects and the ability of our method to provide consistent densitometric measurements in a cohort of clinical chest CT scans from two vendors (Siemens, n = 54 subjects; and GE, n = 50 subjects) acquired with several reconstruction algorithms (filtered back-projection and iterative reconstructions) with high-dose and low-dose protocols.ResultsThe harmonization reduces the effect of nonhomogeneous noise without compromising the resolution of the images (25% RMSE reduction in both clinical datasets). An analysis through hierarchical linear models showed that the average biases induced by differences in dosage and reconstruction methods are also reduced up to 74.20%, enabling comparable results between high-dose and low-dose reconstructions. We also assessed the statistical similarity between acquisitions obtaining increases of up to 30% points and showing that the low-dose vs high-dose comparisons of harmonized data obtain similar and even higher similarity than the observed for high-dose vs high-dose comparisons of nonharmonized data.ConclusionThe proposed harmonization technique allows to compare measures of low-dose with high-dose acquisitions without using a specific reconstruction as a reference. Since the harmonization does not require a precalibration with a phantom, it can be applied to retrospective studies. This approach might be suitable for multicenter trials for which a reference reconstruction is not feasible or hard to define due to differences in vendors, models, and reconstruction techniques.
| S-EPMC7251983 | biostudies-literature
Project description:BackgroundDespite the prevalence of chest CT in the clinic, concerns about unoptimized protocols delivering high radiation doses to patients still remain. This study aimed to assess the additional radiation dose associated with overscanning in chest CT and to develop an automated deep learning-assisted scan range selection technique to reduce radiation dose to patients.ResultsA significant overscanning range (31 ± 24) mm was observed in clinical setting for over 95% of the cases. The average Dice coefficient for lung segmentation was 0.96 and 0.97 for anterior-posterior (AP) and lateral projections, respectively. By considering the exact lung coverage as the ground truth, and AP and lateral projections as input, The DL-based approach resulted in errors of 0.08 ± 1.46 and - 1.5 ± 4.1 mm in superior and inferior directions, respectively. In contrast, the error on external scout views was - 0.7 ± 4.08 and 0.01 ± 14.97 mm for superior and inferior directions, respectively.The ED reduction achieved by automated scan range selection was 21% in the test group. The evaluation of a large multi-centric chest CT dataset revealed unnecessary ED of more than 2 mSv per scan and 67% increase in the thyroid absorbed dose.ConclusionThe proposed DL-based solution outperformed previous automatic methods with acceptable accuracy, even in complicated and challenging cases. The generizability of the model was demonstrated by fine-tuning the model on AP scout views and achieving acceptable results. The method can reduce the unoptimized dose to patients by exclunding unnecessary organs from field of view.
| S-EPMC8572075 | biostudies-literature
Project description:Objective:To demonstrate and test the validity of a novel deep-learning-based system for the automated detection of pulmonary nodules. Materials and Methods:The proposed system uses 2 3D deep learning models, 1 for each of the essential tasks of computer-aided nodule detection: candidate generation and false positive reduction. A total of 888 scans from the LIDC-IDRI dataset were used for training and evaluation. Results:Results for candidate generation on the test data indicated a detection rate of 94.77% with 30.39 false positives per scan, while the test results for false positive reduction exhibited a sensitivity of 94.21% with 1.789 false positives per scan. The overall system detection rate on the test data was 89.29% with 1.789 false positives per scan. Discussion:An extensive and rigorous validation was conducted to assess the performance of the proposed system. The system demonstrated a novel combination of 3D deep neural network architectures and demonstrates the use of deep learning for both candidate generation and false positive reduction to be evaluated with a substantial test dataset. The results strongly support the ability of deep learning pulmonary nodule detection systems to generalize to unseen data. The source code and trained model weights have been made available. Conclusion:A novel deep-neural-network-based pulmonary nodule detection system is demonstrated and validated. The results provide comparison of the proposed deep-learning-based system over other similar systems based on performance.
| S-EPMC6188511 | biostudies-literature
Project description:Till August 17, 2020, COVID-19 has caused 21.59 million confirmed cases in more than 227 countries and territories, and 26 naval ships. Chest CT is an effective way to detect COVID-19. This study proposed a novel deep learning model that can diagnose COVID-19 on chest CT more accurately and swiftly. Based on traditional deep convolutional neural network (DCNN) model, we proposed three improvements: (i) We introduced stochastic pooling to replace average pooling and max pooling; (ii) We combined conv layer with batch normalization layer and obtained the conv block (CB); (iii) We combined dropout layer with fully connected layer and obtained the fully connected block (FCB). Our algorithm achieved a sensitivity of 93.28%?±?1.50%, a specificity of 94.00%?±?1.56%, and an accuracy of 93.64%?±?1.42%, in identifying COVID-19 from normal subjects. We proved using stochastic pooling yields better performance than average pooling and max pooling. We compared different structure configurations and proved our 3CB?+?2FCB yields the best performance. The proposed model is effective in detecting COVID-19 based on chest CT images.
| S-EPMC7609373 | biostudies-literature
Project description:BackgroundGas trapping quantified on chest CT scans has been proposed as a surrogate for small airway disease in COPD. We sought to determine if measurements using paired inspiratory and expiratory CT scans may be better able to separate gas trapping due to emphysema from gas trapping due to small airway disease.MethodsSmokers with and without COPD from the COPDGene Study underwent inspiratory and expiratory chest CT scans. Emphysema was quantified by the percent of lung with attenuation?<?-950HU on inspiratory CT. Four gas trapping measures were defined: (1) Exp(-856), the percent of lung?<?-856HU on expiratory imaging; (2) E/I MLA, the ratio of expiratory to inspiratory mean lung attenuation; (3) RVC(856-950), the difference between expiratory and inspiratory lung volumes with attenuation between -856 and -950 HU; and (4) Residuals from the regression of Exp(-856) on percent emphysema.ResultsIn 8517 subjects with complete data, Exp(-856) was highly correlated with emphysema. The measures based on paired inspiratory and expiratory CT scans were less strongly correlated with emphysema. Exp(-856), E/I MLA and RVC(856-950) were predictive of spirometry, exercise capacity and quality of life in all subjects and in subjects without emphysema. In subjects with severe emphysema, E/I MLA and RVC(856-950) showed the highest correlations with clinical variables.ConclusionsQuantitative measures based on paired inspiratory and expiratory chest CT scans can be used as markers of small airway disease in smokers with and without COPD, but this will require that future studies acquire both inspiratory and expiratory CT scans.
| S-EPMC3627637 | biostudies-literature
Project description:Greater kyphosis angles lead to increased loading on vertebral bodies in computational models. However, results about the relationship between severity of kyphosis and incident vertebral fracture (VF) risk have been conflicting. Therefore, the aim of this study was to evaluate associations between 1) prevalent VFs and severity of kyphosis, and 2) severity of kyphosis and incident VF risk in smokers with or without chronic obstructive pulmonary disease (COPD). Former and current smokers with or without COPD were included. CT scans were made at baseline, 1-year, and 3-year follow-up. VFs were evaluated on superposed sagittal CT reconstructions. Kyphosis was measured as the angle between the lines above T4 and below T9 or T12 . We included 1239 subjects (mean age 61.3 ± 8.0 years, 61.1% male, 80.6% with COPD), of whom 253 (20.4%) had a prevalent VF and 294 (23.7%) an incident VF within 3 years. Presence, number, and severity of prevalent VFs were associated with a greater kyphosis angle. The mean increase in kyphosis angle within 3 years was small but significantly greater in subjects with incident VFs compared with those without (2.2 ± 4.1 versus 1.2 ± 3.9 degrees, respectively, for T4 to T12 angle, p < 0.001). After adjustment for bone attenuation (BA) and prevalent VFs, baseline kyphosis angle was associated with incident VFs within 1 and 3 years (angle T4 to T12 per +1 SD, hazard ratio [HR] = 1.34 [1.12-1.61] and HR 1.29 [1.15-1.45], respectively). Our data showed that a greater kyphosis angle at baseline was independently associated with increased risk of incident VFs within 1 and 3 years, supporting the theory that greater kyphosis angle contributes to higher biomechanical loads in the spine. © 2019 American Society for Bone and Mineral Research.
| S-EPMC6946934 | biostudies-literature
Project description:Research on Coronavirus Disease 2019 (COVID-19) detection methods has increased in the last months as more accurate automated toolkits are required. Recent studies show that CT scan images contain useful information to detect the COVID-19 disease. However, the scarcity of large and well balanced datasets limits the possibility of using detection approaches in real diagnostic contexts as they are unable to generalize. Indeed, the performance of these models quickly becomes inadequate when applied to samples captured in different contexts (e.g., different equipment or populations) from those used in the training phase. In this paper, a novel ensemble-based approach for more accurate COVID-19 disease detection using CT scan images is proposed. This work exploits transfer learning using pre-trained deep networks (e.g., VGG, Xception, and ResNet) evolved with a genetic algorithm, combined into an ensemble architecture for the classification of clustered images of lung lobes. The study is validated on a new dataset obtained as an integration of existing ones. The results of the experimental evaluation show that the ensemble classifier ensures effective performance, also exhibiting better generalization capabilities.
| S-EPMC8494191 | biostudies-literature
Project description:This paper performs a comprehensive study on the deep-learning-based computer-aided diagnosis (CADx) for the differential diagnosis of benign and malignant nodules/lesions by avoiding the potential errors caused by inaccurate image processing results (e.g., boundary segmentation), as well as the classification bias resulting from a less robust feature set, as involved in most conventional CADx algorithms. Specifically, the stacked denoising auto-encoder (SDAE) is exploited on the two CADx applications for the differentiation of breast ultrasound lesions and lung CT nodules. The SDAE architecture is well equipped with the automatic feature exploration mechanism and noise tolerance advantage, and hence may be suitable to deal with the intrinsically noisy property of medical image data from various imaging modalities. To show the outperformance of SDAE-based CADx over the conventional scheme, two latest conventional CADx algorithms are implemented for comparison. 10 times of 10-fold cross-validations are conducted to illustrate the efficacy of the SDAE-based CADx algorithm. The experimental results show the significant performance boost by the SDAE-based CADx algorithm over the two conventional methods, suggesting that deep learning techniques can potentially change the design paradigm of the CADx systems without the need of explicit design and selection of problem-oriented features.
| S-EPMC4832199 | biostudies-literature