Dataset Information

Robust chest CT image segmentation of COVID-19 lung infection based on limited data.

ABSTRACT:

Background

The coronavirus disease 2019 (COVID-19) affects billions of lives around the world and has a significant impact on public healthcare. For quantitative assessment and disease monitoring medical imaging like computed tomography offers great potential as alternative to RT-PCR methods. For this reason, automated image segmentation is highly desired as clinical decision support. However, publicly available COVID-19 imaging data is limited which leads to overfitting of traditional approaches.

Methods

To address this problem, we propose an innovative automated segmentation pipeline for COVID-19 infected regions, which is able to handle small datasets by utilization as variant databases. Our method focuses on on-the-fly generation of unique and random image patches for training by performing several preprocessing methods and exploiting extensive data augmentation. For further reduction of the overfitting risk, we implemented a standard 3D U-Net architecture instead of new or computational complex neural network architectures.

Results

Through a k-fold cross-validation on 20 CT scans as training and validation of COVID-19, we were able to develop a highly accurate as well as robust segmentation model for lungs and COVID-19 infected regions without overfitting on limited data. We performed an in-detail analysis and discussion on the robustness of our pipeline through a sensitivity analysis based on the cross-validation and impact on model generalizability of applied preprocessing techniques. Our method achieved Dice similarity coefficients for COVID-19 infection between predicted and annotated segmentation from radiologists of 0.804 on validation and 0.661 on a separate testing set consisting of 100 patients.

Conclusions

We demonstrated that the proposed method outperforms related approaches, advances the state-of-the-art for COVID-19 segmentation and improves robust medical image analysis based on limited data.

SUBMITTER: Muller D

PROVIDER: S-EPMC8313817 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background and objectiveCoronavirus disease 2019 (COVID-19) is a highly contagious virus spreading all around the world. Deep learning has been adopted as an effective technique to aid COVID-19 detection and segmentation from computed tomography (CT) images. The major challenge lies in the inadequate public COVID-19 datasets. Recently, transfer learning has become a widely used technique that leverages the knowledge gained while solving one problem and applying it to a different but related problem. However, it remains unclear whether various non-COVID19 lung lesions could contribute to segmenting COVID-19 infection areas and how to better conduct this transfer procedure. This paper provides a way to understand the transferability of non-COVID19 lung lesions and a better strategy to train a robust deep learning model for COVID-19 infection segmentation.MethodsBased on a publicly available COVID-19 CT dataset and three public non-COVID19 datasets, we evaluate four transfer learning methods using 3D U-Net as a standard encoder-decoder method. i) We introduce the multi-task learning method to get a multi-lesion pre-trained model for COVID-19 infection. ii) We propose and compare four transfer learning strategies with various performance gains and training time costs. Our proposed Hybrid-encoder Learning strategy introduces a Dedicated-encoder and an Adapted-encoder to extract COVID-19 infection features and general lung lesion features, respectively. An attention-based Selective Fusion unit is designed for dynamic feature selection and aggregation.ResultsExperiments show that trained with limited data, proposed Hybrid-encoder strategy based on multi-lesion pre-trained model achieves a mean DSC, NSD, Sensitivity, F1-score, Accuracy and MCC of 0.704, 0.735, 0.682, 0.707, 0.994 and 0.716, respectively, with better genetalization and lower over-fitting risks for segmenting COVID-19 infection.ConclusionsThe results reveal the benefits of transferring knowledge from non-COVID19 lung lesions, and learning from multiple lung lesion datasets can extract more general features, leading to accurate and robust pre-trained models. We further show the capability of the encoder to learn feature representations of lung lesions, which improves segmentation accuracy and facilitates training convergence. In addition, our proposed Hybrid-encoder learning method incorporates transferred lung lesion features from non-COVID19 datasets effectively and achieves significant improvement. These findings promote new insights into transfer learning for COVID-19 CT image segmentation, which can also be further generalized to other medical tasks.

Project description:ObjectivesTo automate image delineation of tissues and organs in oncological radiotherapy by combining the deep learning methods of fully convolutional network (FCN) and atrous convolution (AC).MethodsA total of 120 sets of chest CT images of patients were selected, on which radiologists had outlined the structures of normal organs. Of these 120 sets of images, 70 sets (8,512 axial slice images) were used as the training set, 30 sets (5,525 axial slice images) as the validation set, and 20 sets (3,602 axial slice images) as the test set. We selected 5 published FCN models and 1 published Unet model, and then combined FCN with AC algorithms to generate 3 improved deep convolutional networks, namely, dilation fully convolutional networks (D-FCN). The images in the training set were used to fine-tune and train the above 8 networks, respectively. The images in the validation set were used to validate the 8 networks in terms of the automated identification and delineation of organs, in order to obtain the optimal segmentation model of each network. Finally, the images of the test set were used to test the optimal segmentation models, and thus we evaluated the capability of each model of image segmentation by comparing their Dice coefficients between automated and physician delineation.ResultsAfter being fully tuned and trained with the images in the training set, all the networks in this study performed well in automated image segmentation. Among them, the improved D-FCN 4s network model yielded the best performance in automated segmentation in the testing experiment, with an global Dice of 87.11%, and a Dice of 87.11%, 97.22%, 97.16%, 89.92%, and 70.51% for left lung, right lung, pericardium, trachea, and esophagus, respectively.ConclusionWe proposed an improved D-FCN. Our results showed that this network model might effectively improve the accuracy of automated segmentation of the images in thoracic radiotherapy, and simultaneously perform automated segmentation of multiple targets.

Project description:BackgroundCoronavirus disease 2019 (COVID-19) is very contagious. Cases appear faster than the available Polymerase Chain Reaction test kits in many countries. Recently, lung computerized tomography (CT) has been used as an auxiliary COVID-19 testing approach. Automatic analysis of the lung CT images is needed to increase the diagnostic efficiency and release the human participant. Deep learning is successful in automatically solving computer vision problems. Thus, it can be introduced to the automatic and rapid COVID-19 CT diagnosis. Many advanced deep learning-based computer vison techniques were developed to increase the model performance but have not been introduced to medical image analysis.MethodsIn this study, we propose a self-supervised two-stage deep learning model to segment COVID-19 lesions (ground-glass opacity and consolidation) from chest CT images to support rapid COVID-19 diagnosis. The proposed deep learning model integrates several advanced computer vision techniques such as generative adversarial image inpainting, focal loss, and lookahead optimizer. Two real-life datasets were used to evaluate the model's performance compared to the previous related works. To explore the clinical and biological mechanism of the predicted lesion segments, we extract some engineered features from the predicted lung lesions. We evaluate their mediation effects on the relationship of age with COVID-19 severity, as well as the relationship of underlying diseases with COVID-19 severity using statistic mediation analysis.ResultsThe best overall F1 score is observed in the proposed self-supervised two-stage segmentation model (0.63) compared to the two related baseline models (0.55, 0.49). We also identified several CT image phenotypes that mediate the potential causal relationship between underlying diseases with COVID-19 severity as well as the potential causal relationship between age with COVID-19 severity.ConclusionsThis work contributes a promising COVID-19 lung CT image segmentation model and provides predicted lesion segments with potential clinical interpretability. The model could automatically segment the COVID-19 lesions from the raw CT images with higher accuracy than related works. The features of these lesions are associated with COVID-19 severity through mediating the known causal of the COVID-19 severity (age and underlying diseases).

Project description:The aim of this study was to investigate the association between image characteristics on preoperative chest CT and severe pleural adhesion during surgery in lung cancer patients. We included consecutive 124 patients who underwent lung cancer surgeries. Preoperative chest CT was retrospectively reviewed to assess pleural thickening or calcification, pulmonary calcified nodules, active pulmonary inflammation, extent of emphysema, interstitial pneumonitis, and bronchiectasis in the operated thorax. The extent of pleural thickening or calcification was visually estimated and categorized into two groups: localized and diffuse. We measured total size of pulmonary calcified nodules. The extent of emphysema, interstitial pneumonitis, and bronchiectasis was also evaluated with a visual scoring system. The occurrence of severe pleural adhesion during lung cancer surgery was retrospectively investigated from the electrical medical records. We performed logistic regression analysis to determine the association of image characteristic on chest CT with severe pleural adhesion. Localized pleural thickening was found in 8 patients (6.5%), localized pleural calcification in 8 (6.5%), pulmonary calcified nodules in 28 (22.6%), and active pulmonary inflammation in 22 (17.7%). There was no patient with diffuse pleural thickening or calcification in this study. Trivial, mild, and moderate emphysema was found in 31 (25.0%), 21 (16.9%), and 12 (9.7%) patients, respectively. Severe pleural adhesion was found in 31 (25.0%) patients. The association of localized pleural thickening or calcification on CT with severe pleural adhesion was not found (P = 0.405 and 0.107, respectively). Size of pulmonary calcified nodules and extent of emphysema were significant variables in a univariate analysis (P = 0.045 and 0.005, respectively). In a multivariate analysis, moderate emphysema was significantly associated with severe pleural adhesion (odds ratio of 11.202, P = 0.001). In conclusion, severe pleural adhesion might be found during lung cancer surgery, provided that preoperative chest CT shows substantial pulmonary calcified nodules or emphysema.

Project description:The purpose of this study was to develop an automated lung segmentation method for computerized detection of lung nodules in digital chest tomosynthesis.The authors collected 45 digital tomosynthesis scans and manually segmented reference lung regions in each scan to assess the performance of the method. The authors automated the technique by calculating the edge gradient in an original image for enhancing lung outline and transforming the edge gradient image to polar coordinate space. The authors then employed a dynamic programming technique to delineate outlines of the unobscured lungs in the transformed edge gradient image. The lung outlines were converted back to the original image to provide the final segmentation result. The above lung segmentation algorithm was first applied to the central reconstructed tomosynthesis slice because of the absence of ribs overlapping lung structures. The segmented lung in the central slice was then used to guide lung segmentation in noncentral slices. The authors evaluated the segmentation method by using (1) an overlap rate of lung regions, (2) a mean absolute distance (MAD) of lung borders, (3) a Hausdorff distance of lung borders between the automatically segmented lungs and manually segmented reference lungs, and (4) the fraction of nodules included in the automatically segmented lungs.The segmentation method achieved mean overlap rates of 85.7%, 88.3%, and 87.0% for left lungs, right lungs, and entire lungs, respectively; mean MAD of 4.8, 3.9, and 4.4 mm for left lungs, right lungs, and entire lungs, respectively; and mean Hausdorrf distance of 25.0 mm, 25.5 mm, and 30.1 mm for left lungs, right lungs, and entire lungs, respectively. All of the nodules inside the reference lungs were correctly included in the segmented lungs obtained with the lung segmentation method.The method achieved relatively high accuracy for lung segmentation and will be useful for computer-aided detection of lung nodules in digital tomosynthesis.