CT Image Dataset Research Articles

Comparative analysis of some selected generative adversarial network models for image augmentation: a case study of COVID-19 x-ray and CT images

One of the fastest-growing fields in today’s world is data analytics. Data analytics paved the way for a significant number of research and development in various fields including medicine and vaccine development, DNA analysis, artificial intelligence and many more. Data plays a very important role in providing the required results and helps in making critical decisions and predictions. However, ethical and legislative restrictions sometimes make it difficult for scientists to acquire data. For example, during the COVID-19 pandemic, data was very limited due to privacy and regulatory issues. To address data unavailability, data scientists usually leverage machine learning algorithms such as Generative Adversarial Networks (GAN) to augment data from existing samples. Today, there are over 450 algorithms that are designed to re-generate or augment data in case of unavailability of the data. With many algorithms in the market, it is practically impossible to predict which algorithm best fits the problem in question, unless many algorithms are tested. In this study, we select the most common types of GAN algorithms available for image augmentation to generate samples capable of representing a whole data distribution. To test the selected models, we used two unique datasets, namely COVID-19 CT images and COVID-19 X-Ray images. Five different GAN algorithms, namely CGAN, DCGAN, f-GAN, WGAN, and CycleGAN, were selected and applied to the samples to see how each algorithm reacts to the samples. To evaluate their performances, Visual Turing Test (VTT) and Fréchet Inception Distance (FID) were used. The VTT result shows that a human expert can accurately distinguish between different samples that were produced. Hence, CycleGAN scored 80% in CT image dataset and 77% in X-Ray image dataset. In contrast, the FID result revealed that CycleGAN had a high convergence and therefore generated high quality and clearer images on both datasets compared to CGAN, DCGAN, f-GAN, and WGAN. This study concluded that the CycleGAN model is the best when it comes to image augmentation due to its friendliness and high convergence.

Multi-domain medical image translation generation for lung image classification based on generative adversarial networks

ObjectiveLung image classification-assisted diagnosis has a large application market. Aiming at the problems of poor attention to existing translation models, the insufficient ability of key transfer and generation, insufficient quality of generated images, and lack of detailed features, this paper conducts research on lung medical image translation and lung image classification based on generative adversarial networks. MethodsThis paper proposes a medical image multi-domain translation algorithm MI-GAN based on the key migration branch. After the actual analysis of the imbalanced medical image data, the key target domain images are selected, the key migration branch is established, and a single generator is used to complete the medical image multi-domain translation. The conversion between domains ensures the attention performance of the medical image multi-domain translation model and the quality of the synthesized images. At the same time, a lung image classification model based on synthetic image data augmentation is proposed. The synthetic lung CT medical images and the original real medical images are used as the training set together to study the performance of the auxiliary diagnosis model in the classification of normal healthy subjects, and also of the mild and severe COVID-19 patients. ResultsBased on the chest CT image dataset, MI-GAN has completed the mutual conversion and generation of normal lung images without disease, viral pneumonia and Mild COVID-19 images. The synthetic images GAN-test and GAN-train indicators reached, respectively 92.188% and 85.069%, compared with other generative models in terms of authenticity and diversity, there is a considerable improvement. The accuracy rate of pneumonia diagnosis of the lung image classification model is 93.85%, which is 3.1% higher than that of the diagnosis model trained only with real images; the sensitivity of disease diagnosis is 96.69%, a relative improvement of 7.1%. 1%, the specificity was 89.70%; the area under the ROC curve (AUC) increased from 94.00% to 96.17%. ConclusionIn this paper, a multi-domain translation model of medical images based on the key transfer branch is proposed, which enables the translation network to have key transfer and attention performance. It is verified on lung CT images and achieved good results. The required medical images are synthesized by the above medical image translation model, and the effectiveness of the synthesized images on the lung image classification network is verified experimentally.

Reinforcement Learning Based Diagnosis and Prediction for COVID-19 by Optimizing a Mixed Cost Function From CT Images.

A novel coronavirus disease (COVID-19) is a pandemic disease has caused 4 million deaths and more than 200 million infections worldwide (as of August 4, 2021). Rapid and accurate diagnosis of COVID-19 infection is critical to controlling the spread of the epidemic. In order to quickly and efficiently detect COVID-19 and reduce the threat of COVID-19 to human survival, we have firstly proposed a detection framework based on reinforcement learning for COVID-19 diagnosis, which constructs a mixed loss function that can integrate the advantages of multiple loss functions. This paper uses the accuracy of the validation set as the reward value, and obtains the initial model for the next epoch by searching the model corresponding to the maximum reward value in each epoch. We also have proposed a prediction framework that integrates multiple detection frameworks using parameter sharing to predict the progression of patients' disease without additional training. This paper also constructed a higher-quality version of the CT image dataset containing 247 cases screened by professional physicians, and obtained more excellent results on this dataset. Meanwhile, we used the other two COVID-19 datasets as external verifications, and still achieved a high accuracy rate without additional training. Finally, the experimental results show that our classification accuracy can reach 98.31%, and the precision, sensitivity, specificity, and AUC (Area Under Curve) are 98.82%, 97.99%, 98.67%, and 0.989, respectively. The accuracy of external verification can reach 93.34% and 91.05%. What's more, the accuracy of our prediction framework is 91.54%. A large number of experiments demonstrate that our proposed method is effective and robust for COVID-19 detection and prediction.

Semantic instance segmentation with discriminative deep supervision for medical images

Semantic instance segmentation is crucial for many medical image analysis applications, including computational pathology and automated radiation therapy. Existing methods for this task can be roughly classified into two categories: (1) proposal-based methods and (2) proposal-free methods. However, in medical images, the irregular shape-variations and crowding instances (e.g., nuclei and cells) make it hard for the proposal-based methods to achieve robust instance localization. On the other hand, ambiguous boundaries caused by the low-contrast nature of medical images (e.g., CT images) challenge the accuracy of the proposal-free methods. To tackle these issues, we propose a proposal-free segmentation network with discriminative deep supervision (DDS), which at the same time allows us to gain the power of the proposal-based method. The DDS module is interleaved with a carefully designed proposal-free segmentation backbone in our network. Consequently, the features learned by the backbone network become more sensitive to instance localization. Also, with the proposed DDS module, robust pixel-wise instance-level cues (especially structural information) are introduced for semantic segmentation. Extensive experiments on three datasets, i.e., a nuclei dataset, a pelvic CT image dataset, and a synthetic dataset, demonstrate the superior performance of the proposed algorithm compared to the previous works.

Application of Deep Convolutional Neural Networks in the Diagnosis of Osteoporosis.

The aim of this study was to assess the possibility of using deep convolutional neural networks (DCNNs) to develop an effective method for diagnosing osteoporosis based on CT images of the spine. The research material included the CT images of L1 spongy tissue belonging to 100 patients (50 healthy and 50 diagnosed with osteoporosis). Six pre-trained DCNN architectures with different topological depths (VGG16, VGG19, MobileNetV2, Xception, ResNet50, and InceptionResNetV2) were used in the study. The best results were obtained for the VGG16 model characterised by the lowest topological depth (ACC = 95%, TPR = 96%, and TNR = 94%). A specific challenge during the study was the relatively small (for deep learning) number of observations (400 images). This problem was solved using DCNN models pre-trained on a large dataset and a data augmentation technique. The obtained results allow us to conclude that the transfer learning technique yields satisfactory results during the construction of deep models for the diagnosis of osteoporosis based on small datasets of CT images of the spine.

An uncertainty-aware deep learning architecture with outlier mitigation for prostate gland segmentation in radiotherapy treatment planning.

Task automation is essential for efficient and consistent image segmentation in radiation oncology. We report on a deep learning architecture, comprising a U-Net and a variational autoencoder (VAE) for automatic contouring of the prostate gland incorporating interobserver variation for radiotherapy treatment planning. The U-Net/VAE generates an ensemble set of segmentations for each image CT slice. A novel outlier mitigation (OM) technique was implemented to enhance the model segmentation accuracy. The primary source dataset (source_prim) consisted of 19 200 CT slices (from 300 patient planning CT image datasets) with manually contoured prostate glands. A smaller secondary source dataset (source_sec) comprised 640 CT slices (from 10 patient CT datasets), where prostate glands were segmented by 5 independent physicians on each dataset to account for interobserver variability. Data augmentation via random rotation (<5 degrees), cropping, and horizontal flipping was applied to each dataset to increase sample size by a factor of 100. A probabilistic hierarchical U-Net with VAE was implemented and pretrained using the augmented source_prim dataset for 30 epochs. Model parameters of the U-Net/VAE were fine-tuned using the augmented source_sec dataset for 100 epochs. After the first round of training, outlier contours in the training dataset were automatically detected and replaced by the most accurate contours (based on Dice similarity coefficient, DSC) generated by the model. The U-Net/OM-VAE was retrained using the revised training dataset. Metrics for comparison included DSC, Hausdorff distance (HD, mm), normalized cross-correlation (NCC) coefficient, and center-of-mass (COM) distance (mm). Results for U-Net/OM-VAE with outliers replaced in the training dataset versus U-Net/VAE without OM were as follows: DSC=0.82±0.01 versus 0.80±0.02 (p=0.019), HD=9.18±1.22 versus 10.18±1.35mm (p=0.043), NCC=0.59±0.07 versus 0.62±0.06, and COM=3.36±0.81 versus 4.77±0.96mm over the average of 15 contours. For the average of 15 highest accuracy contours, values were as follows: DSC=0.90±0.02 versus 0.85±0.02, HD=5.47±0.02 versus 7.54±1.36mm, and COM=1.03±0.58 versus 1.46±0.68mm (p<0.03 for all metrics). Results for the U-Net/OM-VAE with outliers removed were as follows: DSC=0.78±0.01, HD=10.65±1.95mm, NCC=0.46±0.10, COM=4.17±0.79mm for the average of 15 contours, and DSC=0.88±0.02, HD=7.00±1.17mm, COM=1.58±0.63mm for the average of 15 highest accuracy contours. All metrics for U-Net/VAE trained on the source_prim and source_sec datasets via pretraining, followed by fine-tuning, show statistically significant improvement over that trained on the source_sec dataset only. Finally, all metrics for U-Net/VAE with or without OM showed statistically significant improvement over those for the standard U-Net. A VAE combined with a hierarchical U-Net and an OM strategy (U-Net/OM-VAE) demonstrates promise toward capturing interobserver variability and produces accurate prostate auto-contours for radiotherapy planning. The availability of multiple contours for each CT slice enables clinicians to determine trade-offs in selecting the "best fitting" contour on each CT slice. Mitigation of outlier contours in the training dataset improves prediction accuracy, but one must be wary of reduction in variability in the training dataset.

Intelligent Identification of Coal Crack in CT Images Based on Deep Learning.

Automatic segmentation of coal crack in CT images is of great significance for the establishment of digital cores. In addition, segmentation in this field remains challenging due to some properties of coal crack CT images: high noise, small targets, unbalanced positive and negative samples, and complex, diverse backgrounds. In this paper, a segmentation method of coal crack CT images is proposed and a dataset of coal crack CT images is established. Based on the semantic segmentation model DeepLabV3+ of deep learning, the OS of the backbone has been modified to 8, and the ASPP module rate has also been modified. A new loss function is defined by combining CE loss and Dice loss. This deep learning method avoids the problem of manually setting thresholds in traditional threshold segmentation and can automatically and intelligently extract cracks. Besides, the proposed model has 0.1%, 1.2%, 2.9%, and 0.5% increase in Acc, mAcc, MioU, and FWIoU compared with other techniques and has 0.1%, 0.8%, 2%, and 0.4% increase compared with the original DeepLabV3+ on the dataset of coal CT images. The obtained results denote that the proposed segmentation method outperforms existing crack detection techniques and have practical application value in safety engineering.

A 3D image-based modelling approach for understanding spatiotemporal processes in phosphorus fertiliser dissolution, soil buffering and uptake by plant roots

Phosphorus (P) is a key yield-limiting nutrient for crops, but the main source of P fertiliser is finite. Therefore, efficient fertilisation is crucial. Optimal P application requires understanding of the dynamic processes affecting P availability to plants, including fertiliser dissolution rate and soil buffer power. However, standard soil testing methods sample at fixed time points, preventing a mechanistic understanding of P uptake variability. We used image-based modelling to investigate the effects of fertiliser dissolution rate and soil buffer power on P uptake by wheat roots imaged using X-ray CT. We modelled uptake based on 1-day, 1-week, and 14-week dissolution of a fixed quantity of total P for two common soil buffer powers. We found rapid fertiliser dissolution increased short-term root uptake, but total uptake from 1-week matched 1-day dissolution. We quantified the large effects root system architecture had on P uptake, finding that there were trade-offs between total P uptake and uptake per unit root length, representing a carbon investment/phosphorus uptake balance. These results provide a starting point for predictive modelling of uptake from different P fertilisers in different soils. With the addition of further X-ray CT image datasets and a wider range of conditions, our simulation approach could be developed further for rapid trialling of fertiliser-soil combinations to inform field-scale trials or management.

Analysis of CT scan images for COVID-19 pneumonia based on a deep ensemble framework with DenseNet, Swin transformer, and RegNet.

COVID-19 has caused enormous challenges to global economy and public health. The identification of patients with the COVID-19 infection by CT scan images helps prevent its pandemic. Manual screening COVID-19-related CT images spends a lot of time and resources. Artificial intelligence techniques including deep learning can effectively aid doctors and medical workers to screen the COVID-19 patients. In this study, we developed an ensemble deep learning framework, DeepDSR, by combining DenseNet, Swin transformer, and RegNet for COVID-19 image identification. First, we integrate three available COVID-19-related CT image datasets to one larger dataset. Second, we pretrain weights of DenseNet, Swin Transformer, and RegNet on the ImageNet dataset based on transformer learning. Third, we continue to train DenseNet, Swin Transformer, and RegNet on the integrated larger image dataset. Finally, the classification results are obtained by integrating results from the above three models and the soft voting approach. The proposed DeepDSR model is compared to three state-of-the-art deep learning models (EfficientNetV2, ResNet, and Vision transformer) and three individual models (DenseNet, Swin transformer, and RegNet) for binary classification and three-classification problems. The results show that DeepDSR computes the best precision of 0.9833, recall of 0.9895, accuracy of 0.9894, F1-score of 0.9864, AUC of 0.9991 and AUPR of 0.9986 under binary classification problem, and significantly outperforms other methods. Furthermore, DeepDSR obtains the best precision of 0.9740, recall of 0.9653, accuracy of 0.9737, and F1-score of 0.9695 under three-classification problem, further suggesting its powerful image identification ability. We anticipate that the proposed DeepDSR framework contributes to the diagnosis of COVID-19.

Multi-scale graph learning for ovarian tumor segmentation from CT images

Ovarian cancer is the gynecological malignant tumor with low early diagnosis rate and high mortality. Automated and reliable segmentation of ovarian tumor plays an essential role in ovarian cancer radiotherapy, which assists radiologists to assess cancer progresses and make fast therapeutic schedules. However, ovarian cancer is characterized by polycentric tumors and the tumors are irregular in size, which makes the tumor segmentation task challenging. In this paper, a multi-scale graph learning U-Net (MGLU-Net) is proposed for ovarian tumor segmentation. The network adopts an encoder-decoder architecture as the basic backbone. The feature maps of different scales generated by the encoder are projected into graphs with different sizes. On this basis, the graph learning module is designed to jointly exploit local information and long-range dependencies among ovarian tumors at different locations. Meanwhile, multiple graphs with different sizes are constructed to handle the size variation problem. A channel attention module is further designed to highlight the informative features from the channel domain. Extensive experiments are conducted on a real ovarian CT image dataset and Sliver07 challenge dataset. Experiments demonstrate that the proposed method shows superior performance than the state-of-the-art methods.

Lung image segmentation based on DRD U-Net and combined WGAN with Deep Neural Network

PurposeCOVID-19 is a hot issue right now, and it's causing a huge number of infections in people, posing a grave threat to human life. Deep learning-based image diagnostic technology can effectively enhance the deficiencies of the current main detection method. This paper proposes a multi-classification model diagnosis based on segmentation and classification multi-task. MethodIn the segmentation task, the end-to-end DRD U-Net model is used to segment the lung lesions to improve the ability of feature reuse and target segmentation. In the classification task, the model combined with WGAN and Deep Neural Network classifier is used to effectively solve the problem of multi-classification of COVID-19 images with small samples, to achieve the goal of effectively distinguishing COVID-19 patients, other pneumonia patients, and normal subjects. ResultsExperiments are carried out on common X-ray image and CT image data sets. The results display that in the segmentation task, the model is optimal in the key indicators of DSC and HD, and the error is increased by 0.33% and reduced by 3.57 mm compared with the original network U-Net. In the classification task, compared with SMOTE oversampling method, accuracy increased from 65.32% to 73.84%, F-measure increased from 67.65% to 74.65%, G-mean increased from 66.52% to 74.37%. At the same time, compared with other classical multi-task models, the results also have some advantages. ConclusionThis study provides new possibilities for COVID-19 image diagnosis methods, improves the accuracy of diagnosis, and hopes to provide substantial help for COVID-19 diagnosis.

Deep learning predicts immune checkpoint inhibitor-related pneumonitis from pretreatment computed tomography images.

Immune checkpoint inhibitors (ICIs) have revolutionized the treatment of lung cancer, including both non-small cell lung cancer and small cell lung cancer. Despite the promising results of immunotherapies, ICI-related pneumonitis (ICIP) is a potentially fatal adverse event. Therefore, early detection of patients at risk for developing ICIP before the initiation of immunotherapy is critical for alleviating future complications with early interventions and improving treatment outcomes. In this study, we present the first reported work that explores the potential of deep learning to predict patients who are at risk for developing ICIP. To this end, we collected the pretreatment baseline CT images and clinical information of 24 patients who developed ICIP after immunotherapy and 24 control patients who did not. A multimodal deep learning model was constructed based on 3D CT images and clinical data. To enhance performance, we employed two-stage transfer learning by pre-training the model sequentially on a large natural image dataset and a large CT image dataset, as well as transfer learning. Extensive experiments were conducted to verify the effectiveness of the key components used in our method. Using five-fold cross-validation, our method accurately distinguished ICIP patients from non-ICIP patients, with area under the receiver operating characteristic curve of 0.918 and accuracy of 0.920. This study demonstrates the promising potential of deep learning to identify patients at risk for developing ICIP. The proposed deep learning model enables efficient risk stratification, close monitoring, and prompt management of ICIP, ultimately leading to better treatment outcomes.

A self-training teacher-student model with an automatic label grader for abdominal skeletal muscle segmentation

Deep learning on a limited number of labels/annotations is a challenging task for medical imaging analysis. In this paper, we propose a novel self-training segmentation pipeline (Self-Seg in short) for segmenting skeletal muscle in CT images. Self-Seg starts with a small set of annotated images and then iteratively learns from unlabeled datasets to gradually improve the segmentation performance. Self-Seg follows a semi-supervised teacher-student learning scheme and there are two contributions: 1) we construct a self-attention UNet to improve segmentation over the classical UNet model, and 2) we implement an automatic label grader to implicitly incorporate medical knowledge for quality assurance of pseudo labels, from which good quality pseudo labels are identified to enhance learning of the segmentation model. We perform extensive experiments on three CT image datasets and show promising results on five evaluation settings, and we also compared our method to several baseline and related methods and achieved superior performance.

Low-rank matrix factorization with nonconvex regularization and bilinear decomposition

Low-rank matrix factorization (LRMF) is a powerful approach that can recover useful information with low-rank features from corrupted data and has been broadly applied in various scenarios such as computer vision and statistics. Existing convex relaxation-based LRMF models' performance and solutions are often limited by unsatisfied recovery accuracy and prolonged execution time due to excessive relaxation bias and heavy computational burden. In this paper, we first explore one class of parameterized non-convex penalty function and generalize it as a non-convex relaxation substitution term for the original rank function in the LRMF, which can effectively enhance the recovery capability for low-rank data. In order to reduce the computational burden of the nuclear-norm-based optimization scheme and make LRMF applicable to large-scale data. We propose to perform bilinear decomposition on the low-rank matrix and derive the bilinear factorization formula under the parameterized non-convex alternative. With the above considering, a low-rank matrix recovery model via bilinear decomposition and non-convex regularization, denoted as NCBF, is formulated. Further, the optimal solution algorithm for the NCBF model is developed in the framework of the block coordinate descent, combining simultaneously three strategies of decoupling, proximal gradient descent, and block prox-linear. Also, the convergence condition for the proposed algorithm has been given. We perform extensive experiments using synthetic data and real-world image datasets. The synthetic data test results demonstrate the dual superiority of the bilinear decomposition scheme in terms of operation time and estimation accuracy. Application of denoising to both generic and CT image datasets, experimental results show that NCBF outperforms several existing methods under both subjective and objective metrics evaluations.

A retrospective study of 3D deep learning approach incorporating coordinate information to improve the segmentation of pre- and post-operative abdominal aortic aneurysm.

Abdominal aortic aneurysm (AAA) is one of the most common diseases worldwide. 3D segmentation of AAA provides useful information for surgical decisions and follow-up treatment. However, existing segmentation methods are time consuming and not practical in routine use. In this article, the segmentation task will be addressed automatically using a deep learning based approach which has been proved to successfully solve several medical imaging problems with excellent performances. This article therefore proposes a new solution of AAA segmentation using deep learning in a type of 3D convolutional neural network (CNN) architecture that also incorporates coordinate information. The tested CNNs are UNet, AG-DSV-UNet, VNet, ResNetMed and DenseVoxNet. The 3D-CNNs are trained with a dataset of high resolution (256 × 256) non-contrast and post-contrast CT images containing 64 slices from each of 200 patients. The dataset consists of contiguous CT slices without augmentation and no post-processing step. The experiments show that incorporation of coordinate information improves the segmentation results. The best accuracies on non-contrast and contrast-enhanced images have average dice scores of 97.13% and 96.74%, respectively. Transfer learning from a pre-trained network of a pre-operative dataset to post-operative endovascular aneurysm repair (EVAR) was also performed. The segmentation accuracy of post-operative EVAR using transfer learning on non-contrast and contrast-enhanced CT datasets achieved the best dice scores of 94.90% and 95.66%, respectively.

Automatic head computed tomography image noise quantification with deep learning

PurposeComputed tomography (CT) image noise is usually determined by standard deviation (SD) of pixel values from uniform image regions. This study investigates how deep learning (DL) could be applied in head CT image noise estimation. MethodsTwo approaches were investigated for noise image estimation of a single acquisition image: direct noise image estimation using supervised DnCNN convolutional neural network (CNN) architecture, and subtraction of a denoised image estimated with denoising UNet-CNN experimented with supervised and unsupervised noise2noise training approaches. Noise was assessed with local SD maps using 3D- and 2D-CNN architectures. Anthropomorphic phantom CT image dataset (N = 9 scans, 3 repetitions) was used for DL-model comparisons. Mean square error (MSE) and mean absolute percentage errors (MAPE) of SD values were determined using the SD values of subtraction images as ground truth. Open-source clinical head CT low-dose dataset (Ntrain = 37, Ntest = 10 subjects) were used to demonstrate DL applicability in noise estimation from manually labeled uniform regions and in automated noise and contrast assessment. ResultsThe direct SD estimation using 3D-CNN was the most accurate assessment method when comparing in phantom dataset (MAPE = 15.5%, MSE = 6.3HU). Unsupervised noise2noise approach provided only slightly inferior results (MAPE = 20.2%, MSE = 13.7HU). 2DCNN and unsupervised UNet models provided the smallest MSE on clinical labeled uniform regions. ConclusionsDL-based clinical image assessment is feasible and provides acceptable accuracy as compared to true image noise. Noise2noise approach may be feasible in clinical use where no ground truth data is available. Noise estimation combined with tissue segmentation may enable more comprehensive image quality characterization.

A bio‐inspired AlexNet‐DrpXLm architype for an effective brain stroke lesion detection and classification

SummaryIn this article, a bio‐inspired AlexNet‐DrpXLm architype is proposed for an effective brain stroke lesion detection and classification within a short period. Here, the input CT image datasets are collected from Himalayan Institute of Medical Sciences, then the images are preprocessed to take away the noises and also enhance the quality of the images. After that, the input images are trained and the features are extracted with the help of AlexNet model, and then classified as the brain images of normal and abnormal. The last three layers of the AlexNet model are replaced with the dropout extreme learning machine (DrpXLM) classifier to classify the images in efficient manner. The DrpXLM weight parameters are tuned by improved dolphin swarm optimization algorithm. The proposed method attains higher accuracy 99.54%, high precision 90.43%, high F‐score 89.40%, higher specificity 93.56%, higher sensitivity 93.56%, lower computational time 0.02 s, and the proposed method is compared to the existing methods, like random decision forest with gravitational search algorithm, hybrid native Bayes and sample weighted with random forest classification algorithm, and random forest with fractional‐order Darwinian particle swarm optimization.

A Novel Multi-Objective Rat Swarm Optimizer-Based Convolutional Neural Networks for the Diagnosis of COVID-19 Disease

Early detection of coronavirus disease (COVID-19) is considered an essential task for disease control and cure. Thus, an automated diagnosis of COVID-19 is highly desirable. This paper introduces a novel diagnosis approach, namely, RSO-AlexNet-COVID-19. The proposed hybrid approach is based on the rat swarm optimizer (RSO) and convolutional neural network (CNN). RSO is used to find the optimal values for the hyperparameters of the AlexNet architecture to achieve a high level of diagnostic accuracy of COVID-19. It obtained overall classification accuracy of 100% for CT images datasets and an accuracy of 95.58% for the X-ray images dataset. Moreover, the performance of the proposed hybrid approach is compared with other CNN architecture, Inception v3, VGG16, and VGG19.

A Comparison Study Between CNN-Based Deformed Planning CT and CycleGAN-Based Synthetic CT Methods for Improving iCBCT Image Quality.

PurposeThe aim of this study is to compare two methods for improving the image quality of the Varian Halcyon cone-beam CT (iCBCT) system through the deformed planning CT (dpCT) based on the convolutional neural network (CNN) and the synthetic CT (sCT) generation based on the cycle-consistent generative adversarial network (CycleGAN).MethodsA total of 190 paired pelvic CT and iCBCT image datasets were included in the study, out of which 150 were used for model training and the remaining 40 were used for model testing. For the registration network, we proposed a 3D multi-stage registration network (MSnet) to deform planning CT images to agree with iCBCT images, and the contours from CT images were propagated to the corresponding iCBCT images through a deformation matrix. The overlap between the deformed contours (dpCT) and the fixed contours (iCBCT) was calculated for purposes of evaluating the registration accuracy. For the sCT generation, we trained the 2D CycleGAN using the deformation-registered CT-iCBCT slicers and generated the sCT with corresponding iCBCT image data. Then, on sCT images, physicians re-delineated the contours that were compared with contours of manually delineated iCBCT images. The organs for contour comparison included the bladder, spinal cord, femoral head left, femoral head right, and bone marrow. The dice similarity coefficient (DSC) was used to evaluate the accuracy of registration and the accuracy of sCT generation.ResultsThe DSC values of the registration and sCT generation were found to be 0.769 and 0.884 for the bladder (p < 0.05), 0.765 and 0.850 for the spinal cord (p < 0.05), 0.918 and 0.923 for the femoral head left (p > 0.05), 0.916 and 0.921 for the femoral head right (p > 0.05), and 0.878 and 0.916 for the bone marrow (p < 0.05), respectively. When the bladder volume difference in planning CT and iCBCT scans was more than double, the accuracy of sCT generation was significantly better than that of registration (DSC of bladder: 0.859 vs. 0.596, p < 0.05).ConclusionThe registration and sCT generation could both improve the iCBCT image quality effectively, and the sCT generation could achieve higher accuracy when the difference in planning CT and iCBCT was large.

Labeling Noncontrast Head CT Reports for Common Findings Using Natural Language Processing.

Prioritizing reading of noncontrast head CT examinations through an automated triage system may improve time to care for patients with acute neuroradiologic findings. We present a natural language-processing approach for labeling findings in noncontrast head CT reports, which permits creation of a large, labeled dataset of head CT images for development of emergent-finding detection and reading-prioritization algorithms. In this retrospective study, 1002 clinical radiology reports from noncontrast head CTs collected between 2008 and 2013 were manually labeled across 12 common neuroradiologic finding categories. Each report was then encoded using an n-gram model of unigrams, bigrams, and trigrams. A logistic regression model was then trained to label each report for every common finding. Models were trained and assessed using a combination of L2 regularization and 5-fold cross-validation. Model performance was strongest for the fracture, hemorrhage, herniation, mass effect, pneumocephalus, postoperative status, and volume loss models in which the area under the receiver operating characteristic curve exceeded 0.95. Performance was relatively weaker for the edema, hydrocephalus, infarct, tumor, and white-matter disease models (area under the receiver operating characteristic curve > 0.85). Analysis of coefficients revealed finding-specific words among the top coefficients in each model. Class output probabilities were found to be a useful indicator of predictive error on individual report examples in higher-performing models. Combining logistic regression with n-gram encoding is a robust approach to labeling common findings in noncontrast head CT reports.