Pneumoconiosis computer aided diagnosis system based on X-rays and deep learning

Purpose The objective of this study is to construct a computer aided diagnosis system for normal people and pneumoconiosis using X-raysand deep learning algorithms. Materials and methods 1760 anonymous digital X-ray images of real patients between January 2017 and June 2020 were collected for this experiment. In order to concentrate the feature extraction ability of the model more on the lung region and restrain the influence of external background factors, a two-stage pipeline from coarse to fine was established. First, the U-Net model was used to extract the lung regions on each sides of the collection images. Second, the ResNet-34 model with transfer learning strategy was implemented to learn the image features extracted in the lung region to achieve accurate classification of pneumoconiosis patients and normal people. Results Among the 1760 cases collected, the accuracy and the area under curve of the classification model were 92.46% and 89% respectively. Conclusion The successful application of deep learning in the diagnosis of pneumoconiosis further demonstrates the potential of medical artificial intelligence and proves the effectiveness of our proposed algorithm. However, when we further classified pneumoconiosis patients and normal subjects into four categories, we found that the overall accuracy decreased to 70.1%. We will use the CT modality in future studies to provide more details of lung regions.

Detection of Pneumonia Using Chest X-Ray Images and Image Processing Algorithms - A Comparative Study

Utilizing exclusively picture handling procedures, this examination proposes an original strategy for distinguishing the presence of pneumonia mists in chest X-rays (CXR). Collected the several analogue chest CXRs from patients with normal and Pneumonia-infected lungs. Indigenous algorithms have been developed for cropping and for extraction of the lung region from the images. To detect pneumonia clouds first conducted the preprocessing of the image then used the image segmentation techniques like Otsu thresholding K-means clustering and global thresholding and then contour detection algorithm was applied which helped to detect lung boundary, the area’s ratio is used to classify the normal lung from pneumonia affected lung.

Analysis of Lung Imaging Intelligent Diagnosis System for Nursing Intervention of Lung Cancer Patients’ Quality of Life

In order to explore the influence of intelligent imaging diagnosis systems on comprehensive nursing intervention for patients with late-stage lung cancer, the system uses ITK and VTK toolkit to realize image reading, display, image marking, and interactive functions. The optimal threshold method and regional connectivity algorithm were used to segment the lung region, and then, the cavity filling algorithm and repair algorithm were used to repair the lung region. A variable ring filter was used to detect suspected shadows in the lungs. Finally, the classifier proposed in this paper is used to classify benign and malignant. The system has good sensitivity by detecting the images of real patients. 100 patients with advanced lung cancer were randomly divided into control group and nursing intervention group 50 cases each. Patients in the control group received routine radiotherapy and chemotherapy and routine nursing intervention. Patients in the nursing intervention group were given comprehensive nursing intervention on the basis of routine intervention in the control group for 2 consecutive months. Pittsburgh sleep quality index, pain degree, quality of life, and complications after intervention were compared between the 2 groups before and after intervention. The experimental results showed that the sleep quality, pain degree, quality of life, and complications in 2 groups were significantly improved after intervention ( P < 0.05 ), and the improvement degree in the nursing intervention group was higher than that in the control group ( P < 0.05 ). It is proved that comprehensive nursing intervention has a good effect on improving sleep quality, relieving physical pain, improving the quality of life, and reducing complications of lung cancer patients and can effectively improve the quality of life of lung cancer patients.

DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images

(1) Background: COVID-19 has been global epidemic. This work aims to extract 3D infection from COVID-19 CT images; (2) Methods: Firstly, COVID-19 CT images are processed with lung region extraction and data enhancement. In this strategy, gradient changes of voxels in different directions respond to geometric characteristics. Due to the complexity of tubular tissues in lung region, they are clustered to the lung parenchyma center based on their filtered possibility. Thus, infection is improved after data enhancement. Then, deep weighted UNet is established to refining 3D infection texture, and weighted loss function is introduced. It changes cost calculation of different samples, causing target samples to dominate convergence direction. Finally, the trained network effectively extracts 3D infection from CT images by adjusting driving strategy of different samples. (3) Results: Using Accuracy, Precision, Recall and Coincidence rate, 20 subjects from a private dataset and eight subjects from Kaggle Competition COVID-19 CT dataset tested this method in hold-out validation framework. This work achieved good performance both in the private dataset (99.94–00.02%, 60.42–11.25%, 70.79–09.35% and 63.15–08.35%) and public dataset (99.73–00.12%, 77.02–06.06%, 41.23–08.61% and 52.50–08.18%). We also applied some extra indicators to test data augmentation and different models. The statistical tests have verified the significant difference of different models. (4) Conclusions: This study provides a COVID-19 infection segmentation technology, which provides an important prerequisite for the quantitative analysis of COVID-19 CT images.

CT-Based Radiomics Helps to Predict Residual Lung Lesions in COVID-19 Patients at Three Months after Discharge

Background: In this study, our focus was on pulmonary sequelae of coronavirus disease 2019 (COVID-19). We aimed to develop and validate CT-based radiomic models for predicting the presence of residual lung lesions in COVID-19 survivors at three months after discharge. Methods: We retrospectively enrolled 162 COVID-19 confirmed patients in our hospital (84 patients with residual lung lesions and 78 patients without residual lung lesions, at three months after discharge). The patients were all randomly allocated to a training set (n = 114) or a test set (n = 48). Radiomic features were extracted from chest CT images in different regions (entire lung or lesion) and at different time points (at hospital admission or at discharge) to build different models, sequentially, or in combination, as follows: (1) Lesion_A model (based on the lesion region at admission CT); (2) Lesion_D model (based on the lesion region at discharge CT); (3) Δlesion model (based on the lesion region at admission CT and discharge CT); (4) Lung_A model (based on the lung region at admission CT); (5) Lung_D model (based on the lung region at discharge CT); (6) Δlung model (based on the lung region at admission CT and discharge CT). The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to evaluate the predictive performances of the radiomic models. Results: Among the six models, the Lesion_D and the Δlesion models achieved better predictive efficacy, with AUCs of 0.907 and 0.927, sensitivity of 0.898 and 0.763, and specificity of 0.855 and 0.964 in the training set, and AUCs of 0.875 and 0.837, sensitivity of 0.920 and 0.680, and specificity of 0.826 and 0.913 in the test set, respectively. Conclusions: The CT-based radiomic models showed good predictive effects on the presence of residual lung lesions in COVID-19 survivors at three months after discharge, which may help doctors to plan follow-up work and to reduce the psychological burden of COVID-19 survivors.

Precise Segmentation of COVID-19 Infected Lung from CT Images Based on Adaptive First-Order Appearance Model with Morphological/Anatomical Constraints

A new segmentation technique is introduced for delineating the lung region in 3D computed tomography (CT) images. To accurately model the distribution of Hounsfield scale values within both chest and lung regions, a new probabilistic model is developed that depends on a linear combination of Gaussian (LCG). Moreover, we modified the conventional expectation-maximization (EM) algorithm to be run in a sequential way to estimate both the dominant Gaussian components (one for the lung region and one for the chest region) and the subdominant Gaussian components, which are used to refine the final estimated joint density. To estimate the marginal density from the mixed density, a modified k-means clustering approach is employed to classify the Gaussian subdominant components to determine which components belong properly to a lung and which components belong to a chest. The initial segmentation, based on the LCG-model, is then refined by the imposition of 3D morphological constraints based on a 3D Markov–Gibbs random field (MGRF) with analytically estimated potentials. The proposed approach was tested on CT data from 32 coronavirus disease 2019 (COVID-19) patients. Segmentation quality was quantitatively evaluated using four metrics: Dice similarity coefficient (DSC), overlap coefficient, 95th-percentile bidirectional Hausdorff distance (BHD), and absolute lung volume difference (ALVD), and it achieved 95.67±1.83%, 91.76±3.29%, 4.86±5.01, and 2.93±2.39, respectively. The reported results showed the capability of the proposed approach to accurately segment healthy lung tissues in addition to pathological lung tissues caused by COVID-19, outperforming four current, state-of-the-art deep learning-based lung segmentation approaches.

Three-stage segmentation of lung region from CT images using deep neural networks

Background Lung region segmentation is an important stage of automated image-based approaches for the diagnosis of respiratory diseases. Manual methods executed by experts are considered the gold standard, but it is time consuming and the accuracy is dependent on radiologists’ experience. Automated methods are relatively fast and reproducible with potential to facilitate physician interpretation of images. However, these benefits are possible only after overcoming several challenges. The traditional methods that are formulated as a three-stage segmentation demonstrate promising results on normal CT data but perform poorly in the presence of pathological features and variations in image quality attributes. The implementation of deep learning methods that can demonstrate superior performance over traditional methods is dependent on the quantity, quality, cost and the time it takes to generate training data. Thus, efficient and clinically relevant automated segmentation method is desired for the diagnosis of respiratory diseases. Methods We implement each of the three stages of traditional methods using deep learning methods trained on five different configurations of training data with ground truths obtained from the 3D Image Reconstruction for Comparison of Algorithm Database (3DIRCAD) and the Interstitial Lung Diseases (ILD) database. The data was augmented with the Lung Image Database Consortium (LIDC-IDRI) image collection and a realistic phantom. A convolutional neural network (CNN) at the preprocessing stage classifies the input into lung and none lung regions. The processing stage was implemented using a CNN-based U-net while the postprocessing stage utilize another U-net and CNN for contour refinement and filtering out false positives, respectively. Results The performance of the proposed method was evaluated on 1230 and 1100 CT slices from the 3DIRCAD and ILD databases. We investigate the performance of the proposed method on five configurations of training data and three configurations of the segmentation system; three-stage segmentation and three-stage segmentation without a CNN classifier and contrast enhancement, respectively. The Dice-score recorded by the proposed method range from 0.76 to 0.95. Conclusion The clinical relevance and segmentation accuracy of deep learning models can improve though deep learning-based three-stage segmentation, image quality evaluation and enhancement as well as augmenting the training data with large volume of cheap and quality training data. We propose a new and novel deep learning-based method of contour refinement.