Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images

MRI-assessed Dynamic Hyperinflation Induced by Tachypnea in Chronic Obstructive Pulmonary Disease: The SPIROMICS-HF Study

Purpose To assess the repeatability of real-time cine pulmonary MRI measures of metronome-paced tachypnea (MPT)-induced dynamic hyperinflation and its relationship with chronic obstructive pulmonary disease (COPD) severity. Materials and Methods SubPopulations and InteRmediate Outcome Measures In COPD Study (SPIROMICS) (ClinicalTrials.gov identifier no. NCT01969344) is a multicenter prospective cohort study that recruited individuals with COPD with 20 or more pack-years smoking history and controls aged 40-80 years. SPIROMICS-HF is a cross-sectional study evaluating cardiopulmonary interactions in COPD from December 2019 to April 2024. Two-dimensional coronal real-time cine pulmonary MRI (3.2 frames/sec) was performed during MPT twice. Lung masks and lung MR images from an independent study were used for transfer learning to segment real-time cine pulmonary MR images. Dynamic hyperinflation was evaluated as the increase in end-expiratory lung volume (EELV) during tidal breathing to the end of MPT. Repeatability was assessed with intraclass correlation coefficients, and multivariable associations with COPD severity were examined. Results Of the 70 participants (mean age, 67 years ± 10 [SD]; 37 male, 33 female) included in the study, 59% had COPD. The transfer learning model achieved high accuracy in lung segmentation (Dice similarity coefficient, 0.94 ± 0.03). There was good scan-rescan agreement for EELV and dynamic hyperinflation (intraclass correlation coefficient, 0.99 and 0.87, respectively). Dynamic hyperinflation was associated with COPD severity (P trend = .01, with a mean difference between severe COPD and controls of 0.24 L). Conclusion A transfer learning model yielded reproducible quantification of MPT-induced dynamic hyperinflation at real-time cine pulmonary MRI, with greater dynamic hyperinflation in participants with more severe COPD. Keywords: Chronic Obstructive Pulmonary Disease, MR Imaging, Pulmonary, Lung, Technology Assessment Supplemental material is available for this article. ClinicalTrials.gov identifier: NCT01969344 © RSNA, 2025.

Classification of Chronic Obstructive Pulmonary Disease (COPD) Through Respiratory Pattern Analysis

Background: This study proposes a classification system for predicting chronic obstructive pulmonary disease (COPD) patients and non-patients based on image and text data. Method: This study measured the respiratory volume based on thermal images, stored the respiratory data, and derived features related to respiratory patterns, including the total respiratory volume, average distance between expirations, average distance between inspirations, and total respiratory rate. The data for each feature were stored in text format. The four features saved as text were scaled using Z-score normalization and expressed as scores through weighted summation. These scores were compared to a threshold based on the ROC curve values, classifying participants as patients if the score exceeded the threshold and as non-patients if it fell below. Results: The proposed method achieved an accuracy of 82.5%. To validate the proposed approach, precision, recall, and F1-score were utilized, confirming the high classification performance of the model. The results of this study demonstrate the potential for future applications in non-contact medical examinations and diagnoses of respiratory diseases.

Contrastive Registration for Unsupervised Medical Image Segmentation

Medical image segmentation is an important task in medical imaging, as it serves as the first step for clinical diagnosis and treatment planning. While major success has been reported using deep learning supervised techniques, they assume a large and well-representative labeled set. This is a strong assumption in the medical domain where annotations are expensive, time-consuming, and inherent to human bias. To address this problem, unsupervised segmentation techniques have been proposed in the literature. Yet, none of the existing unsupervised segmentation techniques reach accuracies that come even near to the state-of-the-art of supervised segmentation methods. In this work, we present a novel optimization model framed in a new convolutional neural network (CNN)-based contrastive registration architecture for unsupervised medical image segmentation called CLMorph. The core idea of our approach is to exploit image-level registration and feature-level contrastive learning, to perform registration-based segmentation. First, we propose an architecture to capture the image-to-image transformation mapping via registration for unsupervised medical image segmentation. Second, we embed a contrastive learning mechanism in the registration architecture to enhance the discriminative capacity of the network at the feature level. We show that our proposed CLMorph technique mitigates the major drawbacks of existing unsupervised techniques. We demonstrate, through numerical and visual experiments, that our technique substantially outperforms the current state-of-the-art unsupervised segmentation methods on two major medical image datasets.

An integrated method for detecting lung cancer via CT scanning via optimization, deep learning, and IoT data transmission

With its increasing global prevalence, lung cancer remains a critical health concern. Despite the advancement of screening programs, patient selection and risk stratification pose significant challenges. This study addresses the pressing need for early detection through a novel diagnostic approach that leverages innovative image processing techniques. The urgency of early lung cancer detection is emphasized by its alarming growth worldwide. While computed tomography (CT) surpasses traditional X-ray methods, a comprehensive diagnosis requires a combination of imaging techniques. This research introduces an advanced diagnostic tool implemented through image processing methodologies. The methodology commences with histogram equalization, a crucial step in artifact removal from CT images sourced from a medical database. Accurate lung CT image segmentation, which is vital for cancer diagnosis, follows. The Otsu thresholding method and optimization, employing Colliding Bodies Optimization (CBO), enhance the precision of the segmentation process. A local binary pattern (LBP) is deployed for feature extraction, enabling the identification of nodule sizes and precise locations. The resulting image underwent classification using the densely connected CNN (DenseNet) deep learning algorithm, which effectively distinguished between benign and malignant tumors. The proposed CBO+DenseNet CNN exhibits remarkable performance improvements over traditional methods. Notable enhancements in accuracy (98.17%), specificity (97.32%), precision (97.46%), and recall (97.89%) are observed, as evidenced by the results from the fractional randomized voting model (FRVM). These findings highlight the potential of the proposed model as an advanced diagnostic tool. Its improved metrics promise heightened accuracy in tumor classification and localization. The proposed model uniquely combines Colliding Bodies Optimization (CBO) with DenseNet CNN, enhancing segmentation and classification accuracy for lung cancer detection, setting it apart from traditional methods with superior performance metrics.

Digital twins for chronic lung diseases

Digital twins have recently emerged in healthcare. They combine advances in cyber-physical systems, modelling and computation techniques, and enable a bidirectional flow of information between the physical and virtual entities. In respiratory medicine, progress in connected devices and artificial intelligence make it technically possible to obtain digital twins that allow real-time visualisation of a patient's respiratory health. Advances in respiratory system modelling also enable the development of digital twins that could be used to predict the effectiveness of different therapeutic approaches for a patient. For researchers, digital twins could lead to a better understanding of the gene-environment-time interactions involved in the development of chronic respiratory diseases. For clinicians and patients, they could facilitate personalised and timely medicine, by enabling therapeutic adaptations specific to each patient and early detection of disease progression. The objective of this review is to allow the reader to explore the concept of digital twins, their feasibility in respiratory medicine, their potential benefits and the challenges to their implementation.

Flow-Field Inference for Turbulent Exhale Flow Measurement

BACKGROUND

Vision-based pulmonary diagnostics present a unique approach for tracking and measuring natural breathing behaviors through remote imaging. While many existing methods correlate chest and diaphragm movements to respiratory behavior, we look at how the direct visualization of thermal CO2 exhale flow patterns can be tracked to directly measure expiratory flow.

METHODS

In this work, we present a novel method for isolating and extracting turbulent exhale flow signals from thermal image sequences through flow-field prediction and optical flow measurement. The objective of this work is to introduce a respiratory diagnostic tool that can be used to capture and quantify natural breathing, to identify and measure respiratory metrics such as breathing rate, flow, and volume. One of the primary contributions of this work is a method for capturing and measuring natural exhale behaviors that describe individualized pulmonary traits. By monitoring subtle individualized respiratory traits, we can perform secondary analysis to identify unique personalized signatures and abnormalities to gain insight into pulmonary function. In our study, we perform data acquisition within a clinical setting to train an inference model (FieldNet) that predicts flow-fields to quantify observed exhale behaviors over time.

RESULTS

Expiratory flow measurements capturing individualized flow signatures from our initial cohort demonstrate how the proposed flow field model can be used to isolate and analyze turbulent exhale behaviors and measure anomalous behavior.

CONCLUSIONS

Our results illustrate that detailed spatial flow analysis can contribute to unique signatures for identifying patient specific natural breathing behaviors and abnormality detection. This provides the first-step towards a non-contact respiratory technology that directly captures effort-independent behaviors based on the direct measurement of imaged CO2 exhaled airflow patterns.

CMM: A CNN-MLP Model for COVID-19 Lesion Segmentation and Severity Grading

In this paper, a CNN-MLP model (CMM) is proposed for COVID-19 lesion segmentation and severity grading in CT images. The CMM starts by lung segmentation using UNet, and then segmenting the lesion from the lung region using a multi-scale deep supervised UNet (MDS-UNet), finally implementing the severity grading by a multi-layer preceptor (MLP). In MDS-UNet, shape prior information is fused with the input CT image to reduce the searching space of the potential segmentation outputs. The multi-scale input compensates for the loss of edge contour information in convolution operations. In order to enhance the learning of multiscale features, the multi-scale deep supervision extracts supervision signals from different upsampling points on the network. In addition, it is empirical that the lesion which has a whiter and denser appearance tends to be more severe in the COVID-19 CT image. So, the weighted mean gray-scale value (WMG) is proposed to depict this appearance, and together with the lung and lesion area to serve as input features for the severity grading in MLP. To improve the precision of lesion segmentation, a label refinement method based on the Frangi vessel filter is also proposed. Comparative experiments on COVID-19 public datasets show that our proposed CMM achieves high accuracy on COVID-19 lesion segmentation and severity grading.

Quantification of Resection Margin following Sublobar Resection in Lung Cancer Patients through Pre- and Post-Operative CT Image Comparison: Utilizing a CT-Based 3D Reconstruction Algorithm

Sublobar resection has emerged as a standard treatment option for early-stage peripheral non-small cell lung cancer. Achieving an adequate resection margin is crucial to prevent local tumor recurrence. However, gross measurement of the resection margin may lack accuracy due to the elasticity of lung tissue and interobserver variability. Therefore, this study aimed to develop an objective measurement method, the CT-based 3D reconstruction algorithm, to quantify the resection margin following sublobar resection in lung cancer patients through pre- and post-operative CT image comparison. An automated subvascular matching technique was first developed to ensure accuracy and reproducibility in the matching process. Following the extraction of matched feature points, another key technique involves calculating the displacement field within the image. This is particularly important for mapping discontinuous deformation fields around the surgical resection area. A transformation based on thin-plate spline is used for medical image registration. Upon completing the final step of image registration, the distance at the resection margin was measured. After developing the CT-based 3D reconstruction algorithm, we included 12 cases for resection margin distance measurement, comprising 4 right middle lobectomies, 6 segmentectomies, and 2 wedge resections. The outcomes obtained with our method revealed that the target registration error for all cases was less than 2.5 mm. Our method demonstrated the feasibility of measuring the resection margin following sublobar resection in lung cancer patients through pre- and post-operative CT image comparison. Further validation with a multicenter, large cohort, and analysis of clinical outcome correlation is necessary in future studies.

Fully automatic deep learning-based lung parenchyma segmentation and boundary correction in thoracic CT scans

PURPOSE

The proposed work aims to develop an algorithm to precisely segment the lung parenchyma in thoracic CT scans. To achieve this goal, the proposed technique utilized a combination of deep learning and traditional image processing algorithms. The initial step utilized a trained convolutional neural network (CNN) to generate preliminary lung masks, followed by the proposed post-processing algorithm for lung boundary correction.

METHODS

First, the proposed method trained an improved 2D U-Net CNN model with Inception-ResNet-v2 as its backbone. The model was trained on 32 CT scans from two different sources: one from the VESSEL12 grand challenge and the other from AIIMS Delhi. Further, the model's performance was evaluated on a test dataset of 16 CT scans with juxta-pleural nodules obtained from AIIMS Delhi and the LUNA16 challenge. The model's performance was assessed using evaluation metrics such as average volumetric dice coefficient (DSCavg), average IoU score (IoUavg), and average F1 score (F1avg). Finally, the proposed post-processing algorithm was implemented to eliminate false positives from the model's prediction and to include juxta-pleural nodules in the final lung masks.

RESULTS

The trained model reported a DSCavg of 0.9791 ± 0.008, IoUavg of 0.9624 ± 0.007, and F1avg of 0.9792 ± 0.004 on the test dataset. Applying the post-processing algorithm to the predicted lung masks obtained a DSCavg of 0.9713 ± 0.007, IoUavg of 0.9486 ± 0.007, and F1avg of 0.9701 ± 0.008. The post-processing algorithm successfully included juxta-pleural nodules in the final lung mask.

CONCLUSIONS

Using a CNN model, the proposed method for lung parenchyma segmentation produced precise segmentation results. Furthermore, the post-processing algorithm addressed false positives and negatives in the model's predictions. Overall, the proposed approach demonstrated promising results for lung parenchyma segmentation. The method has the potential to be valuable in the advancement of computer-aided diagnosis (CAD) systems for automatic nodule detection.

Segmentation and classification of lungs CT-scan for detecting COVID-19 abnormalities by deep learning technique: U-Net model

Background

Artificial intelligence (AI) techniques have been ascertained useful in the analysis and description of infectious areas in radiological images promptly. Our aim in this study was to design a web-based application for detecting and labeling infected tissues on CT (computed tomography) lung images of patients based on the deep learning (DL) method as a type of AI.

Materials and Methods

The U-Net architecture, one of the DL networks, is used as a hybrid model with pre-trained densely connected convolutional network 121 (DenseNet121) architecture for the segmentation process. The proposed model was constructed on 1031 persons' CT-scan images from Ibn Sina Hospital of Iran in 2021 and some publicly available datasets. The network was trained using 6000 slices, validated on 1000 slices images, and tested against the 150 slices. Accuracy, sensitivity, specificity, and area under the receiver operating characteristics (ROC) curve (AUC) were calculated to evaluate model performance.

Results

The results indicate the acceptable ability of the U-Net-DenseNet121 model in detecting COVID-19 abnormality (accuracy = 0.88 and AUC = 0.96 for thresholds of 0.13 and accuracy = 0.88 and AUC = 0.90 for thresholds of 0.2). Based on this model, we developed the "Imaging-Tech" web-based application for use at hospitals and clinics to make our project's output more practical and attractive in the market.

Conclusion

We designed a DL-based model for the segmentation of COVID-19 CT scan images and, based on this model, constructed a web-based application that, according to the results, is a reliable detector for infected tissue in lung CT-scans. The availability of such tools would aid in automating, prioritizing, fastening, and broadening the treatment of COVID-19 patients globally.

Estimation of normal lung weight index in healthy female domestic pigs

INTRODUCTION

Lung weight is an important study endpoint to assess lung edema in porcine experiments on acute respiratory distress syndrome and ventilatory induced lung injury. Evidence on the relationship between lung-body weight relationship is lacking in the literature. The aim of this work is to provide a reference equation between normal lung and body weight in female domestic piglets.

MATERIALS AND METHODS

177 healthy female domestic piglets from previous studies were included in the analysis. Lung weight was assessed either via a CT-scan before any experimental injury or with a scale after autopsy. The animals were randomly divided in a training (n = 141) and a validation population (n = 36). The relation between body weight and lung weight index (lung weight/body weight, g/kg) was described by an exponential function on the training population. The equation was tested on the validation population. A Bland-Altman analysis was performed to compare the lung weight index in the validation population and its theoretical value calculated with the reference equation.

RESULTS

A good fit was found between the validation population and the exponential equation extracted from the training population (RMSE = 0.060). The equation to determine lung weight index from body weight was: [Formula: see text] At the Bland and Altman analyses, the mean bias between the real and the expected lung weight index was - 0.26 g/kg (95% CI - 0.96-0.43), upper LOA 3.80 g/kg [95% CI 2.59-5.01], lower LOA - 4.33 g/kg [95% CI = - 5.54-(- 3.12)].

CONCLUSIONS

This exponential function might be a valuable tool to assess lung edema in experiments involving 16-50 kg female domestic piglets. The error that can be made due to the 95% confidence intervals of the formula is smaller than the one made considering the lung to body weight as a linear relationship.

GPU-accelerated lung CT segmentation based on level sets and texture analysis

This paper presents a novel semi-automatic method for lung segmentation in thoracic CT datasets. The fully three-dimensional algorithm is based on a level set representation of an active surface and integrates texture features to improve its robustness. The method's performance is enhanced by the graphics processing unit (GPU) acceleration. The segmentation process starts with a manual initialisation of 2D contours on a few representative slices of the analysed volume. Next, the starting regions for the active surface are generated according to the probability maps of texture features. The active surface is then evolved to give the final segmentation result. The recent implementation employs features based on grey-level co-occurrence matrices and Gabor filters. The algorithm was evaluated on real medical imaging data from the LCTCS 2017 challenge. The results were also compared with the outcomes of other segmentation methods. The proposed approach provided high segmentation accuracy while offering very competitive performance.

A new segment method for pulmonary artery and vein

Accurate differentiation between pulmonary arteries and veins (A/V) holds pivotal importance in the realm of diagnosing and treating pulmonary ailments. This study presents a new approach that leverages grayscale differences between A/V. Distinctions are measured using median and mean grayscale values within the vessel area. Initially, adherent regions are removed based on vessel structure. The trunk regions are segmented using gray level information near the heart region of the lung boundary. Incorrectly segmented vessels are corrected based on connectivity. For distal lung vessels, a similar distance field is established using a graph-cut method. Experimental results show the algorithm's superior segmentation accuracy, achieving 97.26% compared to the CNN-based average accuracy of 91.67%. Error branches are more concentrated, aiding subsequent manual and automatic correction. This demonstrates the algorithm's effective segmentation of pulmonary A/V.

Tumor segmentation via enhanced area growth algorithm for lung CT images

BACKGROUND

Since lung tumors are in dynamic conditions, the study of tumor growth and its changes is of great importance in primary diagnosis.

METHODS

Enhanced area growth (EAG) algorithm is introduced to segment the lung tumor in 2D and 3D modes on 60 patients CT images from four different databases by MATLAB software. The contrast augmentation, color intensity and maximum primary tumor radius determination, thresholding, start and neighbor points' designation in an array, and then modifying the points in the braid on average are the early steps of the proposed algorithm. To determine the new tumor boundaries, the maximum distance from the color-intensity center point of the primary tumor to the modified points is appointed via considering a larger target region and new threshold. The tumor center is divided into different subsections and then all previous stages are repeated from new designated points to define diverse boundaries for the tumor. An interpolation between these boundaries creates a new tumor boundary. The intersections with the tumor boundaries are firmed for edge correction phase, after drawing diverse lines from the tumor center at relevant angles. Each of the new regions is annexed to the core region to achieve a segmented tumor surface by meeting certain conditions.

RESULTS

The multipoint-growth-starting-point grouping fashioned a desired consequence in the precise delineation of the tumor. The proposed algorithm enhanced tumor identification by more than 16% with a reasonable accuracy acceptance rate. At the same time, it largely assurances the independence of the last outcome from the starting point. By significance difference of p < 0.05, the dice coefficients were 0.80 ± 0.02 and 0.92 ± 0.03, respectively, for primary and enhanced algorithms. Lung area determination alongside automatic thresholding and also starting from several points along with edge improvement may reduce human errors in radiologists' interpretation of tumor areas and selection of the algorithm's starting point.

CONCLUSIONS

The proposed algorithm enhanced tumor detection by more than 18% with a sufficient acceptance ratio of accuracy. Since the enhanced algorithm is independent of matrix size and image thickness, it is very likely that it can be easily applied to other contiguous tumor images.

TRIAL REGISTRATION

PAZHOUHAN, PAZHOUHAN98000032. Registered 4 January 2021, http://pazhouhan.gerums.ac.ir/webreclist/view.action?webreclist_code=19300.

A Survey on Artificial Intelligence in Pulmonary Imaging

Over the last decade, deep learning (DL) has contributed a paradigm shift in computer vision and image recognition creating widespread opportunities of using artificial intelligence in research as well as industrial applications. DL has been extensively studied in medical imaging applications, including those related to pulmonary diseases. Chronic obstructive pulmonary disease, asthma, lung cancer, pneumonia, and, more recently, COVID-19 are common lung diseases affecting nearly 7.4% of world population. Pulmonary imaging has been widely investigated toward improving our understanding of disease etiologies and early diagnosis and assessment of disease progression and clinical outcomes. DL has been broadly applied to solve various pulmonary image processing challenges including classification, recognition, registration, and segmentation. This paper presents a survey of pulmonary diseases, roles of imaging in translational and clinical pulmonary research, and applications of different DL architectures and methods in pulmonary imaging with emphasis on DL-based segmentation of major pulmonary anatomies such as lung volumes, lung lobes, pulmonary vessels, and airways as well as thoracic musculoskeletal anatomies related to pulmonary diseases.

Progress in magnetic particle imaging signal and iron quantification methods in vivo - application to long circulating SPIONs

The strengths of Magnetic Particle Imaging (MPI) lay in its sensitivity, quantitative nature, and lack of signal attenuation for Superparamagnetic Iron Oxide Nanoparticles (SPION). These advantages make MPI a powerful tool for the non-invasive monitoring of tracer behaviour over time. With more MPI studies emerging, a standardized method for determining the boundaries of a region of interest (ROI) and iron quantification is crucial. The current approaches are inconsistent, making it challenging to compare studies, hindering MPI progression. Here we showcase three different ROI selection methods for the quantification of iron in vivo and ex vivo. Healthy mice were intravenously administered a long circulating tracer, never before applied in MPI, and the ROI methods were tested for their ability to accurately quantify the total signal present, in addition to the accumulation of the tracer in individual organs. We discuss how the quantified iron amount can be vastly altered based on the choice of ROI, the importance of the standard curve and the challenges associated with each method. Lastly, the user variability and accuracy of each method was compared by 3 independent users to ensure their consistency and lack of bias.

A Review of Deep Learning Techniques for Lung Cancer Screening and Diagnosis Based on CT Images

One of the most common and deadly diseases in the world is lung cancer. Only early identification of lung cancer can increase a patient's probability of survival. A frequently used modality for the screening and diagnosis of lung cancer is computed tomography (CT) imaging, which provides a detailed scan of the lung. In line with the advancement of computer-assisted systems, deep learning techniques have been extensively explored to help in interpreting the CT images for lung cancer identification. Hence, the goal of this review is to provide a detailed review of the deep learning techniques that were developed for screening and diagnosing lung cancer. This review covers an overview of deep learning (DL) techniques, the suggested DL techniques for lung cancer applications, and the novelties of the reviewed methods. This review focuses on two main methodologies of deep learning in screening and diagnosing lung cancer, which are classification and segmentation methodologies. The advantages and shortcomings of current deep learning models will also be discussed. The resultant analysis demonstrates that there is a significant potential for deep learning methods to provide precise and effective computer-assisted lung cancer screening and diagnosis using CT scans. At the end of this review, a list of potential future works regarding improving the application of deep learning is provided to spearhead the advancement of computer-assisted lung cancer diagnosis systems.

Effective Electrical Impedance Tomography Based on Enhanced Encoder-Decoder Using Atrous Spatial Pyramid Pooling Module

Electrical impedance tomography (EIT) is a noninvasive and radiation-free imaging method. As a "soft-field" imaging technique, in EIT, the target signal in the center of the measured field is frequently swamped by the target signal at the edge, which restricts its further application. To alleviate this problem, this study presents an enhanced encoder-decoder (EED) method with an atrous spatial pyramid pooling (ASPP) module. The proposed method enhances the ability to detect central weak targets by constructing an ASPP module that integrates multiscale information in the encoder. The multilevel semantic features are fused in the decoder to improve the boundary reconstruction accuracy of the center target. The average absolute error of the imaging results by the EED method reduced by 82.0%, 83.6%, and 36.5% in simulation experiments and 83.0%, 83.2%, and 36.1% in physical experiments compared with the errors of the damped least-squares algorithm, Kalman filtering method, and U-Net-based imaging method, respectively. The average structural similarity improved by 37.3%, 42.9%, and 3.6%, and 39.2%, 45.2%, and 3.8% in the simulation and physical experiments, respectively. The proposed method provides a practical and reliable means of extending the application of EIT by solving the problem of weak central target reconstruction under the effect of strong edge targets in EIT.

A tumor vasculature-based imaging biomarker for predicting response and survival in patients with lung cancer treated with checkpoint inhibitors

Tumor vasculature is a key component of the tumor microenvironment that can influence tumor behavior and therapeutic resistance. We present a new imaging biomarker, quantitative vessel tortuosity (QVT), and evaluate its association with response and survival in patients with non-small cell lung cancer (NSCLC) treated with immune checkpoint inhibitor (ICI) therapies. A total of 507 cases were used to evaluate different aspects of the QVT biomarkers. QVT features were extracted from computed tomography imaging of patients before and after ICI therapy to capture the tortuosity, curvature, density, and branching statistics of the nodule vasculature. Our results showed that QVT features were prognostic of OS (HR = 3.14, 0.95% CI = 1.2 to 9.68, P = 0.0006, C-index = 0.61) and could predict ICI response with AUCs of 0.66, 0.61, and 0.67 on three validation sets. Our study shows that QVT imaging biomarker could potentially aid in predicting and monitoring response to ICI in patients with NSCLC.

Deep Learning Techniques to Diagnose Lung Cancer

Medical imaging tools are essential in early-stage lung cancer diagnostics and the monitoring of lung cancer during treatment. Various medical imaging modalities, such as chest X-ray, magnetic resonance imaging, positron emission tomography, computed tomography, and molecular imaging techniques, have been extensively studied for lung cancer detection. These techniques have some limitations, including not classifying cancer images automatically, which is unsuitable for patients with other pathologies. It is urgently necessary to develop a sensitive and accurate approach to the early diagnosis of lung cancer. Deep learning is one of the fastest-growing topics in medical imaging, with rapidly emerging applications spanning medical image-based and textural data modalities. With the help of deep learning-based medical imaging tools, clinicians can detect and classify lung nodules more accurately and quickly. This paper presents the recent development of deep learning-based imaging techniques for early lung cancer detection.

Research on CT Lung Segmentation Method of Preschool Children based on Traditional Image Processing and ResUnet

Lung segmentation using computed tomography (CT) images is important for diagnosing various lung diseases. Currently, no lung segmentation method has been developed for assessing the CT images of preschool children, which may differ from those of adults due to (1) presence of artifacts caused by the shaking of children, (2) loss of a localized lung area due to a failure to hold their breath, and (3) a smaller CT chest area, compared with adults. To solve these unique problems, this study developed an automatic lung segmentation method by combining traditional imaging methods with ResUnet using the CT images of 60 children, aged 0-6 years. First, the CT images were cropped and zoomed through ecological operations to concentrate the segmentation task on the chest area. Then, a ResUnet model was used to improve the loss for lung segmentation, and case-based connected domain operations were performed to filter the segmentation results and improve segmentation accuracy. The proposed method demonstrated promising segmentation results on a test set of 12 cases, with average accuracy, Dice, precision, and recall of 0.9479, 0.9678, 0.9711, and 0.9715, respectively, which achieved the best performance relative to the other six models. This study shows that the proposed method can achieve good segmentation results in CT of preschool children, laying a good foundation for the diagnosis of children's lung diseases.

Lung Field Segmentation in Chest X-ray Images Using Superpixel Resizing and Encoder–Decoder Segmentation Networks

Lung segmentation of chest X-ray (CXR) images is a fundamental step in many diagnostic applications. Most lung field segmentation methods reduce the image size to speed up the subsequent processing time. Then, the low-resolution result is upsampled to the original high-resolution image. Nevertheless, the image boundaries become blurred after the downsampling and upsampling steps. It is necessary to alleviate blurred boundaries during downsampling and upsampling. In this paper, we incorporate the lung field segmentation with the superpixel resizing framework to achieve the goal. The superpixel resizing framework upsamples the segmentation results based on the superpixel boundary information obtained from the downsampling process. Using this method, not only can the computation time of high-resolution medical image segmentation be reduced, but also the quality of the segmentation results can be preserved. We evaluate the proposed method on JSRT, LIDC-IDRI, and ANH datasets. The experimental results show that the proposed superpixel resizing framework outperforms other traditional image resizing methods. Furthermore, combining the segmentation network and the superpixel resizing framework, the proposed method achieves better results with an average time score of 4.6 s on CPU and 0.02 s on GPU.

Deep Learning-Based Automatic Assessment of Lung Impairment in COVID-19 Pneumonia: Predicting Markers of Hypoxia With Computer Vision

Background

Hypoxia is a potentially life-threatening condition that can be seen in pneumonia patients.

Objective

We aimed to develop and test an automatic assessment of lung impairment in COVID-19 associated pneumonia with machine learning regression models that predict markers of respiratory and cardiovascular functioning from radiograms and lung CT.

Materials and Methods

We enrolled a total of 605 COVID-19 cases admitted to Al Ain Hospital from 24 February to 1 July 2020 into the study. The inclusion criteria were as follows: age ≥ 18 years; inpatient admission; PCR positive for SARS-CoV-2; lung CT available at PACS. We designed a CNN-based regression model to predict systemic oxygenation markers from lung CT and 2D diagnostic images of the chest. The 2D images generated by averaging CT scans were analogous to the frontal and lateral view radiograms. The functional (heart and breath rate, blood pressure) and biochemical findings (SpO₂, HCO3-, K⁺, Na⁺, anion gap, C-reactive protein) served as ground truth.

Results

Radiologic findings in the lungs of COVID-19 patients provide reliable assessments of functional status with clinical utility. If fed to ML models, the sagittal view radiograms reflect dyspnea more accurately than the coronal view radiograms due to the smaller size and the lower model complexity. Mean absolute error of the models trained on single-projection radiograms was approximately 11÷12% and it dropped by 0.5÷1% if both projections were used (11.97 ± 9.23 vs. 11.43 ± 7.51%; p = 0.70). Thus, the ML regression models based on 2D images acquired in multiple planes had slightly better performance. The data blending approach was as efficient as the voting regression technique: 10.90 ± 6.72 vs. 11.96 ± 8.30%, p = 0.94. The models trained on 3D images were more accurate than those on 2D: 8.27 ± 4.13 and 11.75 ± 8.26%, p = 0.14 before lung extraction; 10.66 ± 5.83 and 7.94 ± 4.13%, p = 0.18 after the extraction. The lung extraction boosts 3D model performance unsubstantially (from 8.27 ± 4.13 to 7.94 ± 4.13%; p = 0.82). However, none of the differences between 3D and 2D were statistically significant.

Conclusion

The constructed ML algorithms can serve as models of structure-function association and pathophysiologic changes in COVID-19. The algorithms can improve risk evaluation and disease management especially after oxygen therapy that changes functional findings. Thus, the structural assessment of acute lung injury speaks of disease severity.

Medical Image Segmentation with Learning Semantic and Global Contextual Representation

Automatic medical image segmentation is an essential step toward accurate diseases diagnosis and designing a follow-up treatment. This assistive method facilitates the cancer detection process and provides a benchmark to highlight the affected area. The U-Net model has become the standard design choice. Although the symmetrical structure of the U-Net model enables this network to encode rich semantic representation, the intrinsic locality of the CNN layers limits this network’s capability in modeling long-range contextual dependency. On the other hand, sequence to sequence Transformer models with a multi-head attention mechanism can enable them to effectively model global contextual dependency. However, the lack of low-level information stemming from the Transformer architecture limits its performance for capturing local representation. In this paper, we propose a two parallel encoder model, where in the first path the CNN module captures the local semantic representation whereas the second path deploys a Transformer module to extract the long-range contextual representation. Next, by adaptively fusing these two feature maps, we encode both representations into a single representative tensor to be further processed by the decoder block. An experimental study demonstrates that our design can provide rich and generic representation features which are highly efficient for a fine-grained semantic segmentation task.

How AI Can Help in the Diagnostic Dilemma of Pulmonary Nodules

Simple Summary

Pulmonary nodules are considered a sign of bronchogenic carcinoma, detecting them early will reduce their progression and can save lives. Lung cancer is the second most common type of cancer in both men and women. This manuscript discusses the current applications of artificial intelligence (AI) in lung segmentation as well as pulmonary nodule segmentation and classification using computed tomography (CT) scans, published in the last two decades, in addition to the limitations and future prospects in the field of AI.

Abstract

Pulmonary nodules are the precursors of bronchogenic carcinoma, its early detection facilitates early treatment which save a lot of lives. Unfortunately, pulmonary nodule detection and classification are liable to subjective variations with high rate of missing small cancerous lesions which opens the way for implementation of artificial intelligence (AI) and computer aided diagnosis (CAD) systems. The field of deep learning and neural networks is expanding every day with new models designed to overcome diagnostic problems and provide more applicable and simply used models. We aim in this review to briefly discuss the current applications of AI in lung segmentation, pulmonary nodule detection and classification.

Origins of and lessons from quantitative functional X-ray computed tomography of the lung

Functional CT of the lung has emerged from quantitative CT (qCT). Structural details extracted at multiple lung volumes offer indices of function. Additionally, single volumetric images, if acquired at standardized lung volumes and body posture, can be used to model function by employing such engineering techniques as computational fluid dynamics. With the emergence of multispectral CT imaging including dual energy from energy integrating CT scanners and multienergy binning using the newly released photon counting CT technology, function is tagged via use of contrast agents. Lung disease phenotypes have previously been lumped together by the limitations of spirometry and plethysmography. QCT and its functional embodiment have been imbedded into studies seeking to characterize chronic obstructive pulmonary disease, severe asthma, interstitial lung disease and more. Reductions in radiation dose by an order of magnitude or more have been achieved. At the same time, we have seen significant increases in spatial and density resolution along with methodologic validations of extracted metrics. Together, these have allowed attention to turn towards more mild forms of disease and younger populations. In early applications, clinical CT offered anatomic details of the lung. Functional CT offers regional measures of lung mechanics, the assessment of functional small airways disease, as well as regional ventilation-perfusion matching (V/Q) and more. This paper will focus on the use of quantitative/functional CT for the non-invasive exploration of dynamic three-dimensional functioning of the breathing lung and beating heart within the unique negative pressure intrathoracic environment of the closed chest.

Quantitative evaluation of disease severity in connective tissue disease-associated interstitial lung disease by dual-energy computed tomography

Background

High-resolution computed tomography (HRCT) is recommended diagnosing and monitoring connective tissue disease-associated interstitial lung disease (CTD-ILD). Quantitative computed tomography has the potential to precisely assess the radiological severity of CTD-ILD, but has still been under study.

Objective

To investigate whether dual-energy computed tomography (DECT), a novel quantitative technique, can be used for quantitative severity assessment in CTD-ILD.

Methods

This cross sectional study recruited adult CTD-ILD patients who underwent DECT scans from the ICE study between October 2019 and November 2021. DECT parameters, including effective atomic number (Z_eff), lung (lobe) volume, and monochromatic CT number (MCTN) of each lung lobe, were evaluated. CTD-ILD was classified into extensive CTD-ILD and limited CTD-ILD by staging algorithm using combined forced vital capacity (FVC)%predicted and total extent of ILD (TEI) on CT. Dyspnea, cough, and life quality were scored by Borg dyspnea score, Leicester cough questionnaire (LCQ), and short-form 36 health survey questionnaire (SF-36), respectively.

Results

There was a total of 147 patients with DECT scans enrolled. Higher Z_eff value (3.104 vs 2.256, p < 0.001), higher MCTN (− 722.87 HU vs − 802.20 HU, p < 0.001), and lower lung volume (2309.51cm³ vs 3475.21cm³, p < 0.001) were found in extensive CTD-ILD compared with limited CTD-ILD. DECT parameters had significant moderate correlations with FVC%predicted (|r|= 0.542–0.667, p < 0.01), DLCO%predicted (|r|= 0.371–0.427, p < 0.01), and TEI (|r|= 0.485–0.742, p < 0.01). Receiver operating characteristic (ROC) analysis indicated MCTN averaged over the whole lung had the best performance for extensive CTD-ILD discrimination (AUC = 0.901, cut-off: − 762.30 HU, p < 0.001), with a sensitivity of 82.1% and a specificity of 85.4%. The Z_eff value was the independent risk factor for dyspnea (OR = 3.644, 95% CI: 1.846–7.192, p < 0.001) and cough (OR = 3.101, 95% CI: 1.528–6.294, p = 0.002), and lung volume significantly contributed to the mental component summary (MCS) in SF-36 (standardized β = 0.198, p < 0.05).

Conclusions

DECT can be applied to evaluate the severity of CTD-ILD.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12931-022-01972-4.

Detection and Classification of Bronchiectasis Through Convolutional Neural Networks

PURPOSE

Bronchiectasis is a chronic disease characterized by an irreversible dilatation of bronchi leading to chronic infection, airway inflammation, and progressive lung damage. Three specific patterns of bronchiectasis are distinguished in clinical practice: cylindrical, varicose, and cystic. The predominance and the extension of the type of bronchiectasis provide important clinical information. However, characterization is often challenging and is subject to high interobserver variability. The aim of this study is to provide an automatic tool for the detection and classification of bronchiectasis through convolutional neural networks.

MATERIALS AND METHODS

Two distinct approaches were adopted: (i) direct network performing a multilabel classification of 32×32 regions of interest (ROIs) into 4 classes: healthy, cylindrical, cystic, and varicose and (ii) a 2-network serial approach, where the first network performed a binary classification between normal tissue and bronchiectasis and the second one classified the ROIs containing abnormal bronchi into one of the 3 bronchiectasis typologies. Performances of the networks were compared with other architectures presented in the literature.

RESULTS

Computed tomography from healthy individuals (n=9, age=47±6, FEV1%pred=109±17, FVC%pred=116±17) and bronchiectasis patients (n=21, age=59±15, FEV1%pred=74±25, FVC%pred=91±22) were collected. A total of 19,059 manually selected ROIs were used for training and testing. The serial approach provided the best results with an accuracy and F1 score average of 0.84, respectively. Slightly lower performances were observed for the direct network (accuracy=0.81 and F1 score average=0.82). On the test set, cylindrical bronchiectasis was the subtype classified with highest accuracy, while most of the misclassifications were related to the varicose pattern, mainly to the cylindrical class.

CONCLUSION

The developed networks accurately detect and classify bronchiectasis disease, allowing to collect quantitative information regarding the radiologic severity and the topographical distribution of bronchiectasis subtype.

Automatic Lung Segmentation and Quantification of Aeration in Computed Tomography of the Chest Using 3D Transfer Learning

BACKGROUND

Identification of lung parenchyma on computer tomographic (CT) scans in the research setting is done semi-automatically and requires cumbersome manual correction. This is especially true in pathological conditions, hindering the clinical application of aeration compartment (AC) analysis. Deep learning based algorithms have lately been shown to be reliable and time-efficient in segmenting pathologic lungs. In this contribution, we thus propose a novel 3D transfer learning based approach to quantify lung volumes, aeration compartments and lung recruitability.

METHODS

Two convolutional neural networks developed for biomedical image segmentation (uNet), with different resolutions and fields of view, were implemented using Matlab. Training and evaluation was done on 180 scans of 18 pigs in experimental ARDS (u2Net Pig ) and on a clinical data set of 150 scans from 58 ICU patients with lung conditions varying from healthy, to COPD, to ARDS and COVID-19 (u2Net Human ). One manual segmentations (MS) was available for each scan, being a consensus by two experts. Transfer learning was then applied to train u2Net Pig on the clinical data set generating u2Net Transfer . General segmentation quality was quantified using the Jaccard index (JI) and the Boundary Function score (BF). The slope between JI or BF and relative volume of non-aerated compartment (S JI and S BF , respectively) was calculated over data sets to assess robustness toward non-aerated lung regions. Additionally, the relative volume of ACs and lung volumes (LV) were compared between automatic and MS.

RESULTS

On the experimental data set, u2Net Pig resulted in JI = 0.892 [0.88 : 091] (median [inter-quartile range]), BF = 0.995 [0.98 : 1.0] and slopes S JI = -0.2 {95% conf. int. -0.23 : -0.16} and S BF = -0.1 {-0.5 : -0.06}. u2Net Human showed similar performance compared to u2Net Pig in JI, BF but with reduced robustness S JI = -0.29 {-0.36 : -0.22} and S BF = -0.43 {-0.54 : -0.31}. Transfer learning improved overall JI = 0.92 [0.88 : 0.94], P < 0.001, but reduced robustness S JI = -0.46 {-0.52 : -0.40}, and affected neither BF = 0.96 [0.91 : 0.98] nor S BF = -0.48 {-0.59 : -0.36}. u2Net Transfer improved JI compared to u2Net Human in segmenting healthy (P = 0.008), ARDS (P < 0.001) and COPD (P = 0.004) patients but not in COVID-19 patients (P = 0.298). ACs and LV determined using u2Net Transfer segmentations exhibited < 5% volume difference compared to MS.

CONCLUSION

Compared to manual segmentations, automatic uNet based 3D lung segmentation provides acceptable quality for both clinical and scientific purposes in the quantification of lung volumes, aeration compartments, and recruitability.

Quantitative CT Analysis in Chronic Hypersensitivity Pneumonitis: A Convolutional Neural Network Approach

RATIONALE AND OBJECTIVES

Chronic hypersensitivity pneumonitis (cHP) is a heterogeneous condition, where both small airway involvement and fibrosis may simultaneously occur. Computer-aided analysis of CT lung imaging is increasingly used to improve tissue characterization in interstitial lung diseases (ILD), quantifying disease extension, and progression. We aimed to quantify via a convolutional neural network (CNN) method the extent of different pathological classes in cHP, and to determine their correlation to pulmonary function tests (PFTs) and mosaic attenuation pattern.

MATERIALS AND METHODS

The extension of six textural features, including consolidation (C), ground glass opacity (GGO), fibrosis (F), low attenuation areas (LAA), reticulation (R) and healthy regions (H), was quantified in 27 cHP patients (age: 56 ± 11.5 years, forced vital capacity [FVC]% = 57 ± 17) acquired at full-inspiration via HRCT. Each class extent was correlated to PFTs and to mosaic attenuation pattern.

RESULTS

H showed a positive correlation with FVC%, FEV1% (forced expiratory volume), total lung capacity%, and diffusion of carbon monoxide (DLCO)% (r = 0.74, r = 0.78, r = 0.73, and r = 0.60, respectively, p < 0.001). GGO, R and C negatively correlated with FVC% and FEV1% with the highest correlations found for R (r = -0.44, and r = -0.46 respectively, p < 0.05); F negatively correlated with DLCO% (r = -0.42, p < 0.05). Patients with mosaic attenuation pattern had significantly more H (p = 0.04) and lower R (p = 0.02) and C (p = 0.0009) areas, and more preserved lung function indices (higher FVC%; p = 0.04 and DLCO%; p = 0.05), but did not show more air trapping in lung function tests.

CONCLUSION

CNN quantification of pathological tissue extent in cHP improves its characterization and shows correlation with PFTs. LAA can be overestimated by visual, qualitative CT assessment and mosaic attenuation pattern areas in cHP represents patchy ILD rather than small-airways disease.

Deep Residual Separable Convolutional Neural Network for lung tumor segmentation

Lung cancer is one of the deadliest types of cancers. Computed Tomography (CT) is a widely used technique to detect tumors present inside the lungs. Delineation of such tumors is particularly essential for analysis and treatment purposes. With the advancement in hardware technologies, Machine Learning and Deep Learning methods are outperforming the traditional methods in the field of medical imaging. In order to delineate lung cancer tumors, we have proposed a deep learning-based methodology which includes a maximum intensity projection based pre-processing method, two novel deep learning networks and an ensemble strategy. The two proposed networks named Deep Residual Separable Convolutional Neural Network 1 and 2 (DRS-CNN1 and DRS-CNN2) achieved better performance over the state-of-the-art U-net network and other segmentation networks. For fair comparison, we have evaluated the performances of all networks on Medical Segmentation Decathlon (MSD) and StructSeg 2019 datasets. The DRS-CNN2 achieved a mean Dice Similarity Coefficient (DSC) of 0.649, mean 95 Hausdorff Distance (HD95) of 18.26, mean Sensitivity 0.737 and a mean Precision of 0.765 on independent test sets.

Texture-based classification of lung disease patterns in chronic hypersensitivity pneumonitis and comparison to clinical outcomes

Computer-aided detection algorithms applied to CT lung imaging have the potential to objectively quantify pulmonary pathology. We aim to develop an automatic classification method based on textural features able to classify healthy and pathological patterns on CT lung images and to quantify the extent of each disease pattern in a group of patients with chronic hypersensitivity pneumonitis (cHP), in comparison to pulmonary function tests (PFTs).27 cHP patients were scanned via high resolution CT (HRCT) at full-inspiration. Regions of interest (ROIs) were extracted and labeled as normal (NOR), ground glass opacity (GGO), reticulation (RET), consolidation (C), honeycombing (HB) and air trapping (AT). For each ROI, statistical, morphological and fractal parameters were computed. For automatic classification, we compared two classification methods (Bayesian and Support Vector Machine) and three ROI sizes. The classifier was therefore applied to the overall CT images and the extent of each class was calculated and compared to PFTs. Better classification accuracy was found for the Bayesian classifier and the 16x16 ROI size: 92.1±2.7%. The extent of GGO, HB and NOR significantly correlated with forced vital capacity (FVC) and the extent of NOR with carbon monoxide diffusing capacity (DLCO).Clinical Relevance- Texture analysis can differentiate and objectively quantify pathological classes in the lung parenchyma and may represent a quantitative diagnostic tool in cHP.

The Value of Effective Lung Ventilation Area Ratio Based on CT Image Analysis Is a New Index to Predict the Shorter Outcome of Anti-melanoma Differentiation-Associated Protein 5 Positive Dermatomyositis Associated Interstitial Lung Disease: A Single-Center Retrospective Study

Background: Anti-melanoma differentiation-associated protein 5 (MDA5) positive dermatomyositis (MDA5⁺DM) patients have poor outcomes due to rapidly progressive interstitial lung disease (ILD). The accurate assessment of lung involvement is an urgent focus of research. Methods: A computer-aided lung interstitial image analysis technology has been developed, and a quantitative indicator named effective lung ventilation area ratio (ELVAR) that calculates the proportion of the area outside the lung interstitium in lung tissue has been established. 55 newly diagnosed MDA5⁺DM patients and 46 healthy individuals, matched for age and gender, were enrolled in this study. MDA5⁺DM patients were classified into early death group or early survival group according to their survival state within 3 months after diagnosis. Clinical characteristics, laboratory and immunological test results, lung involvement (including ELVAR value) and treatment were compared between early death group and early survival group to determine an index that can predict prognoses of patients with MDA5⁺DM. Results: There were significant differences between early death MDA5⁺DM patients and early survival MDA5⁺DM patients about 12 indices including age of onset, CRP, ferritin, albumin, and pulmonary involvement including severity of type I respiratory failure at diagnosis, P/F ratio, oxygen supplementation, values of ELVAR, FVC, and DLCO. The results of ROC analysis and correlation analysis showed the value of ELVAR had good diagnostic value and widely correlation with many clinical characteristics. Univariate analysis and Multivariate analysis showed four factors including age of onset, ferritin, value of ELVAR, and oxygen supplementation >4 L/min significantly value for poor prognosis in MDA5⁺DM patients. A cutoff value of 0.835 about ELVAR had good predictive power for mortality within 3 months in 54.2% of MDA5⁺DM patients. Conclusion: The value of ELVAR derived from computed tomography image analysis is a new index that can predict poor outcomes in MDA5⁺DM patients with rapidly progressive interstitial lung disease.

Quantitative Multivolume Proton-Magnetic Resonance Imaging in Lung Transplant Recipients: Comparison With Computed Tomography and Spirometry

RATIONALE AND OBJECTIVES

Acute and chronic graft rejection remains the major problem in clinical surveillance of lung-transplanted patients and early detection of complications is of capital importance to allow the optimal therapeutic option. The aim of this study was to investigate the role of quantitative non contrast-enhanced magnetic resonance imaging (MRI) as a non-ionizing imaging modality to assess ventilation impairment in patients who have undergone lung transplantation, in comparison with quantitative computed tomography (CT) and spirometry.

MATERIALS AND METHODS

Ten lung-transplanted patients (39 ±12 years, forced-expiratory volume in 1 second (FEV1) = 81 ± 27%, forced vital capacity (FVC) = 87 ± 27%) were acquired in breath-hold at full-expiration and full-inspiration with 1.5T MRI and CT. Maps of expiratory-inspiratory difference in MR signal-intensity and CT-density were computed to estimate regional ventilation. Based on expiratory, inspiratory, and expiratory-inspiratory difference values, each pixel was classified as healthy (H), low ventilation (LV), air trapping (AT), and consolidation (C) and the percent extent of each class was quantified.

RESULTS

Overall, expiratory-inspiratory difference in MR signal-intensity correlated to CT-density (r = 0.64, p < 0.0001) and to FEV1 (ρ = 0.71, p = 0.02). The linear correlation between MRI and CT functional maps considering all the four classes is r = 0.93 (p < 0.0001). MRI percent volumes of H, AT, and C correlated to FEV1 %pred, with the highest correlation reported for AT (ρ = -0.82).

CONCLUSION

Results demonstrated a good agreement between MRI and CT ventilation imaging and between the corresponding percent volumes of lung damage. Quantitative MRI may represent an accurate non-ionizing imaging technique for longitudinal monitoring of lung transplant recipients.

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.

Integrating Lung Parenchyma Segmentation and Nodule Detection With Deep Multi-Task Learning

Lung parenchyma segmentation is valuable for improving the performance of lung nodule detection in computed tomography (CT) images. Traditionally, the two tasks are performed separately. This paper proposes a deep multi-task learning (MTL) approach to integrate these tasks for better lung nodule detection. Three new ideas lead to our proposed approach. First, lung parenchyma segmentation is used as the attention module and is combined with nodule detection in a single deep network. Second, lung nodule detection is performed in an anchor-free manner by dividing it into two subtasks, nodule center identification and nodule size regression. Third, a novel pyramid dilated convolution block (PDCB) is proposed to utilize the advantage of dilated convolution and tackle its gridding problem for better lung parenchyma segmentation. Based on these ideas, we design our end-to-end deep network architecture and corresponding MTL method to achieve lung parenchyma segmentation and nodule detection simultaneously. We evaluate the proposed approach on the commonly used Lung Nodule Analysis 2016 (LUNA16) dataset. The experimental results show the value of our contributions and demonstrate that our approach can yield significant improvements compared with state-of-the-art counterparts.

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.

Three-dimensional image reconstruction based on improved U-net network for anatomy of pulmonary segmentectomy

Pulmonary segmentectomy is one of the advanced techniques in thoracic surgery, but it is difficult to understand and master because of its complex anatomical structure. The purpose of this study is to explore the application effect of three-dimensional (3D) image reconstruction based on an improved U-net network in the anatomy of thoracic surgery. In this study, a total of 40 standardization training residents of thoracic surgery in our hospital were randomly divided into two groups. The control group was taught by conventional thin-slice CT images, while the observation group was taught by 3D image reconstruction based on the improved U-net network. After the training process was completed, the teaching effect was compared between these two groups. Using the improved U-net network model, 3D reconstruction of pulmonary segments can be realized quickly. Compared with the control group, the individual and total objective scores in the observation group were higher. The satisfaction of learning interest, content understanding, clinical thinking mode, and understanding of operation process in the observation group was higher than that of the control group. From the results, we concluded that the 3D image reconstruction technology based on the improved U-net network could help students master the anatomical structure of pulmonary segments and improve their learning interest and clinical thinking ability.

A 3D image segmentation for lung cancer using V.Net architecture based deep convolutional networks

Lung segmentation of chest CT scan is utilised to identify lung cancer and this step is also critical in other diagnostic pathways. Therefore, powerful algorithms to accomplish this accurate segmentation task are highly needed in the medical imaging domain, where the tumours are required to be segmented with the lung parenchyma. Also, the lung parenchyma needs to be detached from the tumour regions that are often confused with the lung tissue. Recently, lung semantic segmentation is more suitable to allocate each pixel in the image to a predefined class based on fully convolutional networks (FCNs). In this paper, CT cancer scans from the Task06_Lung database were applied to FCN that was inspired by V.Net architecture for efficiently selecting a region of interest (ROI) using the 3D segmentation. This lung database is segregated into 64 training images and 32 testing images. The proposed system is generalised by three steps including data preprocessing, data augmentation and neural network based on the V-Net model. Then, it was evaluated by dice score coefficient (DSC) to calculate the ratio of the segmented image and the ground truth image. This proposed system outperformed other previous schemes for 3D lung segmentation with an average DCS of 80% for ROI and 98% for surrounding lung tissues. Moreover, this system demonstrated that 3D views of lung tumours in CT images precisely carried tumour estimation and robust lung segmentation.

Lung Segmentation on HRCT and Volumetric CT for Diffuse Interstitial Lung Disease Using Deep Convolutional Neural Networks

A robust lung segmentation method using a deep convolutional neural network (CNN) was developed and evaluated on high-resolution computed tomography (HRCT) and volumetric CT of various types of diffuse interstitial lung disease (DILD). Chest CT images of 617 patients with various types of DILD, including cryptogenic organizing pneumonia (COP), usual interstitial pneumonia (UIP), and nonspecific interstitial pneumonia (NSIP), were scanned using HRCT (1-2-mm slices, 5-10-mm intervals) and volumetric CT (sub-millimeter thickness without intervals). Each scan was segmented using a conventional image processing method and then manually corrected by an expert thoracic radiologist to create gold standards. The lung regions in the HRCT images were then segmented using a two-dimensional U-Net architecture with the deep CNN, using separate training, validation, and test sets. In addition, 30 independent volumetric CT images of UIP patients were used to further evaluate the model. The segmentation results for both conventional and deep-learning methods were compared quantitatively with the gold standards using four accuracy metrics: the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). The mean and standard deviation values of those metrics for the HRCT images were 98.84 ± 0.55%, 97.79 ± 1.07%, 0.27 ± 0.18 mm, and 25.47 ± 13.63 mm, respectively. Our deep-learning method showed significantly better segmentation performance (p < 0.001), and its segmentation accuracies for volumetric CT were similar to those for HRCT. We have developed an accurate and robust U-Net-based DILD lung segmentation method that can be used for patients scanned with different clinical protocols, including HRCT and volumetric CT.

Generation-based study of airway remodeling in smokers with normal-looking CT with normalization to control inter-subject variability

PURPOSE

With the help of quantitative computed tomography (QCT), it is possible to identify smoking-associated airway remodeling. However, there is currently little information on whether QCT-based airway metrics are sensitive to early airway wall remodeling in subclinical phases of smoking-associated airway disease. This study aimed to evaluate a predictive model that normalized airway parameters and investigate structural airway alterations in smokers with normal-looking CT using the normalization scheme.

METHODS

In this retrospective analysis, 222 non-smokers (male 97, female 125) and 69 smokers (male 66, female 3) from January 2014 to December 2016 were included, and airway parameters were quantitatively analyzed. To control inter-subject variability, multiple linear regressions of tracheal wall thickness (WT), diameter (D), and luminal area (LA) were performed, adjusted for age, sex, and height. Using this normalization scheme, airway parameters with matched generation were compared between smokers and non-smokers.

RESULTS

Using the normalization scheme, it was possible to assess generation-based structural alterations of the airways in subclinical smokers. Smokers showed diffuse luminal narrowing of airways for most generations (P < 0.05, except 3rd generation), no change in wall thickness of the proximal bronchi (1st-3rd generation), and a thinning of distal airways (P <0.05, ≥4th generation).

CONCLUSION

QCT assessment for subclinical smokers can help identify minimal structural changes in airways induced by smoking.

3D segmentation of lungs with juxta-pleural tumor using the improved active shape model approach

BACKGROUND AND OBJECTIVE:

At present, there are many methods for pathological lung segmentation. However, there are still two unresolved problems. (1) The search steps in traditional ASM is a least square optimization method, which is sensitive to outlier marker points, and it makes the profile update to the transition area in the middle of normal lung tissue and tumor rather than a true lung contour. (2) If the noise images exist in the training dataset, the corrected shape model cannot be constructed.

METHODS:

To solve the first problem, we proposed a new ASM algorithm. Firstly, we detected these outlier marker points by a distance method, and then the different searching functions to the abnormal and normal marker points are applied. To solve the second problem, robust principal component analysis (RPCA) of low rank theory can remove noise, so the proposed method combines RPCA instead of PCA with ASM to solve this problem. Low rank decompose for marker points matrix of training dataset and covariance matrix of PCA will be done before segmentation using ASM.

RESULTS:

Using the proposed method to segment 122 lung images with juxta-pleural tumors of EMPIRE10 database, got the overlap rate with the gold standard as 94.5%. While the accuracy of ASM based on PCA is only 69.5%.

CONCLUSIONS:

The results showed that when the noise sample is contained in the training sample set, a good segmentation result for the lungs with juxta-pleural tumors can be obtained by the ASM based on RPCA.

Pathological lung segmentation in chest CT images based on improved random walker

BACKGROUND AND OBJECTIVE

Pathological lung segmentation as a pretreatment step in the diagnosis of lung diseases has been widely explored. Because of the complexity of pathological lung structures and gray blur of the border, accurate lung segmentation in clinical 3D computed tomography images is a challenging task. In view of the current situation, the work proposes a fast and accurate pathological lung segmentation method. The following contributions have been made: First, the edge weights introduce spatial information and clustering information, so that walkers can use more image information during walking. Second, a Gaussian Distribution of seed point set is established to further expand the possibility of selection between fake seed points and real seed points. Finally, the pre-parameter is calculated using original seed points, and the final results are fitted with new seed points.

METHODS

This study proposes a segmentation method based on an improved random walker algorithm. The proposed method consists of the following steps: First, a gray value is used as the sample distribution. Gaussian mixture model is used to obtain the clustering probability of an image. Thus, the spatial distance and clustering result are added as new weights, and the new edge weights are used to construct a random walker map. Second, a large number of marked points are automatically selected, and the intermediate results are obtained from the newly constructed map and retained only as pre-parameters. When new seed points are introduced, the probability value of the walker is quickly calculated from the new parameters and pre-parameters, and the final segmentation result can be obtained.

RESULTS

The proposed method was tested on 65 sets of CT cases. Quantitative evaluation with different methods confirms the high accuracy on our dataset (98.55%) and LOLA11 dataset (97.41%). Similarly, the average segmentation time (10.5s) is faster than random walker (1,332.5s).

CONCLUSIONS

The comparison of the experimental results show that the proposed method can accurately and quickly obtain pathological lung processing results. Therefore, it has potential clinical applications.

Plasma metabolomic profiling of patients recovered from COVID-19 with pulmonary sequelae 3 months after discharge

Background

Elucidation of the molecular mechanisms involved in the pathogenesis of coronavirus disease 2019 (COVID-19) may help to discover therapeutic targets.

Methods

To determine the metabolomic profile of circulating plasma from COVID-19 survivors with pulmonary sequelae 3 months after discharge, a random, outcome-stratified case-control sample was analyzed. We enrolled 103 recovered COVID-19 patients as well as 27 healthy donors, and performed pulmonary function tests, computerized tomography (CT) scans, laboratory examinations, and liquid chromatography-mass spectrometry.

Results

Plasma metabolite profiles of COVID-19 survivors with abnormal pulmonary function were different from those of healthy donors or subjects with normal pulmonary function. These alterations were associated with disease severity and mainly involved amino acid and glycerophospholipid metabolic pathways. Furthermore, increased levels of triacylglycerols, phosphatidylcholines, prostaglandin E2, arginine, and decreased levels of betain and adenosine were associated with pulmonary CO diffusing capacity and total lung capacity. The global plasma metabolomic profile differed between subjects with abnormal and normal pulmonary function.

Conclusions

Further metabolite-based analysis may help to identify the mechanisms underlying pulmonary dysfunction in COVID-19 survivors, and provide potential therapeutic targets in the future.

CT image segmentation for inflamed and fibrotic lungs using a multi-resolution convolutional neural network

The purpose of this study was to develop a fully-automated segmentation algorithm, robust to various density enhancing lung abnormalities, to facilitate rapid quantitative analysis of computed tomography images. A polymorphic training approach is proposed, in which both specifically labeled left and right lungs of humans with COPD, and nonspecifically labeled lungs of animals with acute lung injury, were incorporated into training a single neural network. The resulting network is intended for predicting left and right lung regions in humans with or without diffuse opacification and consolidation. Performance of the proposed lung segmentation algorithm was extensively evaluated on CT scans of subjects with COPD, confirmed COVID-19, lung cancer, and IPF, despite no labeled training data of the latter three diseases. Lobar segmentations were obtained using the left and right lung segmentation as input to the LobeNet algorithm. Regional lobar analysis was performed using hierarchical clustering to identify radiographic subtypes of COVID-19. The proposed lung segmentation algorithm was quantitatively evaluated using semi-automated and manually-corrected segmentations in 87 COVID-19 CT images, achieving an average symmetric surface distance of [Formula: see text] mm and Dice coefficient of [Formula: see text]. Hierarchical clustering identified four radiographical phenotypes of COVID-19 based on lobar fractions of consolidated and poorly aerated tissue. Lower left and lower right lobes were consistently more afflicted with poor aeration and consolidation. However, the most severe cases demonstrated involvement of all lobes. The polymorphic training approach was able to accurately segment COVID-19 cases with diffuse consolidation without requiring COVID-19 cases for training.