Lung Imaging Research Articles

COVID Pneumonia Severity Detection of Chest CT-Scan Images based on Robust Semantic Segmentation

Image segmentation has steadily grown especially for clinical usage and disease recognition in radiological research. This procedure, aimed at acquiring quantitative measurements, strives to distinguish regions or objects of interest from adjacent body tissues. To be more specific, it entails measuring the area and volume of segmented structures to extract more refined diagnostic information. The main hurdles encountered by segmentation algorithms originate from challenges like variations in intensity, artifacts, and the close juxtaposition of diverse soft tissues in the grayscale. In this paper, a robust semantic segmentation is proposed to specify the infected regions of lung images and consider the severity degree of the pneumonia caused by COVID-19 disease. The proposed model provides an accurate diagnosis of the chest CT scan image with satisfied performance with 93% accuracy and the second most important metric which is the Jaccard Index with 0.746±0.09 shows higher prediction performance than most existing systems in the literature.

Preparation of a Novel Multifunctional Cationic Liposome Drug-carrying System and its Functional Study on Lung Cancer.

Low-dose chemotherapy is a promising treatment strategy that may be improved by controlled delivery. This study aimed to design polyethylene glycol-stabilized bilayer-decorated magnetic Cationic Liposomes (CLs) as a drug delivery system for integrated functional studies of lung cancer cell therapy and imaging. A novel multifunctional folic acid targeting magnetic CLs docetaxel drug-loading system (FA-CLs-Fe- DOC) was prepared and tested for its physical properties, encapsulation rate and drug release performance. The feasibility of FA-CLs-Fe-DOC ability to inhibit tumor cells and act as an MRI contrast agent was investigated in vitro, and the target recognition and therapeutic ability of FA-CLs-Fe-DOC was studied in vivo. FA-CLs-Fe-DOC had a particle size of 221.54 ± 6.42 nm and a potential of 28.64 ± 3.56 mv, with superparamagnetic properties and better stability. The encapsulation rate was 95.36 ± 1.63%, and the drug loading capacity was 9.52 ± 0.22%, which possessed the drug slow-release performance and low cytotoxicity and could effectively inhibit the proliferation of lung cancer cells, promoting apoptosis of lung cancer cells. MRI showed that it had the function of tracking and localization of lung cancer cells. In vivo experiments confirmed the targeted recognition property and therapeutic function of lung cancer cells. In this study, we successfully prepared an FA-CLs-Fe-DOC capable of specifically targeting lung cancer cells with integrated functions of efficient lung cancer cell killing and imaging localization. This targeted drug packaging technology may provide a new strategy for the design of integrated carriers for targeted cancer therapy and imaging.

Comparative analysis of ultrasonographic fetal lung texture in twin and singleton fetuses.

Increased fetal lung heterogeneity has been associated with term fetal lungs in singleton gestations. Theobjective of this study was to determine if fetal lung heterogeneity index (HI) differs between twin and singleton fetuses in the late second and third trimesters. Prospective cohort study of women with singleton and twin gestations with medically-indicated ultrasound examinations at 24weeks of gestation onward. Grayscale transverse fetal lung images were obtained at thelevel of the four-chamber heart. A region of interest wasselected in each fetal lung image. Fetal lung HI was determined with MATLAB software using a dithering technique with ultrasound image pixels transformed into a binary map form from which a dynamic range value was determined. HI averages and standard deviations were generated for twin and singleton fetuses from 24weeks gestation onward. Two sample t-tests were used to compare the mean HI at each gestational week between singleton and twin fetuses. In total, 388 singleton and 478 twin images were analyzed. From 35 through 38weeks of gestation a statistically significant divergence in mean HI was observed withhigher means in singleton compared to twin fetuses. At24weeks of gestation there was a significantly higher HI in twin fetuses compared to singletons. No differences in fetal lung HI were observed between 25 and 34weeks gestational age. Differences in fetal lung HI were observed when comparing twin and singleton fetuses. Further investigation is required to determine the potential clinical significance of these findings.

Enhancing cancer prediction in challenging screen-detected incident lung nodules using time-series deep learning

Lung cancer screening (LCS) using annual computed tomography (CT) scanning significantly reduces mortality by detecting cancerous lung nodules at an earlier stage. Deep learning algorithms can improve nodule malignancy risk stratification. However, they have typically been used to analyse single time point CT data when detecting malignant nodules on either baseline or incident CT LCS rounds. Deep learning algorithms have the greatest value in two aspects. These approaches have great potential in assessing nodule change across time-series CT scans where subtle changes may be challenging to identify using the human eye alone. Moreover, they could be targeted to detect nodules developing on incident screening rounds, where cancers are generally smaller and more challenging to detect confidently.Here, we show the performance of our Deep learning-based Computer-Aided Diagnosis model integrating Nodule and Lung imaging data with clinical Metadata Longitudinally (DeepCAD-NLM-L) for malignancy prediction. DeepCAD-NLM-L showed improved performance (AUC = 88%) against models utilizing single time-point data alone. DeepCAD-NLM-L also demonstrated comparable and complementary performance to radiologists when interpreting the most challenging nodules typically found in LCS programs. It also demonstrated similar performance to radiologists when assessed on out-of-distribution imaging dataset. The results emphasize the advantages of using time-series and multimodal analyses when interpreting malignancy risk in LCS.

Prognostic value of biohybrid screening results for assessing cancer risk using the example of lung cancer

Introduction. One of the leading places in the structure of socially significant diseases in the Russian Federation is occupied by malignant neoplasms, among which cancer of the trachea, bronchi and lung occupies the first place in terms of prevalence. Screening for lung cancer is not carried out at the federal level in Russia; recommended screening measures include questionnaires to identify risk factors for the development of the disease (including occupational) and the formation of dispensary observation groups. The study aims to assess the prognostic value of a new method of biohybrid screening of lung cancer by exhaled air. Materials and methods. Scientists conducted a study at the National Medical Research Center of Oncology of the Ministry of Health, Russian Federation, with the participation of 24 conditionally healthy volunteers and 5 patients diagnosed with lung cancer in the early stages of the disease. The design of the study is simultaneous (on-line) with blinding; experts estimated the risk of systematic errors at 10 points on the QUADAS scale. The authors examined exhaled air samples on a gas analyzer (biohybrid detector) of the BGS-APK 02SZZ model, in which the sensor were animals — gray domesticated rats (Rattus norvegicus) with microelectrode matrices implanted into the olfactory bulb, and which were in the internal (ventilated) space of the analyzer in a state of drug anesthesia. The conclusion about the presence or absence of a risk of lung cancer was formed by an artificial neural network of the analyzer, at the input of which bioelectric signals from each microelectrode were received, which were preprocessed using a system for recording the focal activity of the olfactory analyzer. The specialists confirmed the presence or absence of a risk of lung cancer by a reference method, according to computed tomography of the chest in accordance with the Lung Imaging Reporting and Data System (LungRADS™). Results. During the study, experts determined the effectiveness indicators of the method of biohybrid lung cancer screening by exhaled air: sensitivity (64%), specificity (87%), prognosticality of negative and positive conclusions about the presence/absence of disease risk (82% and 72%, respectively). Conclusion. The safety, efficiency and throughput of the investigated method, together with the reproducibility of the analyzer's conclusions, meet the criteria of practicability to ensure the first (population-based) stage of lung cancer screening.

Distributed edge to cloud ensemble deep learning architecture to diagnose Covid-19 from lung image in IoT based e-Health system

Distributed edge to cloud ensemble deep learning architecture to diagnose Covid-19 from lung image in IoT based e-Health system

Hybrid Artificial Intelligence Approach to COVID-19 Diagnosis from CT Images: Deep Networks and Classification Analysis

Using lung images obtained by computed tomography (CT), this study aims to detect coronavirus (Covid-19) disease with deep learning (DL) techniques. The study included 751 lung CT images from 118 Covid-19 patients and 628 lung CT images from 100 healthy individuals. In total, 70% of the 1379 images were used for training and 30% for testing. In the study, two different methods were proposed on the same dataset. In the first method, the images were trained on AlexNet, VGG-16, VGG-19, GoogleNet and a proposed network. The performance metrics obtained from the five networks were compared and it was observed that the proposed network achieved the highest accuracy value with 95.61%. In the second method, the images were trained on VGG-16, VGG-19, DenseNet-121, ResNet-50 and MobileNet networks. Among the image features obtained from each of these networks, the best 1000 features were selected by Principal Component Analysis (PCA). The best 1000 features were classified with Random Forest (RF) and Support Vector Machines (SVM). According to the classification results, the best 1000 features selected from the features extracted by the VGG-16 and MobileNet networks were obtained with the highest accuracy rate of 93.94% using SVM. It is thought that this study can be a helpful tool in the diagnosis of Covid-19 disease while reducing time and labor costs with the use of artificial intelligence (AI).

Lung and Colon Cancer Histopathological Image Classification Using 1D Convolutional Channel-based Attention Networks

Lung and Colon cancer are the leading diseases of death and disability in humans caused by a combination of genetic diseases and biochemical abnormalities. If these are diagnosed in their early stages, they can not be spread in organs and negatively impact human life. Many deep-learning networks have recently been proposed to detect and classify these malignancies. However, incorrect detection or misclassification of these fatal diseases can significantly affect an individual's health and well-being. This paper introduces a novel, cost-effective, and mobile-embedded architecture to diagnose and classify Lung squamous cell carcinomas and adenocarcinomas of the lung and colon from digital pathology images. Extensive experiment shows that our proposed modifications achieve 100% testing results for lung, colon, and lung-and-colon cancer detection. Our novel architecture takes around 0.65 million trainable parameters and around 6.4 million flops to achieve the best lung and colon cancer detection performance. Compared with the other results, our proposed architecture shows state-of-the-art performance.

Comparison of Interstitial Lung Disease Between Antineutrophil Cytoplasmic Antibodies Positive and Negative Patients: A Retrospective Cohort Study.

Positive antineutrophil cytoplasmic antibodies (ANCAs) may occur in the setting of interstitial lung disease (ILD), with or without ANCA-associated vasculitis (AAV). We aim to compare the characteristics and clinical course of patients with ILD and positive ANCA (ANCA-ILD) to those with negative ANCA. We performed a single-center retrospective cohort study from 2018 to 2021. All patients with ILD and ANCA testing were included. Patient characteristics (symptoms, dyspnea scale, and systemic AAV), test results (pulmonary high-resolution computed tomography and pulmonary function tests), and adverse events were collected from electronic medical records. Descriptive statistics and the Fisher exact test were used to compare the outcomes of patients with ANCA-ILD to those with ILD and negative ANCA. A total of 265 patients with ILD were included. The mean follow-up duration was 69.3 months, 26 patients (9.8%) were ANCA positive, and 69.2% of those with ANCA-ILD had another autoantibody. AAV occurred in 17 patients (65.4%) with ANCA-ILD. In 29.4% of patients, AAV developed following ILD diagnosis. Usual interstitial pneumonia was the most common radiologic pattern in patients with ANCA-ILD. There was no association between ANCA status and the evolution of dyspnea,diffusing capacity of the lungs for carbon monoxide, and lung imaging. Forced vital capacity improved over time in 42% of patients with ANCA-ILD and in 17% of patients with negative ANCA (P = 0.006). Hospitalization occurred in 46.2% of patients with ANCA-ILD and in 21.8% of patients with negative ANCA (P = 0.006). Both groups had similar mortality rates. Routine ANCA testing should be considered in patients with ILD. Patients with ANCA-ILD are at risk for AAV. More research is required to better understand and manage patients with ANCA-ILD.

Lung cancer computed tomography image classification using Attention based Capsule Network with dispersed dynamic routing

AbstractLung cancer is relying as one of the significant and leading cause for the deaths which are based on cancer. So, an effective diagnosis is a crucial step to save the patients who are all dying due to lung cancer. Moreover, the diagnosis must be performed based on the severity of lung cancer and the severity can be addressed with the help of an optimal classification approach. So, this research introduced an Attention based Capsule Network (A‐Caps Net) with dispersed dynamic routing to perform in‐depth classification of the disease affected partitions of the image and results in better classification results. The attention layer with dispersed dynamic routing evaluates the digit capsule from feature vector in a constant manner. As the first stage, data acquisitioned from datasets such as Lung Nodule Analysis‐16 (LUNA‐16), The Cancer Imaging Archive (TCIA) dataset and Lung Image Database Consortium and Image Database Resource Initiative (LIDC‐IDRI). After acquisitioning data, pre‐processing is done to enhance the resolution of the image using Generative Adversarial Network. The pre‐processed output is given as output for extraction of features that takes place using GLCM and VGG‐16 which extracts the low level features and high level features respectively. Finally, categorization of lung cancer is performed using Attention based Capsule Network (A‐Caps Net) with dispersed dynamic routing which categorize the lung cancer as benign and malignant. The results obtained through experimental analysis exhibits that proposed approach attained better accuracy of 99.57%, 99.91% and 99.29% for LUNA‐16, LIDC‐IDRI and TCIA dataset respectively. The classification accuracy achieved by the proposed approach for LUNA‐16 dataset is 99.57% which is comparably higher than DBN, 3D CNN, Squeeze Nodule Net and 3D‐DCNN with multi‐layered filter with accuracies of 99.16%, 97.17% and 94.1% respectively.

Lung Cancer Detection Using a Modified Convolutional Neural Network (CNN)

<p><span>Image processing is used to classify lung images with malignant or normal nodules. The Convolutional Neural Network (CNN) method is often used to classify images. This study uses a modified CNN architecture with various layers, filters, batch size, dropout, and epoch values. Variations were made to determine the best accuracy value and reduce the overfitting value of the proposed CNN architecture. This study implements the method using the Keras library with the Python programming language. The data is in the form of CT-Scan images of lung cancer and normal lungs. The results of several experiments from the proposed model produce an accuracy value of 95% using three layers, 128 filters on the first layer, 256 on the second layer, and 512 filters on the third layer, then with 32 batch sizes, 0.5 dropout.</span></p>

SwinRes: A hybrid model that effectively diagnoses COVID‐19 through x‐ray lung images

AbstractCOVID‐19 has been ravaging the world for a long time, and although its effects are currently the same as those of a cold or a fever, timely diagnosis of COVID‐19 in the elderly and in patients with related illnesses is still a matter of great urgency. To address this challenge, we propose a model that combines the strengths of the Swin Transformer and ResNet34 architectures to efficiently diagnose COVID‐19 in elderly and vulnerable patients. In this paper, we design a model that integrates Swin transformer and resnet34, which not only integrates the advantages of transformer and CNN but also achieves excellent performance in this image classification problem. Moreover, a pre‐processing method is also proposed to increase the accuracy of the model to 99.08%. In this paper, experiments were conducted on Kaggle's publicly available three‐classification and four‐classification datasets, respectively, and on the three main evaluation metrics of Accuracy, Precision, and Recall, the first dataset obtained 98.81%, 99.49%, and 97.99%, while the second dataset obtained 88.82%, 88.92%, and 86.38%. These findings highlight the validity and potential of our proposed model for diagnosing the presence or absence of COVID‐19 in elderly and vulnerable patients.

Programming of neutrophil transcriptome by endothelial ERG maintains anti-inflammatory vascular niche in the lungs

Neutrophils, the predominant blood leukocyte and first responders to the infection, reside as the marginated pool in the lungs. Vascular hyperpermeability and activation of infiltrating neutrophils is the hallmark of lethal acute lung injury (ALI) and acute respiratory distress syndrome (ARDS). However, signaling nodes that govern crosstalk among these ontologically distinct cell types to maintain tissue homeostasis remain unclear. Here, we identify the ERG transcription factor, which maintains endothelial cell (EC) lineage, as the instructor of anti-inflammatory neutrophils. We show that ERG is highly expressed in lung EC, but the expression was reduced markedly during neutrophilic injury by bacterial pneumonia. Intravital imaging and FACS analysis of mice lungs conditionally lacking ERG in the endothelium (iEC-ERG−/−mice) showed increased neutrophil retention and activation due to rewiring of their transcriptome (hereafter referred to as EC-ERG null neutrophils). RNA sequencing of EC-ERG null neutrophils showed genes enriched with inflammation (IL-1β, TNF-α, MIP-2α), survival (RelB, CD47), and retention (CXCR4) markers. Neutrophils isolated from the blood of ARDS patients similarly showed increased expression of IL-8, TNF-α, and CXCR4 expression. EC-ERG null neutrophils induced lung injury when adoptively transferred into a naïve mouse. EC-ERG loss elicited an immune migratory and chemotactic program by activating the NF-κB-IL8 cascade, exacerbating ALI in a mouse model. We show that ERG in endothelium preserves neutrophil activation and infiltration by upregulating the multipurpose deubiquitinase A20 expression in mouse and human lung endothelial cells (EC). Rescuing A20 deubiquitinase or suppressing IL8-CXCR2 axis through small molecule inhibitor, Reparixin, reversed hyperpermeability, and neutrophilic injury. In summary, our study identifies specialized ERG-instructed anti-inflammatory ‘immune niche’ to prevent neutrophilic inflammation and lung injury. National Institutes of Health (NIH) Grants HL060678, HL084153. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures

Automatic classification of colon and lung cancer images is crucial for early detection and accurate diagnostics. However, there is room for improvement to enhance accuracy, ensuring better diagnostic precision. This study introduces two novel dense architectures (D1 and D2) and emphasizes their effectiveness in classifying colon and lung cancer from diverse images. It also highlights their resilience, efficiency, and superior performance across multiple datasets. These architectures were tested on various types of datasets, including NCT-CRC-HE-100K (set of 100,000 non-overlapping image patches from hematoxylin and eosin (H&E) stained histological images of human colorectal cancer (CRC) and normal tissue), CRC-VAL-HE-7K (set of 7180 image patches from N = 50 patients with colorectal adenocarcinoma, no overlap with patients in NCT-CRC-HE-100K), LC25000 (Lung and Colon Cancer Histopathological Image), and IQ-OTHNCCD (Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases), showcasing their effectiveness in classifying colon and lung cancers from histopathological and Computed Tomography (CT) scan images. This underscores the multi-modal image classification capability of the proposed models. Moreover, the study addresses imbalanced datasets, particularly in CRC-VAL-HE-7K and IQ-OTHNCCD, with a specific focus on model resilience and robustness. To assess overall performance, the study conducted experiments in different scenarios. The D1 model achieved an impressive 99.80 % accuracy on the NCT-CRC-HE-100K dataset, with a Jaccard Index (J) of 0.8371, a Matthew's Correlation Coefficient (MCC) of 0.9073, a Cohen's Kappa (Kp) of 0.9057, and a Critical Success Index (CSI) of 0.8213. When subjected to 10-fold cross-validation on LC25000, the D1 model averaged (avg) 99.96 % accuracy (avg J, MCC, Kp, and CSI of 0.9993, 0.9987, 0.9853, and 0.9990), surpassing recent reported performances. Furthermore, the ensemble of D1 and D2 reached 93 % accuracy (J, MCC, Kp, and CSI of 0.7556, 0.8839, 0.8796, and 0.7140) on the IQ-OTHNCCD dataset, exceeding recent benchmarks and aligning with other reported results. Efficiency evaluations were conducted in various scenarios. For instance, training on only 10 % of LC25000 resulted in high accuracy rates of 99.19 % (J, MCC, Kp, and CSI of 0.9840, 0.9898, 0.9898, and 0.9837) (D1) and 99.30 % (J, MCC, Kp, and CSI of 0.9863, 0.9913, 0.9913, and 0.9861) (D2). In NCT-CRC-HE-100K, D2 achieved an impressive 99.53 % accuracy (J, MCC, Kp, and CSI of 0.9906, 0.9946, 0.9946, and 0.9906) with training on only 30 % of the dataset and testing on the remaining 70 %. When tested on CRC-VAL-HE-7K, D1 and D2 achieved 95 % accuracy (J, MCC, Kp, and CSI of 0.8845, 0.9455, 0.9452, and 0.8745) and 96 % accuracy (J, MCC, Kp, and CSI of 0.8926, 0.9504, 0.9503, and 0.8798), respectively, outperforming previously reported results and aligning closely with others. Lastly, training D2 on just 10 % of NCT-CRC-HE-100K and testing on CRC-VAL-HE-7K resulted in significant outperformance of InceptionV3, Xception, and DenseNet201 benchmarks, achieving an accuracy rate of 82.98 % (J, MCC, Kp, and CSI of 0.7227, 0.8095, 0.8081, and 0.6671). Finally, using explainable AI algorithms such as Grad-CAM, Grad-CAM++, Score-CAM, and Faster Score-CAM, along with their emphasized versions, we visualized the features from the last layer of DenseNet201 for histopathological as well as CT-scan image samples. The proposed dense models, with their multi-modality, robustness, and efficiency in cancer image classification, hold the promise of significant advancements in medical diagnostics. They have the potential to revolutionize early cancer detection and improve healthcare accessibility worldwide.

Convolutional Neural Networks Applied to Lung Image Detection: Model Comparison and Optimal Selection

The topic of pulmonary health has become a prevalent concern among the public, making monitoring lung health a crucial subject. Numerous researchers have proposed models or methods for detecting pulmonary images, and their effectiveness has been confirmed. However, in the domain of pulmonary image detection, there is a systematic comparison to identify the most suitable and efficient method. Therefore, the theme of this study is to discover, through comparative analysis, the model method most fitting for current pulmonary image detection. The research methodology is outlined as follows: firstly, introduce popular model methods in the current context; secondly, summarize and record the accuracy of each model in pulmonary image recognition; and finally, conduct a horizontal comparison to derive conclusions regarding the optimal model method. This study reveals that Feature Fusion exhibits an outstanding accuracy of 97.79% in pulmonary image recognition, securing the top position. In contrast, Transformer has the lowest accuracy, yet it still reaches 78.9%. Therefore, Feature Fusion emerges as the most promising model method currently deserving widespread promotion in the field of pulmonary image detection.

Continual Monitoring of Respiratory Disorders to Enhance Therapy via Real-Time Lung Sound Imaging in Telemedicine

This work presents a configurable Internet of Things architecture for acoustical sensing and analysis for frequent remote respiratory assessments. The proposed system creates a foundation for enabling real-time therapy and patient feedback adjustment in a telemedicine setting. By allowing continuous remote respiratory monitoring, the system has the potential to give clinicians access to assessments from which they could make decisions about modifying therapy in real-time and communicate changes directly to patients. The system comprises a wearable wireless microphone array interfaced with a programmable microcontroller with embedded signal conditioning. Experiments on the phantom model were conducted to demonstrate the feasibility of reconstructing acoustic lung images for detecting obstructions in the airway and provided controlled validation of noise resilience and imaging capabilities. An optimized denoising technique and design innovations provided 7 dB more SNR and 7% more imaging accuracy for the proposed system, benchmarked against digital stethoscopes. While further clinical studies are warranted, initial results suggest potential benefits over single-point digital stethoscopes for internet-enabled remote lung monitoring needing noise immunity and regional specificity. The flexible architecture aims to bridge critical technical gaps in frequent and connected respiratory function at home or in busy clinical settings challenged by ambient noise interference.

Prediction of recurrence-free survival in lung adenocarcinoma based on self-supervised pre-training and multi-task learning

Computed tomography (CT) imaging is a vital tool for the diagnosis and assessment of lung adenocarcinoma, and using CT images to predict the recurrence-free survival (RFS) of lung adenocarcinoma patients post-surgery is of paramount importance in tailoring postoperative treatment plans. Addressing the challenging task of accurate RFS prediction using CT images, this paper introduces an innovative approach based on self-supervised pre-training and multi-task learning. We employed a self-supervised learning strategy known as "image transformation to image restoration" to pretrain a 3D-UNet network on publicly available lung CT datasets to extract generic visual features from lung images. Subsequently, we enhanced the network's feature extraction capability through multi-task learning involving segmentation and classification tasks, guiding the network to extract image features relevant to RFS. Additionally, we designed a multi-scale feature aggregation module to comprehensively amalgamate multi-scale image features, and ultimately predicted the RFS risk score for lung adenocarcinoma with the aid of a feed-forward neural network. The predictive performance of the proposed method was assessed by ten-fold cross-validation. The results showed that the consistency index (C-index) of the proposed method for predicting RFS and the area under curve (AUC) for predicting whether recurrence occurs within three years reached 0.691 ± 0.076 and 0.707 ± 0.082, respectively, and the predictive performance was superior to that of existing methods. This study confirms that the proposed method has the potential of RFS prediction in lung adenocarcinoma patients, which is expected to provide a reliable basis for the development of individualized treatment plans.

Lung Cancer Classification using Optimized Attention-based Convolutional Neural Network with DenseNet-201 Transfer Learning Model on CT image

In this paper, the Lung Cancer Classification using Convolutional Neural Network with DenseNet-201 Transfer Learning model optimized through Namib Beetle Optimization Algorithm on CT image (AtCNN-DenseNet-201 TL-NBOA-CT) is proposed. The input data are gathered from the CT Lung image. In pre-processing section, it removes the noise and enhances input images by Modified Sage-Husa Kalman Filtering (MSHKF).The pre-processed image is given into feature extraction phase. Then, six statistical features including mean, variance, entropy, energy, Average Amplitude, kurtosis are extracted based on Improved Empirical Wavelet Transforms (IEWT). Then, the extracted features are given to the Attention-based Convolutional Neural Network with DenseNet-201Transfer Learning (AtCNN-DenseNet-201 TL) to classify the Cancer and Non-Cancer of the CT image, where batch normalization layer of At CNN eliminated and added by DenseNet-201 layer. Namib Beetle Optimization Algorithm (NBOA) proposed in this work to enhance the AtCNN-DenseNet-201 classifier, which precisely classifies the lung cancer. The proposed AtCNN-DenseNet-201 TL-NBOA-CT method is implemented and the effectiveness is assessed with some performance measures. The proposed AtCNN-DenseNet-201 TL-NBOA-CT method attains 18.30 %, 21.37 % and 23.07 % greater precision, 24.84 %, 16.32 % and 31.36 % greater accuracy and 14.32 %, 21.97 % and 23.38 % greater F1-Score compared with existing techniques like detection and categorization of lung cancer CT pictures utilizing improved deep belief network along Gabor filters (CLC-CT-EDBN), presented categorization of lung cancer CT pictures utilizing a three dimensional deep CNN with multi-layer filter (CLC-CT-3D-DCNN), and novel hybrid deep learning technique for early identification of lung cancer utilizing neural networks (CLC-CT-3D-CNN) respectively.

Exploring the link between a novel approach for computer aided lung sound analysis and imaging biomarkers: a cross-sectional study

BackgroundComputer Aided Lung Sound Analysis (CALSA) aims to overcome limitations associated with standard lung auscultation by removing the subjective component and allowing quantification of sound characteristics. In this proof-of-concept study, a novel automated approach was evaluated in real patient data by comparing lung sound characteristics to structural and functional imaging biomarkers.MethodsPatients with cystic fibrosis (CF) aged > 5y were recruited in a prospective cross-sectional study. CT scans were analyzed by the CF-CT scoring method and Functional Respiratory Imaging (FRI). A digital stethoscope was used to record lung sounds at six chest locations. Following sound characteristics were determined: expiration-to-inspiration (E/I) signal power ratios within different frequency ranges, number of crackles per respiratory phase and wheeze parameters. Linear mixed-effects models were computed to relate CALSA parameters to imaging biomarkers on a lobar level.Results222 recordings from 25 CF patients were included. Significant associations were found between E/I ratios and structural abnormalities, of which the ratio between 200 and 400 Hz appeared to be most clinically relevant due to its relation with bronchiectasis, mucus plugging, bronchial wall thickening and air trapping on CT. The number of crackles was also associated with multiple structural abnormalities as well as regional airway resistance determined by FRI. Wheeze parameters were not considered in the statistical analysis, since wheezing was detected in only one recording.ConclusionsThe present study is the first to investigate associations between auscultatory findings and imaging biomarkers, which are considered the gold standard to evaluate the respiratory system. Despite the exploratory nature of this study, the results showed various meaningful associations that highlight the potential value of automated CALSA as a novel non-invasive outcome measure in future research and clinical practice.

B cells in the pneumococcus-infected lung are heterogeneous and require CD4+ T cell help including CD40L to become resident memory B cells.

Recovery from respiratory pneumococcal infections generates lung-localized protection against heterotypic bacteria, mediated by resident memory lymphocytes. Optimal protection in mice requires re-exposure to pneumococcus within days of initial infection. Serial surface marker phenotyping of B cell populations in a model of pneumococcal heterotypic immunity revealed that bacterial re-exposure stimulates the immediate accumulation of dynamic and heterogeneous populations of B cells in the lung, and is essential for the establishment of lung resident memory B (BRM) cells. The B cells in the early wave were activated, proliferating locally, and associated with both CD4+ T cells and CXCL13. Antagonist- and antibody-mediated interventions were implemented during this early timeframe to demonstrate that lymphocyte recirculation, CD4+ cells, and CD40 ligand (CD40L) signaling were all needed for lung BRM cell establishment, whereas CXCL13 signaling was not. While most prominent as aggregates in the loose connective tissue of bronchovascular bundles, morphometry and live lung imaging analyses showed that lung BRM cells were equally numerous as single cells dispersed throughout the alveolar septae. We propose that CD40L signaling from antigen-stimulated CD4+ T cells in the infected lung is critical to establishment of local BRM cells, which subsequently protect the airways and parenchyma against future potential infections.