Diagnosis Of Lung Disease Research Articles

Application of Artificial Intelligence in Radiological Image Analysis for Pulmonary Disease Diagnosis: A Review of Current Methods and Challenges

Introduction and purposeArtificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), is revolutionizing radiology by improving diagnostic accuracy and efficiency. This paper examines AI applications, especially convolutional neural networks (CNNs), in diagnosing pulmonary diseases, such as pneumonia, tuberculosis, and lung cancer. The goal is to explore the impact of these technologies and assess challenges in their integration into clinical practice. Material and methodsThis review is based on articles from the PubMed database, published between 2015 and 2024, using keywords such as artificial intelligence in radiology, AI in medicine, AI in chest X-ray, and AI in chest-CT. ResultsAI, driven by ML and DL, has significantly enhanced medical imaging analysis, automating tasks that require expert interpretation. CNNs excel in processing raw image data and identifying hierarchical features, surpassing traditional methods in diagnosing lung diseases from radiographs and CT scans. AI systems demonstrate exceptional accuracy in detecting pneumonia, tuberculosis, and lung cancer, providing rapid, consistent results, particularly valuable in resource-limited settings. However, challenges persist, including the need for diverse training datasets, model interpretability, and integration into existing workflows. ConclusionsAI, especially CNN-based DL models, is reshaping radiology by advancing diagnostic capabilities. While it often outperforms traditional methods, AI is best used to complement human expertise. Overcoming challenges in data quality, system integration, and training is essential for broader clinical adoption. Continued research will enhance AI’s reliability and utility, ultimately improving patient outcomes.

Automated system for diagnosing pulmonary fibrosis using crackle analysis in recorded lung sounds based on iterative envelope mean fractal dimension filter.

Patients with pulmonary fibrosis (PF) often experience long waits before getting a correct diagnosis, and this delay in reaching specialized care is associated with increased mortality, regardless of the severity of the disease. Early diagnosis and timely treatment of PF can potentially extend life expectancy and maintain a better quality of life. Crackles present in the recorded lung sounds may be crucial for the early diagnosis of PF. This paper describes an automated system for differentiating lung sounds related to PF from other pathological lung conditions using the average number of crackles per breath cycle (NOC/BC). The system is divided into four main parts: (1) pre-processing, (2) separation of crackles from normal breath sounds using the iterative envelope mean fractal dimension (IEM-FD) filter, (3) crackle verification and counting, and (4) estimating NOC/BC. The system was tested on a dataset consisting of 48 (24 fibrotic and 24 non-fibrotic) subjects and the results were compared with an assessment by two expert respiratory physicians. The set of HRCT images, reviewed by two expert radiologists for the presence or absence of pulmonary fibrosis, was used as the ground truth for evaluating the PF and non-PF classification performance of the system. The overall performance of the automatic classifier based on receiver operating curve-derived cut-off value for average NOC/BC of 18.65 (AUC=0.845, 95 % CI 0.739-0.952, p<0.001; sensitivity=91.7 %; specificity=59.3 %) compares favorably with the averaged performance of the physicians (sensitivity=83.3 %; specificity=56.25 %). Although radiological assessment should remain the gold standard for diagnosis of fibrotic interstitial lung disease, the automatic classification system has strong potential for diagnostic support, especially in assisting general practitioners in the auscultatory assessment of lung sounds to prompt further diagnostic work up of patients with suspect of interstitial lung disease.

Korean Guidelines for Diagnosis and Management of Interstitial Lung Diseases: Connective Tissue Disease Associated Interstitial Lung Disease.

Connective tissue disease (CTD) comprising a various range of autoimmune disorders is often accompanied by lung involvement, which can lead to life-threatening complications. The main types of CTDs that can present as interstitial lung disease (ILD) include rheumatoid arthritis, systemic sclerosis, Sjögren's syndrome, mixed connective tissue disease, idiopathic inflammatory myopathies, and systemic lupus erythematosus. CTD-ILD poses a significant challenge in clinical diagnosis and management due to its heterogeneous nature and variable prognosis. Early diagnosis by clinical, serological, and radiographic assessments is crucial to differentiate CTD-ILD from idiopathic forms and to adopt appropriate therapeutic strategies. Therefore, we have reviewed the numerous clinical manifestations and diagnostic approaches for each type of CTD-ILD, considering the diversity and complexity of CTD-ILD. The significance of a multidisciplinary approach in optimizing the management of CTD-ILD has been underscored by recent therapeutic advancements, which include the use of immunosuppressive agents, antifibrotic therapies, and newer biological agents targeting specific pathways implicated in the pathogenesis. Therapeutic strategies should be tailored to each condition, considering the type of CTD, the extent of lung involvement, and the presence of extrapulmonary manifestations. Furthermore, we aimed to provide clinical guidance including therapeutic recommendations for the effective management of CTD-ILD, based on PICO analysis.

Infection Rate and Risk Factors of SARS-CoV-2 Infection in Retail Workers at the Onset of the COVID-19 Pandemic, Quebec, Canada.

Background/Objectives: During the pandemic, client-facing workers were perceived to be at greater risk of SARS-CoV-2 infection. This study investigated the risk factors for SARS-CoV-2 infection among a cohort of 304 retail workers in the Quebec City metropolitan area. Methods: After providing consent, participants were interviewed to gather information on demographic, socioeconomic, behavioural, and occupational variables. They were subsequently followed for up to five visits, scheduled every 12 ± 4 weeks. The study covered critical periods before and during the emergence of the Omicron variants and included retrospective reporting of COVID-19 symptoms and virus detection tests to capture the pandemic's early stages. Results: During the observation period, 173 (57%) participants experienced a first episode of COVID-19. Serological evidence of recent infection was detected in 160 participants (53%), while 117 (38%) reported a positive virus detection test. In adjusted analyses, risk factors for infection included younger age, a diagnosis of lung disease, longer weekly working hours, more frequent social gatherings, and having received fewer than three doses of vaccine. Notably, the increased risk associated with younger age and longer working hours was observed only after the relaxation of public health measures in the spring of 2022. Conclusions: These data suggest that during the early years of the pandemic when strict public health measures were in place, retail work was not a significant risk factor for SARS-CoV-2 infection in Quebec City metropolitan area. These findings highlight the complex dynamics of COVID-19 transmission and the effectiveness of workplace protective measures.

Content Validation of the QOL-B-RD and PROMIS-F SF-7a to Measure Respiratory and Fatigue Symptoms of MAC Lung Disease.

The Quality of Life-Bronchiectasis (QOL-B) questionnaire and Patient Reported Outcome Measurement Information System Short Form v1.0-Fatigue7a (PROMIS-F SF-7a) have the potential to measure respiratory and fatigue symptoms, respectively, in patients with Mycobacterium avium complex (MAC) lung disease but have not yet been evaluated for content validity in this population. Semi-structured qualitative interviews were conducted in United States patients with a current MAC lung disease diagnosis. Concept elicitation (CE) interviews were conducted (n=25 participants) to identify key respiratory and fatigue symptoms expressed as important and relevant to patients with MAC lung disease and to evaluate the appropriateness of the QOL-B and PROMIS-F SF-7a to measure these symptoms. Cognitive interviews (CIs) were subsequently conducted (n=20 participants) to evaluate the relevance, comprehensibility, and appropriateness of the QOL-B respiratory domain (QOL-B-RD) and PROMIS-F SF-7a. All interviews were recorded, transcribed, and coded for qualitative content analysis. The most important or relevant respiratory symptom concepts to CE interview participants were "cough," "shortness of breath during activity," and "mucus/phlegm." The most important or relevant fatigue symptom concepts were "tiredness," "lack of energy," and "tire easily/low stamina." These symptoms are covered by existing items in the QOL-B-RD and PROMIS-F SF-7a. Cognitive interview participants' feedback confirmed the item content, response options, concept attributes, and recall period for each instrument were effective, relevant, and meaningful to most patients with MAC lung disease. Based on Wave 1 findings, the QOL-B instructions were revised for the Wave 2 interviews, where the text referencing "bronchiectasis" was replaced with "your lung condition." Participant feedback in Wave 2 confirmed the revised instruction wording was easily understood and appropriate. The study results support the content validity of the QOL-B-RD and PROMIS-F SF-7a, which were shown to be relevant and appropriate to evaluate respiratory and fatigue symptoms, respectively, in patients with MAC lung disease.

Diagnosing Respiratory Variability: Convolutional Neural Networks for Chest X-ray Classification Across Diverse Pulmonary Conditions.

The global burden of lung diseases is a pressing issue, particularly in developing nations with limited healthcare access. Accurate diagnosis of lung conditions is crucial for effective treatment, but diagnosing lung ailments using medical imaging techniques like chest radiograph images and CT scans is challenging due to the complex anatomical intricacies of the lungs. Deep learning methods, particularly convolutional neural networks (CNN), offer promising solutions for automated disease classification using imaging data. This research has the potential to significantly improve healthcare access in developing countries with limited medical resources, providing hope for better diagnosis and treatment of lung diseases. The study employed a diverse range of CNN models for training, including a baseline model and transfer learning models such as VGG16, VGG19, InceptionV3, and ResNet50. The models were trained using image datasets sourced from the NIH and COVID-19 repositories containing 8000 chest radiograph images depicting four lung conditions (lung opacity, COVID-19, pneumonia, and pneumothorax) and 2000 healthy chest radiograph images, with a ten-fold cross-validation approach. The VGG19-based model outperformed the baseline model in diagnosing lung diseases with an average accuracy of 0.995 and 0.996 on validation and external test datasets. The proposed model also outperformed published lung-disease prediction models; these findings underscore the superior performance of the VGG19 model compared to other architectures in accurately classifying and detecting lung diseases from chest radiograph images. This study highlights AI's potential, especially CNNs like VGG19, in improving diagnostic accuracy for lung disorders, promising better healthcare outcomes. The predictive model is available on GitHub at https://github.com/PGlab-NIPER/Lung_disease_classification .

Diagnosis of fibrotic interstitial lung diseases based on the combination of label-free quantitative multiphoton fiber histology and machine learning.

Interstitial lung disease (ILD), characterized by inflammation and fibrosis, often suffers from low diagnostic accuracy and consistency. Traditional H&E staining primarily reveals cellular inflammation with limited detail on fibrosis. To address these issues, we introduce a pioneering label-free quantitative multiphoton fiber histology (MPFH) technique that delineates the intricate characteristics of collagen and elastin fibers for ILDs diagnosis. We acquired co-located multiphoton and H&E-stained images from a single tissue slice. Multiphoton imaging was performed on the deparaffinized section to obtain fibrotic tissue information, followed by H&E staining to capture cellular information. This approach was tested in a blinded diagnostic trial among 7 pathologists involving 14 relatively normal lung patients and 31 ILD patients (11 idiopathic pulmonary fibrosis (IPF) / usual interstitial pneumonia (UIP), 14 nonspecific interstitial pneumonia (NSIP), and 6 pleuroparenchymal fibroelastosis (PPFE)). A customized algorithm extracted quantitative fiber indicators from multiphoton images. These indicators, combined with clinical and radiological features, were used to develop an automatic multi-class ILDs classifier. Using MPFH, we can acquire high-quality, co-localized images of collagen fibers, elastin fibers, and cells. We found that the type, distribution, and degree of fibrotic proliferation can effectively distinguish between different subtypes. The blind study showed MPFH enhanced diagnostic consistency (kappa values from 0.56 to 0.72) and accuracy (from 73.0% to 82.5%, p=0.0090). The combination of quantitative fiber indicators effectively distinguished between different tissues, with areas under the receiver operating characteristic curves exceeding 0.92. The automatic classifier achieved 93.8% accuracy, closely paralleling the 92.2% accuracy of expert pathologists. The outcomes of our research underscore the transformative potential of MPFH in the field of f-ILD diagnostics. By integrating quantitative analysis of fiber characteristics with advanced machine learning algorithms, MPFH facilitates the automatic and accurate identification of various fibrotic disease subtypes, showcasing a significant leap forward in precision diagnostics.

Unlocking the clinical potential of paired inspiratory and expiratory CT scans in the differential diagnosis of cystic lung diseases: A systematic review.

Currently, high-resolution computed tomography (HRCT) is the imaging of choice for the differential diagnosis of various cystic lung lesions, including true cystic lung diseases (CLD) and lesions that may mimic them. However, the traditionally used inspiratory scan still presents a significant spectrum of overlapping radiological features. Recent studies have demonstrated variation in lesion size between inspiratory and expiratory phases, probably due to cyst-airway communication. In this study, we aimed to conduct a systematic review of paired inspiratory and expiratory HRCT in the assessment of cystic lesions as an additional tool to narrow the differential diagnosis. A systematic search was performed in PubMed, Scopus, EMBASE, BVS, and Cochrane through August 2023. Full-text articles that performed paired inspiratory and expiratory CT scans in adult patients with cystic lung lesions were included, with the outcome measured as the reduction in lesion size according to the respiratory phase. Diagnoses were confirmed through histopathological or radiological features. Out of the 96 records, three studies met the criteria for inclusion and were analyzed, comprising a total of 149 participants and 513 cystic lesions. Pulmonary Langerhans Cell Histiocytosis (PLCH), Lymphangioleiomyomatosis (LAM) honeycombing and cystic bronchiectasis became considerably smaller during expiratory CT scans, while the size of emphysema tended to remain constant during respiratory cycles. This study has suggested that paired inspiratory and expiratory CT scans can be valuable for helping differentiate between emphysema and other diseases with a cystic pattern due to their ability to reveal dynamic properties of the lesions. However, the average reduction in cyst size as a single parameter is not sufficient for further refining diagnostics. Studies exploring advanced metrics to assess the reduction in lesion diameter emerge as potential opportunities to investigate the cyst-airway communication hypothesis and further enhance the diagnostic accuracy of paired methods.

Accurate Lung Nodule Segmentation With Detailed Representation Transfer and Soft Mask Supervision.

Accurate lung lesion segmentation from computed tomography (CT) images is crucial to the analysis and diagnosis of lung diseases, such as COVID-19 and lung cancer. However, the smallness and variety of lung nodules and the lack of high-quality labeling make the accurate lung nodule segmentation difficult. To address these issues, we first introduce a novel segmentation mask named "soft mask", which has richer and more accurate edge details description and better visualization, and develop a universal automatic soft mask annotation pipeline to deal with different datasets correspondingly. Then, a novel network with detailed representation transfer and soft mask supervision (DSNet) is proposed to process the input low-resolution images of lung nodules into high-quality segmentation results. Our DSNet contains a special detailed representation transfer module (DRTM) for reconstructing the detailed representation to alleviate the small size of lung nodules images and an adversarial training framework with soft mask for further improving the accuracy of segmentation. Extensive experiments validate that our DSNet outperforms other state-of-the-art methods for accurate lung nodule segmentation, and has strong generalization ability in other accurate medical segmentation tasks with competitive results. Besides, we provide a new challenging lung nodules segmentation dataset for further studies (https://drive.google.com/file/d/15NNkvDTb_0Ku0IoPsNMHezJR TH1Oi1wm/view?usp=sharing).

AIE nanoparticle with enhanced fluorescence for ultrasensitive lateral flow immunoassays and point-of-care diagnosis of interstitial lung disease.

Krebs von den Lungen-6 (KL-6) has been recognized as an effective serum biomarker for interstitial lung disease (ILD). The KL-6 accurate detection is of great significance for evaluating the severity of ILD and the prognosis of patients. In this study, a bright aggregation-induced emission luminogen (AIEgen) N, N'-((1,2-diphenylethene-1,2-diyl)bis(4,1-phenylene))bis(N-phenylnaphthalen-1-amine) (TPETN) with a high quantum yield of 87.57% was designed and synthesized, which was subsequently encapsulated into polystyrene nanoparticles (PSNPs) for construction of ultrahigh fluorescent nanoparticle (TPNPs). The obtained TPNPs was found to be 128 times and 16 times higher sensitivity than traditional gold nanoparticles (AuNPs) and tetramethyl 4',4''',4''''',4'''''''-(ethene-1,1,2,2-tetrayl) tetrakis([1,1'-biphenyl]-4-carboxylate) (TCBPE) embedded nanoparticles (TCNPs), respectively. Then, TPNPs were employed as signal output to construct a lateral flow immunoassay platform (TPNP-LFIA) for KL-6 detection. TPNP-LFIA achieved a limit of detection (LOD) of 0.0534ng/mL, which was 77.15 times and 7.69 times lower than those of AuNP- and TCNP- based LFIA, respectively. The dynamic linearity of TPNP-LFIA for detecting KL-6 ranged from 0.15 to 333.33ng/mL. The recovery rates of TPNP-LFIA in serum samples varied from 99.96% to 108.13%, with coefficients of variation ≤6.24%. Hence, TPNP-LFIA has promising potential as a rapid and quantitative method for detecting KL-6.

Bronchoalveolar Lavage and Its Interpretation

Bronchoalveolar lavage (BAL) is performed via bronchoscopy, typically under conscious sedation. It plays a crucial role in the differential diagnosis of lung disease, because it provides valuable information about the lung parenchyma, including cellular composition, the presence of microorganisms, and cytological features. Furthermore, BAL has therapeutic applications and is widely used in medical research. However, careful patient selection is required, because the diagnostic yield may vary and the procedure has inherent risks.

Evaluation of the Effects of Sedation and Anesthesia on Total Lung Volume and Attenuation in Rabbit Lung CT Exams.

Respiratory disease is common in rabbits, but subclinical conditions can be challenging to diagnose and may cause respiratory problems during anesthesia. CT is the preferred method for diagnosing lung diseases, but anesthesia can alter lung volume and cause lung lobe collapse. In this study, seventeen healthy 5-month-old male New Zealand white rabbits underwent thoracic CT scans under different conditions. Rabbits were sedated with midazolam and butorphanol and scanned in a sphinx position; they were then anesthetized with dexmedetomidine and ketamine and scanned again in sternal recumbency during spontaneous breathing. Lastly, apnea was induced using intermittent positive pressure ventilation (IPPV) for a final scan. Lung volume and density were measured using the 3D Slicer version 5.6.2 software, with thresholds set between -1050 and -100 Hounsfield Units (HU). Sedated animals had significantly higher total lung volume (69.39 ± 10.04 cm3) than anesthetized (47.10 ± 9.28 cm3) and anesthetized apnea rabbits (48.60 ± 7.40 cm3). Mean lung attenuation during sedation was -611.26 HU (right) and -636.00 HU (left). After anesthesia induction, values increased to -552.75 HU (right) and -561.90 HU (left). Following apnea induction, attenuation slightly decreased to -569.40 HU (right) and -579.94 HU (left). The results indicate that sedation may be preferable for rabbit lung CT to minimize anesthesia-related changes.

Lung image quality assessment and diagnosis using generative autoencoders in unsupervised ensemble learning

The lung is a critical organ for blood gas exchange. Early lung disease detection is often hindered by subtle symptoms. The diagnosis typically requires expert analysis of lung image scans, where both conventional methods and advanced machine learning (ML) and deep learning (DL) techniques are employed for scan segmentation and disease detection. However, it is a challenge to develop reliable computational models, due to the scarcity of high-quality data. With a major emphasis on lung disease classification and segmentation performance, this work presents a novel data quality assessment technique specifically designed for lung image datasets. The proposed pipeline combines ensemble learning, unsupervised learning, and generative autoencoders with attention mechanisms (GAME). By including attentional mechanisms in the generative autoencoders, we improve the tool’s ability to locate and prioritise areas of interest in lung images and extract the right features, which increases the accuracy of our algorithms. The pipeline automates quality checks and reduces the need for high-quality data, while reducing human oversight. Because it’s crucial to validate the robustness of the algorithms in our tool, we tested it using lung scans from the NIH-ChestXray and CheXpert datasets, and obtained IOU scores of 0.88 and 0.86, F1 scores of 0.95 and 0.95, and accuracy scores of 0.96 and 0.95, respectively, which shows they can be used as a classification tool as well as a segmentation tool. Given the challenging conditions in which the early diagnosis of lung disease is made, this is a significant step forward in the development of self-sustaining and accurate disease detection systems. The proposed model is made available to the public and the same is accessible via https://github.com/harshivchandra/LungDataQualityAssessment.

Deep Learning Approaches for Chest Radiograph Interpretation: A Systematic Review

Lung diseases are a major global health concern, with nearly 4 million deaths annually, according to the World Health Organization (WHO). Chest X-rays (CXR) are widely used as a cost-effective and efficient diagnostic tool by radiologists to detect conditions such as pneumonia, tuberculosis, COVID-19, and lung cancer. This review paper provides an overview of the current research on diagnosing lung diseases using CXR images and Artificial Intelligence (AI), without focusing on any specific disease. It examines different approaches employed by researchers to leverage CXR, an accessible diagnostic medium, for early lung disease detection. This review shortlisted 11 research papers addressing this problem through AI, exploring the datasets used and their sources. Results varied across studies: for lung cancer, Deep Convolutional Neural Network (DCNN) achieved 97.20% accuracy, while multiclass frameworks like ResNet152V2+Bi-GRU (gated reccurent unit) reached 79.78% and 93.38%, respectively. For COVID-19 detection, accuracy rates of 98% and 99.37% were achieved using EfficientNet and Parallel Convolutional Neural Network-Extreme Learning Machine (CNN-ELM). Additionally, studies on the CXR-14 dataset (14 classes) showed high accuracy, with MobileNet V2 reaching 94%. Other notable results include 73% accuracy with VDSNet, 98.05% with VGG19+CNN for three classes, and high accuracy in detecting pediatric pneumonia, lung opacity, pneumothorax, and tuberculosis.

A propósito de enfermedades restrictivas pulmonares, neumonía organizada criptogénica. Reporte de Caso y revisión de la literatura.

Cryptogenic organizing pneumonia is an interstitial pneumonia of the lung that has been related to cellular repair mechanisms after lung injury. This condition does not have an identifiable etiological cause, which is why it is considered an idiopathic interstitial condition. Mentioned below is the case of an 84-year-old female patient, hypertensive and dyslipidemic, who consulted for a 6-month history characterized by a dry cough and inspiratory pain predominantly in the left rib cage, associated with dyspnea on small exertions, without fever. Other causes, including pulmonary tuberculosis, HIV, and gastric and lung cancer, were ruled out. Imaging findings showing the presence of typical features for cryptogenic organizing pneumonia. Who was managed with anti-inflammatory and corticosteroid therapy with progressive clinical improvement. The presence of this condition, although rare, is relevant when it comes to establishing differential diagnoses of restrictive lung diseases with a benign course, in which early diagnosis and targeted treatment have shown high recovery rates.

Weakly supervised chest X-ray abnormality localization with non-linear modulation and foreground control

Chest X-ray is widely used to diagnose lung diseases. Due to the demand for accelerating analysis and interpretation to reduce the workload of radiologists, there has been a growing interest in building automated systems of chest X-ray abnormality localization. However, fully supervised methods usually require well-trained radiologists to annotate bounding boxes manually, which is labor-intensive and time-consuming. As a result, weakly supervised chest X-ray abnormality localization is gaining increasing attention because it only requires image-level annotations. Existing weakly supervised object localization (WSOL) techniques, which typically utilize class activation maps, often result in incomplete coverage and fragmentation of the objects and rely on class-specific classification accuracy. In this study, we propose a novel WSOL framework for chest X-ray abnormality localization that uses VMamba as the backbone and integrates three practical components to improve localization accuracy. First, we propose a non-linear modulation module to refine Foreground Prediction Maps (FPM) by expanding the foreground activation region and enhancing its continuity. Second, we design an FPM fusion module to strengthen the foreground and suppress the background, thereby improving their separability in chest X-ray images. Third, we craft a novel foreground control loss that regulates the feature maps to refine the background and foreground activation for better foreground identification. The proposed method is evaluated on two commonly used chest X-ray datasets, the NIH chest X-ray dataset and the RSNA dataset, and demonstrates superior performance over six state-of-the-art WSOL methods. In addition, the robustness and applicability of the proposed method are evaluated using three additional datasets with varying modalities and image quality.

ILDIM-MFAM: interstitial lung disease identification model with multi-modal fusion attention mechanism.

This study aims to address the potential and challenges of multimodal medical information in the diagnosis of interstitial lung disease (ILD) by developing an ILD identification model (ILDIM) based on the multimodal fusion attention mechanism (MFAM) to improve the accuracy and reliability of ILD. Large-scale multimodal medical information data, including chest CT image slices, physiological indicator time series data, and patient history text information were collected. These data are professionally cleaned and normalized to ensure data quality and consistency. Convolutional Neural Network (CNN) is used to extract CT image features, Bidirectional Long Short-Term Memory Network (Bi-LSTM) model is used to learn temporal physiological metrics data under long-term dependency, and Self-Attention Mechanism is used to encode textual semantic information in patient's self-reporting and medical prescriptions. In addition, the multimodal perception mechanism uses a Transformer-based model to improve the diagnostic performance of ILD by learning the importance weights of each modality's data to optimally fuse the different modalities. Finally, the ablation test and comparison results show that the model performs well in terms of comprehensive performance. By combining multimodal data sources, the model not only improved the Precision, Recall and F1 score, but also significantly increased the AUC value. This suggests that the combined use of different modal information can provide a more comprehensive assessment of a patient's health status, thereby improving the diagnostic comprehensiveness and accuracy of ILD. This study also considered the computational complexity of the model, and the results show that ILDIM-MFAM has a relatively low number of model parameters and computational complexity, which is very favorable for practical deployment and operational efficiency.

The value of lung ultrasound in the differential diagnosis of common lung diseases in newborns.

To investigate the value of lung ultrasound in the differential diagnosis of common neonatal lung diseases. A total of 160 newborns with suspected lung diseases admitted to the Department of Neonatology of Linping Branch of the Second Affiliated Hospital of Zhejiang University from January 2020 to June 2023, were selected for examination. Perform lung ultrasound within 24 hours of admission for above newborns, using the final clinical diagnosis as standard. Calculate the accuracy, sensitivity, and specificity of lung ultrasound technology in the diagnosing neonatal lung diseases, and assess its value in the differential diagnosis of common neonatal lung diseases. A total of 160 newborns suspected of having lung disease were finally diagnosed with lung disease in 142 cases. The accuracy of lung ultrasound in differentiating neonatal pneumonia, respiratory distress syndrome of the newborn, meconium aspiration syndrome, transient tachypnea of the newborn, pneumothorax, atelectasis, and pulmonary hemorrhage was 96.8%, 98.1%, 98.8%, 100%, 100%, 100%, and 100%, respectively. The detection rate of lung ultrasound examination for lung disease in newborns was 85.00%, with a sensitivity of 95.77%, specificity of 77.77%, positive predictive value of 97.14% and negative predictive value of 70.0%. The consistency test kappa value between lung ultrasound findings and the final clinical diagnosis of neonatal lung diseases is 0.846. Lung ultrasound holds significant value in the differential diagnosis of common lung diseases in newborns.

Diagnosis and Management of Drug-Induced Interstitial Lung Disease in the context of Anti-Cancer Therapy: a Multidisciplinary Viewpoint by Portuguese Experts.

Drug-induced interstitial lung disease (DI-ILD) is a significant complication in patients undergoing treatment with certain anti-cancer therapies, with incidence rates rising, particularly with newer drugs such as trastuzumab-deruxtecan, which may impact their safe and effective use. Although the exact pathophysiological mechanisms remain unknown, and different drugs may induce lung damage through different pathways, the most recognized mechanisms are cytotoxic- and immune-mediated effects. Multidisciplinary teams play a crucial role in the diagnosis, management, and prevention of DI-ILD. Given the wide variability in the onset of DI-ILD, which may occur within the first few days of treatment or months after, patient education and clinician training are essential for early detection and improved outcomes. Moreover, the diagnostic confirmation requires the exclusion of alternative causes through clinical, imaging and bronchoscopy evaluation. Treatment strategies largely depend on the grade of severity of the clinical manifestations of DI-ILD, ranging from interruption or discontinuation of the offending drug to corticosteroid therapy and hospitalization for appropriate monitoring. Nonetheless, further research is needed to better understand the impact of emerging anti-cancer drugs on DI-ILD and to establish standardized management protocols.

Analysis of Lung Disease Prediction using Machine Learning Algorithms

Lung diseases are a notable in global health concern, requiring early diagnosis for better recovery and survival rates. Deep learning strategies, especially CNNs, have shown great promise in self learning lung disease diagnosis from medical images like chest X-rays. Ensemble learning methods using pretrained networks such as VGG16, InceptionV3, and MobileNetV2 have achieved up to 94% accuracy in identifying conditions like COVID-19, pneumonia, and lung opacity. Lightweight CNN models also performed well, with accuracy up to 89.89%. Traditional machine learning algorithms, including Random Forest and Logistic Regression, yielded accuracy rates between 88% and 90%. A hybrid deep learning approach, combining CNN based feature extraction with classifiers like AdaBoost, SVM, and Random Forest, improved classification accuracy by 3.1% and reduced computational complexity by 16.91%. This hybrid method highlights the main feature for integrating deep learning with traditional classifiers to enhance lung disease detection efficiency