Beyond Visual Interpretation: Quantitative Analysis and Artificial Intelligence in Interstitial Lung Disease Diagnosis "Expanding Horizons in Radiology"

Fibrosis: cross-organ biology and pathways to development of innovative drugs

Fibrosis is a pathophysiological mechanism involved in chronic and progressive diseases that results in excessive tissue scarring. Diseases associated with fibrosis include metabolic dysfunction-associated steatohepatitis (MASH), inflammatory bowel diseases (IBDs), chronic kidney disease (CKD), idiopathic pulmonary fibrosis (IPF) and systemic sclerosis (SSc), which are collectively responsible for substantial morbidity and mortality. Although a few drugs with direct antifibrotic activity are approved for pulmonary fibrosis and considerable progress has been made in the understanding of mechanisms of fibrosis, translation of this knowledge into effective therapies continues to be limited and challenging. With the aim of assisting developers of novel antifibrotic drugs, this Review integrates viewpoints of biologists and physician-scientists on core pathways involved in fibrosis across organs, as well as on specific characteristics and approaches to assess therapeutic interventions for fibrotic diseases of the lung, gut, kidney, skin and liver. This discussion is used as a basis to propose strategies to improve the translation of potential antifibrotic therapies.

Integrating Radiomics Signature into Clinical Pathway for Patients with Progressive Pulmonary Fibrosis

Interstitial lung diseases (ILDs) are a heterogeneous group of pulmonary disorders characterised by variable degrees of inflammation, interstitial thickening, and fibrosis leading to distortion of the pulmonary architecture and gas exchange impairment. There are approximately 200 different entities in this category. ILDs are commonly classified based on several criteria, including causes, clinical features, and radiological patterns. Chest HRCT is the gold standard for the recognition of lung alteration patterns underlying interstitial lung diseases (ILDs), diagnosing specific patterns, and evaluating radiologic progression. Methods based on artificial intelligence (AI) may be used in computational medicine, especially in image-based specialties such as radiology. The evolving field of radiomics offers a unique and non-invasive approach to extracting quantitative information from medical images, particularly high-resolution computed tomography (HRCT) scans. This comprehensive review explores the burgeoning role of radiomics in unravelling the intricacies of interstitial lung disease. It focuses on its potential applications in diagnosis, prognostication, and treatment response evaluation.

Detection of Intracranial Hemorrhage from Computed Tomography Images: Diagnostic Role and Efficacy of ChatGPT-4o

Background/Objectives: The role of artificial intelligence (AI) in radiological image analysis is rapidly evolving. This study evaluates the diagnostic performance of Chat Generative Pre-trained Transformer Omni (GPT-4 Omni) in detecting intracranial hemorrhages (ICHs) in non-contrast computed tomography (NCCT) images, along with its ability to classify hemorrhage type, stage, anatomical location, and associated findings. Methods: A retrospective study was conducted using 240 cases, comprising 120 ICH cases and 120 controls with normal findings. Five consecutive NCCT slices per case were selected by radiologists and analyzed by ChatGPT-4o using a standardized prompt with nine questions. Diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated by comparing the model's results with radiologists' assessments (the gold standard). After a two-week interval, the same dataset was re-evaluated to assess intra-observer reliability and consistency. Results: ChatGPT-4o achieved 100% accuracy in identifying imaging modality type. For ICH detection, the model demonstrated a diagnostic accuracy of 68.3%, sensitivity of 79.2%, specificity of 57.5%, PPV of 65.1%, and NPV of 73.4%. It correctly classified 34.0% of hemorrhage types and 7.3% of localizations. All ICH-positive cases were identified as acute phase (100%). In the second evaluation, diagnostic accuracy improved to 73.3%, with a sensitivity of 86.7% and a specificity of 60%. The Cohen's Kappa coefficient for intra-observer agreement in ICH detection indicated moderate agreement (κ = 0.469). Conclusions: ChatGPT-4o shows promise in identifying imaging modalities and ICH presence but demonstrates limitations in localization and hemorrhage type classification. These findings highlight its potential for improvement through targeted training for medical applications.

Potential strength and weakness of artificial intelligence integration in emergency radiology: a review of diagnostic utilizations and applications in patient care optimization

Artificial intelligence (AI) and its recent increasing healthcare integration has created both new opportunities and challenges in the practice of radiology and medical imaging. Recent advancements in AI technology have allowed for more workplace efficiency, higher diagnostic accuracy, and overall improvements in patient care. Limitations of AI such as data imbalances, the unclear nature of AI algorithms, and the challenges in detecting certain diseases make it difficult for its widespread adoption. This review article presents cases involving the use of AI models to diagnose intracranial hemorrhage, spinal fractures, and rib fractures, while discussing how certain factors like, type, location, size, presence of artifacts, calcification, and post-surgical changes, affect AI model performance and accuracy. While the use of artificial intelligence has the potential to improve the practice of emergency radiology, it is important to address its limitations to maximize its advantages while ensuring the safety of patients overall.

Pulmonary fibrosis: pathogenesis and therapeutic strategies

Pulmonary fibrosis (PF) is a chronic and progressive lung disease characterized by extensive alterations of cellular fate and function and excessive accumulation of extracellular matrix, leading to lung tissue scarring and impaired respiratory function. Although our understanding of its pathogenesis has increased, effective treatments remain scarce, and fibrotic progression is a major cause of mortality. Recent research has identified various etiological factors, including genetic predispositions, environmental exposures, and lifestyle factors, which contribute to the onset and progression of PF. Nonetheless, the precise mechanisms by which these factors interact to drive fibrosis are not yet fully elucidated. This review thoroughly examines the diverse etiological factors, cellular and molecular mechanisms, and key signaling pathways involved in PF, such as TGF-β, WNT/β-catenin, and PI3K/Akt/mTOR. It also discusses current therapeutic strategies, including antifibrotic agents like pirfenidone and nintedanib, and explores emerging treatments targeting fibrosis and cellular senescence. Emphasizing the need for omni-target approaches to overcome the limitations of current therapies, this review integrates recent findings to enhance our understanding of PF and contribute to the development of more effective prevention and management strategies, ultimately improving patient outcomes.

Optimizing double-layered convolutional neural networks for efficient lung cancer classification through hyperparameter optimization and advanced image pre-processing techniques

Lung cancer remains a leading cause of cancer-related mortality globally, with prognosis significantly dependent on early-stage detection. Traditional diagnostic methods, though effective, often face challenges regarding accuracy, early detection, and scalability, being invasive, time-consuming, and prone to ambiguous interpretations. This study proposes an advanced machine learning model designed to enhance lung cancer stage classification using CT scan images, aiming to overcome these limitations by offering a faster, non-invasive, and reliable diagnostic tool. Utilizing the IQ-OTHNCCD lung cancer dataset, comprising CT scans from various stages of lung cancer and healthy individuals, we performed extensive preprocessing including resizing, normalization, and Gaussian blurring. A Convolutional Neural Network (CNN) was then trained on this preprocessed data, and class imbalance was addressed using Synthetic Minority Over-sampling Technique (SMOTE). The model's performance was evaluated through metrics such as accuracy, precision, recall, F1-score, and ROC curve analysis. The results demonstrated a classification accuracy of 99.64%, with precision, recall, and F1-score values exceeding 98% across all categories. SMOTE significantly enhanced the model's ability to classify underrepresented classes, contributing to the robustness of the diagnostic tool. These findings underscore the potential of machine learning in transforming lung cancer diagnostics, providing high accuracy in stage classification, which could facilitate early detection and tailored treatment strategies, ultimately improving patient outcomes.

The Unveiled Triad: Clinical, Radiological and Pathological Insights into Hypersensitivity Pneumonitis

Hypersensitivity pneumonitis (HP) is a diffuse parenchymal lung disease (DLPD) characterized by complex interstitial lung damage with polymorphic and protean inflammatory aspects affecting lung tissue targets including small airways, the interstitium, alveolar compartments and vascular structures. HP shares clinical and often radiological features with other lung diseases in acute or chronic forms. In its natural temporal evolution, if specific therapy is not initiated promptly, HP leads to progressive fibrotic damage with reduced lung volumes and impaired gas exchange. The prevalence of HP varies considerably worldwide, influenced by factors like imprecise disease classification, diagnostic method limitations for obtaining a confident diagnosis, diagnostic limitations in the correct processing of high-resolution computed tomography (HRCT) radiological parameters, unreliable medical history, diverse geographical conditions, heterogeneous agricultural and industrial practices and occasionally ineffective individual protections regarding occupational exposures and host risk factors. The aim of this review is to present an accurate and detailed 360-degree analysis of HP considering HRCT patterns and the role of the broncho-alveolar lavage (BAL), without neglecting biopsy and anatomopathological aspects and future technological developments that could make the diagnosis of this disease less challenging.

Recent advances in mass spectrometry for the detection of doping

INTRODUCTION

The analysis of doping control samples is preferably performed by mass spectrometry, because obtained results meet the highest analytical standards and ensure an impressive degree of reliability. The advancement in mass spectrometry and all its associated technologies thus allow for continuous improvements in doping control analysis.

AREAS COVERED

Modern mass spectrometric systems have reached a status of increased sensitivity, robustness, and specificity within the last decade. The improved sensitivity in particular has, on the other hand, also led to the detection of drug residues that were attributable to scenarios where the prohibited substances were not administered consciously but rather by the unconscious ingestion of or exposure to contaminated products. These scenarios and their doubtless clarification represent a great challenge. Here, too, modern MS systems and their applications can provide good insights in the interpretation of dose-related metabolism of prohibited substances. In addition to the development of new instruments itself, software-assisted analysis of the sometimes highly complex data is playing an increasingly important role and facilitating the work of doping control laboratories.

EXPERT OPINION

The sensitive analysis and evaluation of a higher number of samples in a shorter time is made possible by the ongoing developments in mass spectrometry.

Advances in the identification and management of progressive pulmonary fibrosis: perspective from Chinese experts

Fibrosing interstitial lung diseases (FILDs) other than idiopathic pulmonary fibrosis (IPF) can develop into progressive pulmonary fibrosis (PPF) despite initial management. A substantial proportion of patients with non-IPF interstitial lung diseases (ILDs) progress to PPF, including connective tissue disease-associated ILD (such as rheumatoid arthritis-associated ILD, systemic sclerosis-associated ILD, and idiopathic inflammatory myositis-associated ILD), fibrosing hypersensitivity pneumonitis, and fibrosing occupational ILD. The concept of PPF emerged only recently and several studies have confirmed the impact of PPF on mortality. In addition to poor prognosis among patients with PPF, there remains a lack of consensus in the diagnosis and treatment of PPF across different types of ILDs. There is a need to raise awareness of PPF in FILDs and to explore measures to improve PPF diagnosis and treatment, which in turn could potentially reduce the progression from FILD to PPF. This review discusses the disease burden of PPF and recent advances in the management of PPF among patients with ILDs, including antifibrotic medications that have emerged as promising treatment options. Additionally, this review highlights the perspectives of expert Chinese physicians with regard to their experience in managing PPF in clinical practice.

Multimodal Diagnostics of Changes in Rat Lungs after Vaping

(1) Background: The use of electronic cigarettes has become widespread in recent years. The use of e-cigarettes leads to milder pathological conditions compared to traditional cigarette smoking. Nevertheless, e-liquid vaping can cause morphological changes in lung tissue, which affects and impairs gas exchange. This work studied the changes in morphological and optical properties of lung tissue under the action of an e-liquid aerosol. To do this, we implemented the "passive smoking" model and created the specified concentration of aerosol of the glycerol/propylene glycol mixture in the chamber with the animal. (2) Methods: In ex vivo studies, the lungs of Wistar rats are placed in the e-liquid for 1 h. For in vivo studies, Wistar rats were exposed to the e-liquid vapor in an aerosol administration chamber. After that, lung tissue samples were examined ex vivo using optical coherence tomography (OCT) and spectrometry with an integrating sphere. Absorption and reduced scattering coefficients were estimated for the control and experimental groups. Histological sections were made according to the standard protocol, followed by hematoxylin and eosin staining. (3) Results: Exposure to e-liquid in ex vivo and aerosol in in vivo studies was found to result in the optical clearing of lung tissue. Histological examination of the lung samples showed areas of emphysematous expansion of the alveoli, thickening of the alveolar septa, and the phenomenon of plasma permeation, which is less pronounced in in vivo studies than for the exposure of e-liquid ex vivo. E-liquid aerosol application allows for an increased resolution and improved imaging of lung tissues using OCT. Spectral studies showed significant differences between the control group and the ex vivo group in the spectral range of water absorption. It can be associated with dehydration of lung tissue owing to the hyperosmotic properties of glycerol and propylene glycol, which are the main components of e-liquids. (4) Conclusions: A decrease in the volume of air in lung tissue and higher packing of its structure under e-liquid vaping causes a better contrast of OCT images compared to intact lung tissue.