Background: Pleural diseases represent a significant healthcare burden, affecting over 350 000 patients annually in the US alone and requiring accurate diagnostic approaches for optimal management. Traditional imaging techniques have limitations in differentiating various pleural disorders and invasive procedures are usually required for definitive diagnosis.Methods: We conducted a nonsystematic, narrative literature review aimed at describing the latest advances in imaging techniques and artificial intelligence (AI) applications in pleural diseases.Results: Novel ultrasound-based techniques, such as elastography and contrast-enhanced ultrasound, are described for their promising diagnostic accuracy in differentiating malignant from benign pleural lesions. Quantitative imaging techniques utilising pixel-density measurements to noninvasively distinguish exudative from transudative effusions are highlighted. AI algorithms, which have shown remarkable performance in pleural abnormality detection, malignant effusion characterisation and automated pleural fluid volume quantification, are also described. Finally, the role of deep-learning models in early complication detection and automated analysis of follow-up imaging studies is examined.Conclusions: Advanced imaging techniques and AI applications show promise in the management and follow-up of pleural diseases, improving diagnostic accuracy and reducing the need for invasive procedures. However, larger prospective studies are needed for validation. The integration of AI-driven imaging analysis with molecular and genomic data offers potential for personalised therapeutic strategies, although challenges in data privacy, algorithm transparency and clinical validation persist. This comprehensive approach may revolutionise pleural disease management, enhancing patient outcomes through more accurate, noninvasive diagnostic strategies.

Background: Drug-induced interstitial lung disease (DI-ILD) encompasses a heterogeneous spectrum of potentially severe pulmonary toxicities associated with various pharmacological agents. Diagnosis is often delayed due to nonspecific symptoms and imaging findings that can mimic other ILDs or infections, particularly in patients receiving oncological or immunomodulatory therapies. Novel approaches are needed to improve early recognition and management. Methods: We conducted a non-systematic, narrative literature review across major biomedical databases up to June 2025, aimed at describing current and emerging applications of artificial intelligence (AI) and radiomics in the early diagnosis, risk stratification, and personalised management of DI-ILD. Results: Radiomics applied to computed tomography and positron emission tomography/computed tomography enables extraction of high-dimensional quantitative features capturing subclinical alterations undetectable by visual assessment. In DI-ILD (particularly immune checkpoint inhibitor-related pneumonitis), radiomic models show potential diagnostic utility in distinguishing overlapping imaging patterns and predicting fibrotic progression. Integration with clinical, radiological and pharmacogenomic data has improved model performance in several studies. Additionally, AI approaches, including convolutional neural networks and ensemble learning methods, demonstrate promise in enhancing pattern recognition and risk stratification. Conclusions: Radiomics and AI are emerging complementary tools in multidisciplinary management of DI-ILD, offering objective imaging biomarkers and facilitating multimodal data integration to improve diagnostic precision and personalised therapeutic decisions. Nonetheless, reproducibility remains limited by variability in imaging protocols and lack of large-scale prospective multicentre validation. Clinical implementation requires standardised protocols to ensure consistency and reliability. The development of transparent, interpretable models seamlessly integrated into healthcare workflows is essential to fully leverage their real-world potential in proactive patient care.

Worldwide there is an imbalance between the number of patients discharged after Covid-19 and the availability of healthcare resources to follow them after acute illness. Six-minute walking test (6MWT) is a valid and inexpensive measure of exercise capacity for people with chronic lung disease. We used 6MWT during follow-up of patients discharged after Covid-19 to verify if it can be a reliable measure of the disease recovery. During 6MWT we reported walking distance in meters (6MWD), lowest SpO2 when breathing air (SpO2 nadir), desaturation and distance–saturation product (DSP), defined as the product of 6MWD and SpO2 nadir (Table). Data from the first 100 subjects show that 6MWD and DSP at 6 months correlates positively with percent predicted DLCO (p=0.0001) and inversely with HRCT severity score at six months (p<0.05). In addition, patients with PaO2/FiO2 during hospitalization (P/F nadir) 200 mmHg during hospitalization. In conclusion, 6MWT is a useful test in post-Covid-19 follow-up as it correlates with the severity of acute disease and with functional/radiological impairment in the chronic phase of Covid-19. Furthermore, it shows the progressive improvement in exercise capacity.

During the COVID-19 pandemic, the use of non-invasive respiratory support (NIRS) became crucial in treating patients with acute hypoxemic respiratory failure. Despite the fear of viral aerosolization, non-invasive respiratory support has gained attention as a way to alleviate ICU overcrowding and reduce the risks associated with intubation. The COVID-19 pandemic has led to an unprecedented increased demand for research, resulting in numerous publications on observational studies, clinical trials, reviews, and meta-analyses in the past three years. This comprehensive narrative overview describes the physiological rationale, pre-COVID-19 evidence, and results of observational studies and randomized control trials regarding the use of high-flow nasal oxygen, non-invasive mechanical ventilation, and continuous positive airway pressure in adult patients with COVID-19 and associated acute hypoxemic respiratory failure. The review also highlights the significance of guidelines and recommendations provided by international societies and the need for further well-designed research to determine the optimal use of NIRS in treating this population.

Advances in bronchoscopic techniques for the diagnosis of lung cancer Interventional pulmonology uses minimally invasive techniques to diagnose and treat lung cancer, pleural disease, and many types of complex airway and lung disorders. Over the past decade, interventional pulmonology has seen significant progress in the field of endoscopic procedures, particularly in the diagnosis, staging, and sometimes treatment of lung cancer. The research topic "Advances in Bronchoscopic Techniques for the Diagnosis of Lung Cancer" brings together diverse contributions that showcase the latest innovations in bronchoscopy. Here we highlight the innovative advances presented in the articles within this Research Topic from the perspective of an interventional pulmonologist. When faced with a lung lesion suspected to be lung cancer on chest computed tomography (CT) it is imperative to evaluate the least invasive and most effective diagnostic approach. Among the potential options, the bronchoscopic approach offers the advantage of directly visualizing the airways and the ability to perform biopsies of mucosal alterations. In their original research article, Zhu et al. employed narrow-band imaging (NBI), an endoscopic technique for evaluating surface patterns and microvascular architecture using a narrow spectrum of light that retains only blue and green wavelengths. The study included 916 patients with clinical or radiologic suspicion of central lung cancer or patients undergoing follow-up after curative lung cancer surgery, all of whom underwent bronchoscopy with NBI. Compared with pathological findings, NBI demonstrated diagnostic sensitivity, specificity, positive predictive value, and negative predictive value of 91.7%, 84.9%, 97.6%, and 61.5%, respectively. The article also describes the predominant vascular pattern in relation to the histologic types. If the lung lesion is peripheral rather than central, it can still be accessed with a bronchoscope using other technologies, such as fluoroscopy and/or a radial endobronchial ultrasound (R-EBUS) probe. This, inserted through the working channel of a flexible bronchoscope or catheter (guide sheath), facilitates real-time imaging of the surrounding tissue, enabling the clinician to confirm the location of the lesion. Hu et al., in their original research article, analyzed the clinical significance of the resistance encountered by the R-EBUS probe when passing through peripheral lung lesions for diagnostic purposes. Probe resistance was classified as type I (no resistance), type II (moderate), and type III (high). A significant difference in the diagnostic yield between malignant and benign disease was Frontiers in Oncology frontiersin.org 01