From Pixels to Prognosis: Unlocking the Potential of Deep Learning in Fibrotic Lung Disease Imaging Analysis.

The licensing of antifibrotic therapy for fibrotic lung diseases, including idiopathic pulmonary fibrosis IPF has created an urgent need for reliable biomarkers to predict disease progression and treatment response. Some patients experience stable disease trajectories, while others deteriorate rapidly, making treatment decisions challenging. High-resolution chest CT has become crucial for diagnosis, but visual assessments by radiologists suffer from low reproducibility and high interobserver variability. To address these issues, computer-based image analysis, called quantitative CT, has emerged. However, many quantitative CT methods rely on human input for training, therefore potentially incorporating human error into computer training. Rapid advances in artificial intelligence, specifically deep learning, aim to overcome this limitation by enabling autonomous quantitative analysis. While promising, deep learning also presents challenges including the need to minimize algorithm biases, ensuring explainability, and addressing accessibility and ethical concerns. This review explores the development and application of deep learning in improving the imaging process for fibrotic lung disease.

Description of a single centre cohort of patients with systemic sclerosis from the University Hospital of Buenos Aires and factors associated with lung function deterioration. A retrospective study.

INTRODUCTION: Given the paucity of data in Latin America and especially in Argentina regarding the epidemiology of SSc, the prevalence of ILD, its course, and particularly the response to treatment, our objective was to evaluate a cohort of SSc patients evaluated in a single University Hospital in Buenos Aires. PATIENTS/METHODS: We included 152 patients with SSc, followed from disease onset to last pulmonary function test and with at least two PFT and up to 30 months between each. RESULTS: Sixty-one percent had diffuse SSc (DSSc) and 32% limited SSc (LSSc). The only significant clinical differences between these groups were a higher initial mRodnan score and prevalence of ILD in the DSSc. These also had significantly more anti Scl-70 (Topoisomerase 1) antibodies compared to the LSSC group who had significantly more anti centromere antibodies. The DSSc group also had significantly more extensive damage on HRCT with no differences in terms of imaging patterns. Comparing patients with and without ILD by HRCT, those with ILD had significantly more extensive damage, significantly more anti Scl-70 antibodies, and significantly fewer anti centromere antibodies than those without ILD. Patients whose ILD progressed had a smoking history (OR 4.97) and prior immunosuppressive treatment (OR 15.6) (multivariate analysis). Overall disease duration was significantly shorter in those who progressed. CONCLUSIONS: Our SSc population had similar characteristics to those described elsewhere as well as prevalence of ILD and its progression. We found a shorter disease duration, smoking, and prior immunosuppressive treatment to be associated with ILD progression.

Description of a single centre cohort of patients with systemic sclerosis from the University Hospital of Buenos Aires and factors associated with lung function deterioration. A retrospective study / Descripción de una cohorte de pacientes con esclerosis sistémica del Hospital de la Universidad de Buenos Aires y factores asociados al deterioro de la función pulmonar. Un estudio retrospectivo

Introduction: Given the paucity of data in Latin America and especially in Argentina regarding the epidemiology of SSc, the prevalence of ILD, its course, and particularly the response to treatment, our objective was to evaluate a cohort of SSc patients evaluated in a single University Hospital in Buenos Aires. Patients/Methods: We included 152 patients with SSc, followed from disease onset to last pulmonary function test and with at least two PFT and up to 30 months between each. Results: Sixty-one percent had diffuse SSc (DSSc) and 32% limited SSc (LSSc). The only significant clinical differences between these groups were a higher initial mRodnan score and prevalence of ILD in the DSSc. These also had significantly more anti Scl-70 (Topoisomerase 1) antibodies compared to the LSSC group who had significantly more anti centromere antibodies. The DSSc group also had significantly more extensive damage on HRCT with no differences in terms of imaging patterns. Comparing patients with and without ILD by HRCT, those with ILD had significantly more extensive damage, significantly more anti Scl-70 antibodies, and significantly fewer anti centromere antibodies than those without ILD. Patients whose ILD progressed had a smoking history (OR 4.97) and prior immunosuppressive treatment (OR 15.6) (multivariate analysis). Overall disease duration was significantly shorter in those who progressed. Conclusions: Our SSc population had similar characteristics to those described elsewhere as well as prevalence of ILD and its progression. We found a shorter disease duration, smoking, and prior immunosuppressive treatment to be associated with ILD progression.(AU)

Introducción: La escasez de datos en Latinoamérica, y especialmente en Argentina, sobre la epidemiología de la esclerosis sistémica (SSc), la prevalencia de enfermedad pulmonar intersticial (EPID) y su progresión, llevó a evaluar una cohorte de pacientes con SSc atendidos en un hospital universitario de Buenos Aires, Argentina. Pacientes/Métodos: Incluimos 152 pacientes con SSc, seguidos desde el inicio de la enfermedad hasta el último examen funcional respiratorio (EFR) y con por lo menos dos EFR separados por un mínimo de 30 meses. Resultados: El 61% tenían enfermedad difusa (DSSc) y el 32%, limitada (LSSc). Aquellos con DSSc tuvieron significativamente un mayor índice modificado de Rodnan y prevalencia de EPID. Estos también tuvieron significativamente más anticuerpos anti-Scl-70 (topoisomerasa 1) comparados con LSSc, quienes tuvieron significativamente más anticuerpos anti-centrómero. Aquellos con DSSc mostraron significativamente más daño en la tomografía computada de alta resolución (TACAR), pero sin diferencias respecto a patrón de imágenes. Aquellos con EPID por TACAR tuvieron significativamente más daño, más anticuerpos anti Scl-70 y menos anticuerpos anti-centrómero que aquellos sin EPID. La progresión de EPID (análisis multivariado) se relacionó con consumo de tabaco (OR: 4,97) y uso previo de inmunosupresores (OR: 15,6). La duración de la enfermedad fue menor en los que progresaron. Conclusiones:Nuestra población de SSc tuvo características similares a lo descripto en el resto del mundo, así como la prevalencia y la progresión de EPID. Encontramos una menor duración de enfermedad, el consumo de tabaco y el uso previo de inmunosupresores asociados a la progresión de EPID.(AU)

Exploring computer-based imaging analysis in interstitial lung disease: opportunities and challenges.

The advent of quantitative computed tomography (QCT) and artificial intelligence (AI) using high-resolution computed tomography data has revolutionised the way interstitial diseases are studied. These quantitative methods provide more accurate and precise results compared to prior semiquantitative methods, which were limited by human error such as interobserver disagreement or low reproducibility. The integration of QCT and AI and the development of digital biomarkers has facilitated not only diagnosis but also prognostication and prediction of disease behaviour, not just in idiopathic pulmonary fibrosis in which they were initially studied, but also in other fibrotic lung diseases. These tools provide reproducible, objective prognostic information which may facilitate clinical decision-making. However, despite the benefits of QCT and AI, there are still obstacles that need to be addressed. Important issues include optimal data management, data sharing and maintenance of data privacy. In addition, the development of explainable AI will be essential to develop trust within the medical community and facilitate implementation in routine clinical practice.

Machine learning in radiology: the new frontier in interstitial lung diseases.

Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes.