Diagnostic approach to interstitial lung disease

Predictive role of natural killer cells in bronchoalveolar lavage fluid of patients with sarcoidosis

Sarcoidosis is a rare granulomatous disease of unknown aetiology belonging to the wide group of interstitial lung diseases.). Although the limitlessness of BAL fluid is debated, it remains one of the best matrices for studying the pathogenesis of sarcoidosis. Natural killer (NK) cells have been described in BAL fluid from sarcoidosis patients. Elevated NK cells in BAL fluid from sarcoidosis patients have been found to be associated with poor outcomes. In this study, NK cells were evaluated in BAL samples from sarcoidosis patients at the time of diagnosis and associated with clinical characteristics in order to evaluate their prognostic role. Of the 276 patients suspected to have sarcoidosis on the basis of clinical and radiological findings, 248 had a final diagnosis of sarcoidosis. Clinical parameters, Scadding stage, and extrapulmonary localization were collected in a database. It resulted in fibrotic sarcoidosis patients being associated with an increase in lymphocyte percentages in BAL samples, particularly NK cells when compared with other groups. From ROC analysis, NK cell percentages in BAL samples resulted as being the best predictive markers in discriminating stage 4 of sarcoidosis from other RX stages (AUC=0.85, p<0.0001). Furthermore, after the stratification of patients on the basis of the number of extrapulmonary localizations, patients with an higher number of extrapulmonary localizations also showed higher percentages of NK cells in BAL fluid. In conclusion, NK cell percentages in BAL fluid can be considered a good prognostic marker of fibrotic phenotypes of sarcoidosis and involvement of other organs, although their diagnostic utility was poor.

Unsupervised machine learning identifies predictive progression markers of IPF

OBJECTIVES

To identify and evaluate predictive lung imaging markers and their pathways of change during progression of idiopathic pulmonary fibrosis (IPF) from sequential data of an IPF cohort. To test if these imaging markers predict outcome.

METHODS

We studied radiological disease progression in 76 patients with IPF, including overall 190 computed tomography (CT) examinations of the chest. An algorithm identified candidates for imaging patterns marking progression by computationally clustering visual CT features. A classification algorithm selected clusters associated with radiological disease progression by testing their value for recognizing the temporal sequence of examinations. This resulted in radiological disease progression signatures, and pathways of lung tissue change accompanying progression observed across the cohort. Finally, we tested if the dynamics of marker patterns predict outcome, and performed an external validation study on a cohort from a different center.

RESULTS

Progression marker patterns were identified and exhibited high stability in a repeatability experiment with 20 random sub-cohorts of the overall cohort. The 4 top-ranked progression markers were consistently selected as most informative for progression across all random sub-cohorts. After spatial image registration, local tracking of lung pattern transitions revealed a network of tissue transition pathways from healthy to a sequence of disease tissues. The progression markers were predictive for outcome, and the model achieved comparable results on a replication cohort.

CONCLUSIONS

Unsupervised learning can identify radiological disease progression markers that predict outcome. Local tracking of pattern transitions reveals pathways of radiological disease progression from healthy lung tissue through a sequence of diseased tissue types.

KEY POINTS

• Unsupervised learning can identify radiological disease progression markers that predict outcome in patients with idiopathic pulmonary fibrosis. • Local tracking of pattern transitions reveals pathways of radiological disease progression from healthy lung tissue through a sequence of diseased tissue types. • The progression markers achieved comparable results on a replication cohort.

Integrated approach to bronchoalveolar lavage cytology to distinguish interstitial lung diseases

BACKGROUND

Broncho-alveolar lavage (BAL) is a safe diagnostic procedure, useful for differentiating fibrotic lung disorders and for excluding malignancy and infection. A recent multicenter study demonstrated a new, relatively sensitive, and specific index called Bronchoalveolar Cytology Threshold (BCT), useful for distinguishing healthy individuals from patients with lung diseases.

OBJECTIVES

In our study, BCT was applied for the first time to the analysis of interstitial lung diseases (ILDs), investigating its potential for differential diagnosis. Combinations of BAL cells that improve diagnostic accuracy for ILDs were studied and are proposed.

METHODS

A retrospective analysis of BAL samples was performed. We considered more than 1000 BAL samples from patients investigated for ILD, performed at Siena University Hospital. The samples enrolled for the study included 468 patients: 413 with and 55 without ILD. BAL was performed for diagnostic purposes in line with international guidelines. BCT were calculated according to available literature.

RESULTS

Among ILDs, patients with fibrotic hypersensitivity pneumonitis, idiopathic pulmonary fibrosis (IPF) and sarcoidosis showed significantly lower BCTs than unclassified ILD. Asbestosis patients showed significantly lower BCTs than nonspecific interstitial pneumonia (NSIP), cryptogenic organizing pneumonia (COP), connective tissue disease related ILD (CTD-ILD), sarcoidosis and unclassified ILD patients. COP patients showed significantly higher BCT than IPF, f-HP and sarcoidosis. Moreover, COP patients were best distinguished by BCT.

CONCLUSION

The analysis of BAL features is currently included in the diagnostic algorithm of ILDs. BAL cell patterns and BCT index can provide useful information for distinguishing ILDs, reducing the need for invasive procedures. Integrated approaches to BAL analysis can improve the interpretation of results without further cost or loss of time.

Automated classification of usual interstitial pneumonia using regional volumetric texture analysis in high-resolution computed tomography

OBJECTIVES

We propose a novel computational approach for the automated classification of classic versus atypical usual interstitial pneumonia (UIP).

MATERIALS AND METHODS

Thirty-three patients with UIP were enrolled in this study. They were classified as classic versus atypical UIP by a consensus of 2 thoracic radiologists with more than 15 years of experience using the American Thoracic Society evidence-based guidelines for computed tomography diagnosis of UIP. Two cardiothoracic fellows with 1 year of subspecialty training provided independent readings. The system is based on regional characterization of the morphological tissue properties of lung using volumetric texture analysis of multiple-detector computed tomography images. A simple digital atlas with 36 lung subregions is used to locate texture properties, from which the responses of multidirectional Riesz wavelets are obtained. Machine learning is used to aggregate and to map the regional texture attributes to a simple score that can be used to stratify patients with UIP into classic and atypical subtypes.

RESULTS

We compared the predictions on the basis of regional volumetric texture analysis with the ground truth established by expert consensus. The area under the receiver operating characteristic curve of the proposed score was estimated to be 0.81 using a leave-one-patient-out cross-validation, with high specificity for classic UIP. The performance of our automated method was found to be similar to that of the 2 fellows and to the agreement between experienced chest radiologists reported in the literature. However, the errors of our method and the fellows occurred on different cases, which suggests that combining human and computerized evaluations may be synergistic.

CONCLUSIONS

Our results are encouraging and suggest that an automated system may be useful in routine clinical practice as a diagnostic aid for identifying patients with complex lung disease such as classic UIP, obviating the need for invasive surgical lung biopsy and its associated risks.