Texture-based classification of lung disease patterns in chronic hypersensitivity pneumonitis and comparison to clinical outcomes.

Computer-aided detection algorithms applied to CT lung imaging have the potential to objectively quantify pulmonary pathology. We aim to develop an automatic classification method based on textural features able to classify healthy and pathological patterns on CT lung images and to quantify the extent of each disease pattern in a group of patients with chronic hypersensitivity pneumonitis (cHP), in comparison to pulmonary function tests (PFTs).27 cHP patients were scanned via high resolution CT (HRCT) at full-inspiration. Regions of interest (ROIs) were extracted and labeled as normal (NOR), ground glass opacity (GGO), reticulation (RET), consolidation (C), honeycombing (HB) and air trapping (AT). For each ROI, statistical, morphological and fractal parameters were computed. For automatic classification, we compared two classification methods (Bayesian and Support Vector Machine) and three ROI sizes. The classifier was therefore applied to the overall CT images and the extent of each class was calculated and compared to PFTs. Better classification accuracy was found for the Bayesian classifier and the 16x16 ROI size: 92.1±2.7%. The extent of GGO, HB and NOR significantly correlated with forced vital capacity (FVC) and the extent of NOR with carbon monoxide diffusing capacity (DLCO).Clinical Relevance- Texture analysis can differentiate and objectively quantify pathological classes in the lung parenchyma and may represent a quantitative diagnostic tool in cHP.

Computational Fluid Dynamics (CFD) Analysis of Subject-specific Bronchial Tree Models in Lung Cancer Patients.

Lung resection is the only potentially curative treatment for lung cancer. The inevitable partial removal of functional lung tissue along with the tumoral mass requires a careful and structured pre-operative condition of patients. In particular, the postoperative residual functionality of the lung needs to be predicted. Clinically, this is assessed through algorithms based on pulmonary function tests (PFTs). However, these approaches neglect the local airway segment's functionality and provide a globally averaged evaluation. CFD was demonstrated to provide patient-specific, quantitative, and local information on flow dynamics and regional ventilation in the bronchial tree. This study aims to apply CFD to characterize the flow dynamics in 12 patients affected by lung cancer and evaluate the effects of the tumoral masses on flow parameters and lobar flow distribution. Patient-specific airway models were reconstructed from CT images, and the tumoral masses were manually segmented. Measurements of lungs and tumor volumes were collected. A peripherality index was defined to describe tumor distance from the parenchyma. CFD simulations were performed in Fluent®, and the results were analyzed in terms of flow parameters and lobar volume flow rate (VFR). The predicted postoperative forced expiratory volume in 1s (ppoFEV1) was estimated and compared to the current clinical algorithm. The patients under analysis showed relatively small tumoral masses located close to the lung parenchyma. CFD results did not highlight lobar alterations of flow parameters, whereas the flow to the lung affected by the tumor was found to be significantly lower (p=0.026) than the contralateral lung. The estimation ppoFEV1 obtained through the results of the simulations showed a high correlation (ρ=0.993, p<0.001) with the clinical formula.Clinical Relevance- The proposed study establishes the efficacy and applicability of CFD for the pre-operative characterization of patients undergoing lobectomy surgery. This technique can provide additional information on local functionality and flow dynamics to support patients' operability.