RESUMO
Background: Pleuroparenchymal Fibroelastosis (PPFE) is a rare disease that consists of elastofibrosis that involves the pleura and subpleural lung parenchyma; it is an unusual pulmonary disease with unique clinical, radiological and pathological characteristics. According to recent studies, PPFE may not be a definite disease but a form of chronic lung injury. The aim of this retrospective study is to determine the incidence and to evaluate the distribution, severity and progression of this radiological entity on high-resolution CT (HRCT) exams of the chest, performed in routine clinical practice. In total, 1514 HRCT exams performed in the period January 2016-June 2018 were analyzed. For each exam, the presence of PPFE was evaluated and a quantitative score was assigned (from 0 to 7 points, based on the maximum depth of fibrotic involvement of the parenchyma). When available, two exams with a time interval of at least 6 months were compared for each patient in order to evaluate progression (defined as the increase in the disease score). Patients were divided into different groups according to exposure and their associated diseases. Statistical analysis was performed by using the Wilcoxon test and Kruskal-Wallis test. Results: PPFE was detected in 174 out of 1514 patients (11.6%), with a mean score of 6.1 ± 3.9 (range 1-14). In 106 out of 174 patients (60.9%), a previous CT scan was available and an evolution of PPFE was detected in 19 of these (11.5%). Among these 19 patients with worsening PPFE, 4 had isolated PPFE that was associated with chronic exposure or connective tissue disorders, and the other 15 had an associated lung disease and/or a chronic exposure. In this group, it was found that the ventral segments of the upper lobes, fissures and apical segments of the lower lobes had a greater statistically significant involvement in the progression of the disease compared to the non-progressive group. In 16 of 174 patients (9.2%, 7 of which belonged to the radiological progression group) a biopsy through video-assisted thoracoscopic surgery or apicoectomy confirmed PPFE. Conclusion: PPFE-like lesions are not uncommon on HRCT exams in routine clinical practice, and are frequently found in patients with different forms of chronic lung injury. Further studies are necessary to explain why the disease progresses in some cases, while in most, it remains stationary over time.
RESUMO
OBJECTIVE: The purpose of this study is to analyze the texture characteristics of chronic non-bacterial osteomyelitis (CNO) bone lesions, identified as areas of altered signal intensity on short tau inversion recovery (STIR) sequences, and to distinguish them from bone marrow growth-related changes through Machine Learning (ML) and Deep Learning (DL) analysis. MATERIALS AND METHODS: We included a group of 66 patients with confirmed diagnosis of CNO and a group of 28 patients with suspected extra-skeletal systemic disease. All examinations were performed on a 1.5 T MRI scanner. Using the opensource 3D Slicer software version 4.10.2, the ROIs on CNO lesions and on the red bone marrow were sampled. Texture analysis (TA) was carried out using Pyradiomics. We applied an optimization search grid algorithm on nine classic ML classifiers and a Deep Learning (DL) Neural Network (NN). The model's performance was evaluated using Accuracy (ACC), AUC-ROC curves, F1-score, Positive Predictive Value (PPV), Mean Absolute Error (MAE) and Root-Mean-Square Error (RMSE). Furthermore, we used Shapley additive explanations to gain insight into the behavior of the prediction model. RESULTS: Most predictive characteristics were selected by Boruta algorithm for each combination of ROI sequences for the characterization and classification of the two types of signal hyperintensity. The overall best classification result was obtained by the NN with ACC = 0.91, AUC = 0.93 with 95% CI 0.91-0.94, F1-score = 0.94 and PPV = 93.8%. Between classic ML methods, ensemble learners showed high model performance; specifically, the best-performing classifier was the Stack (ST) with ACC = 0.85, AUC = 0.81 with 95% CI 0.8-0.84, F1-score = 0.9, PPV = 90%. CONCLUSIONS: Our results show the potential of ML methods in discerning edema-like lesions, in particular by distinguishing CNO lesions from hematopoietic bone marrow changes in a pediatric population. The Neural Network showed the overall best results, while a Stacking classifier, based on Gradient Boosting and Random Forest as principal estimators and Logistic Regressor as final estimator, achieved the best results between the other ML methods.
