Radiomics and Clinical Data for the Diagnosis of Incidental Pulmonary Nodules and Lung Cancer Screening: Radiolung Integrative Predictive Model.

INTRODUCTION: Early diagnosis of lung cancer (LC) is crucial to improve survival rates. Radiomics models hold promise for enhancing LC diagnosis. This study assesses the impact of integrating a clinical and a radiomic model based on deep learning to predict the malignancy of pulmonary nodules (PN). METHODOLOGY: Prospective cross-sectional study of 97 PNs from 93 patients. Clinical data included epidemiological risk factors and pulmonary function tests. The region of interest of each chest CT containing the PN was analysed. The radiomic model employed a pre-trained convolutional network to extract visual features. From these features, 500 with a positive standard deviation were chosen as inputs for an optimised neural network. The clinical model was estimated by a logistic regression model using clinical data. The malignancy probability from the clinical model was used as the best estimate of the pre-test probability of disease to update the malignancy probability of the radiomic model using a nomogram for Bayes' theorem. RESULTS: The radiomic model had a positive predictive value (PPV) of 86%, an accuracy of 79% and an AUC of 0.67. The clinical model identified DLCO, obstruction index and smoking status as the most consistent clinical predictors associated with outcome. Integrating the clinical features into the deep-learning radiomic model achieves a PPV of 94%, an accuracy of 76% and an AUC of 0.80. CONCLUSIONS: Incorporating clinical data into a deep-learning radiomic model improved PN malignancy assessment, boosting predictive performance. This study supports the potential of combined image-based and clinical features to improve LC diagnosis.

Evaluation of Light's criteria in cytologically proved malignant pleural effusions.

BACKGROUND: Malignant pleural effusions are usually described as exudates. However, several studies have determined a high incidence of cytologically proved malignant effusions in transudates. The study aims to determine the compliance of cytologically proved malignant pleural effusions with Light's Criteria and to assess when it is necessary to perform more studies in transudates. METHODS: We have retrospectively reviewed all the cytologically positive effusions at our institution over six years. Biochemical characteristics were recorded, and Light's criteria were determined for each effusion. We analyzed the effusions' compliance with the criteria and determined whether its primary tumor or the presence of cirrhosis, acute kidney injury or congestive heart failure could interfere in the criteria being met. RESULTS: Overall, 224 patients presented malignant pleural effusions with biochemical pleural fluid analysis. Two (0.9%) were transudative effusions and two hundred and twenty-two (99.1%) were exudative effusions. Lung carcinoma, breast carcinoma and ovarian carcinoma were the most frequent primary tumors. One hundred and two (45.94%) patients met three Light criteria, 77 (34.68%) patients met two criteria and 43 (19.36%) met one criterion. Both patients with transudative malignant pleural effusions presented concomitant malignant ascites. CONCLUSIONS: Malignant transudative pleural effusions were 0.9% of our patients. We found no relation between transudative malignant effusions and the presence of cirrhosis, acute kidney injury or congestive heart failure, or the type of tumor. We found no difference between the tumor type and the distribution of Light's criteria met.

Right sleeve S2 segmentectomy for lung carcinoid tumor in a patient with tracheal bronchus.

Carcinoid tumors are relative rare neuroendocrine tumors of the lung. Bronchial obstruction's symptoms as cough, hemoptysis and pneumonia may be present when they are centrally located and lung-sparing surgery is usually preferred. We describe the case of an adult patient with a central right upper lobe carcinoid tumor and a concurrent tracheal bronchus malformation. This peculiar bronchial malformation allowed a sleeve S2 segmentectomy sparing the S1-S3 segments and the middle and lower lobes. The patient was discharged on day 4 without complications.

Transbronchial and transesophageal fine-needle aspiration using a single ultrasound bronchoscope in the diagnosis of locoregional recurrence of surgically-treated lung cancer.

BACKGROUND: The present study sought to evaluate the usefulness of EBUS-TBNA in the diagnosis of locoregional recurrence of lung cancer in a cohort of lung cancer patients who were previously treated surgically, and describe our initial experience of EUS-B-FNA in this clinical scenario. METHODS: We retrospectively studied the clinical records of all patients with a previous surgically-treated lung cancer who were referred to our bronchoscopy unit after suspicion of locoregional recurrence. The diagnostic sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and overall accuracy of EBUS-TBNA for the diagnosis of locoregional recurrence were evaluated. RESULTS: Seventy-three patients were included. EBUS-TBNA confirmed malignancy in 40 patients: 34 confirmed to have locoregional recurrence, six had metachronous tumours. Of the 33 patients with non-malignant EBUS-TBNA; 2 had specific non-malignant diseases, 26 underwent radiological follow up and 5 patients underwent surgery. Of the 26 patients who had radiological follow up; 18 remained stable, three presented thoracic radiological progression and 5 presented extrathoracic progression. Of the 5 patients who underwent surgery; 3 had metachronous tumours, one confirmed to be a true negative and one presented nodal invasion. Seven patients underwent EUS-B-FNA, four of them confirmed to have recurrence. The sensitivity, specificity, NPV, PPV and overall accuracy of EBUS-TBNA for the diagnosis of locoregional recurrence were 80.9, 100, 69.2, 100 and 86.6% respectively. CONCLUSIONS: EBUS-TBNA is an accurate procedure for the diagnosis of locoregional recurrence of surgically-treated lung cancer. EUS-B-FNA combined with EBUS-TBNA broads the diagnostic yield of EBUS-TBNA alone.

Pleuroparenchymal Fibroelastosis: A New Entity within the Spectrum of Rare Idiopathic Interstitial Pneumonias.

Pleuroparenchymal fibroelastosis (PPFE) is a rare entity that has been recently included in the official American Thoracic Society/European Respiratory Society (ATS/ERS) statement in 2013 as a group of rare idiopathic interstitial pneumonias (IIPs). PPFE is characterized by pleural and subpleural parenchymal thickening due to elastic fiber proliferation, mainly in the upper lobes. The etiology of the disease is unclear, although some cases have been associated as a complication after bone marrow transplantation, lung transplantation (LT), chemotherapy, and recurrent respiratory infections. The patients usually report progressive dyspnea and dry cough and are predisposed to develop spontaneous or iatrogenic pneumothoraces after surgical lung biopsy (SLB) for its diagnosis. That is why better awareness with the clinical and radiologic features can help optimal management by the multidisciplinary team. Novel invasive techniques such as cryobiopsy may become useful tools in these patients as it could spare SLB. We present the first reported cases in Spain.