A promising approach for screening pulmonary hypertension based on frontal chest radiographs using deep learning: A retrospective study.

BACKGROUND: To date, the missed diagnosis rate of pulmonary hypertension (PH) was high, and there has been limited development of a rapid, simple, and effective way to screen the disease. The purpose of this study is to develop a deep learning approach to achieve rapid detection of possible abnormalities in chest radiographs suggesting PH for screening patients suspected of PH. METHODS: We retrospectively collected frontal chest radiographs and the pulmonary artery systolic pressure (PASP) value measured by Doppler transthoracic echocardiography from 762 patients (357 healthy controls and 405 with PH) from three institutes in China from January 2013 to May 2019. The wohle sample comprised 762 images (641 for training, 80 for internal test, and 41 for external test). We firstly performed a 8-fold cross-validation on the 641 images selected for training (561 for pre-training, 80 for validation), then decided to tune learning rate to 0.0008 according to the best score on validation data. Finally, we used all the pre-training and validation data (561+80 = 641) to train our models (Resnet50, Xception, and Inception V3), evaluated them on internal and external test dataset to classify the images as having manifestations of PH or healthy according to the area under the receiver operating characteristic curve (AUC/ROC). After that, the three deep learning models were further used for prediction of PASP using regression algorithm. Moreover, we invited an experienced chest radiologist to classify the images in the test dataset as having PH or not, and compared the prediction accuracy performed by deep learing models with that of manual classification. RESULTS: The AUC performed by the best model (Inception V3) achieved 0.970 in the internal test, and slightly declined in the external test (0.967) when using deep learning algorithms to classify PH from normal based on chest X-rays. The mean absolute error (MAE) of the best model for prediction of PASP value was smaller in the internal test (7.45) compared to 9.95 in the external test. Manual classification of PH based on chest X-rays showed much lower AUCs compared to that performed by deep learning models both in the internal and external test. CONCLUSIONS: The present study used deep learning algorithms to classify abnormalities suggesting PH in chest radiographs with high accuracy and good generalizability. Once tested prospectively in clinical settings, the technology could provide a non-invasive and easy-to-use method to screen patients suspected of having PH.

Neutrophil-To-Lymphocyte Ratio Predicted Long-Term Chemotherapy Benefits In Stage IIIB-IV Non-Squamous Non-Small Cell Lung Cancer Patients Without Sensitive Mutations.

PURPOSE: To investigate the predictive capability of clinical parameters for long-term chemotherapy benefits among stage IIIB-IV non-squamous non-small cell lung cancer (NSCLC) patients without sensitive mutations. PATIENTS AND METHODS: We investigated the clinical features of 206 stage IIIB-IV non-squamous NSCLC patients without sensitive mutations and assessed their predictive value for disease control rate (DCR) at 6 and 12 months post-treatment. RESULTS: Seventy-two patients received docetaxel and platinum-based chemotherapy while 134 received pemetrexed and platinum-based chemotherapy. The 6-month and 12-month DCR were 33 (45.8%) and 6 (8.3%) in the docetaxel group and 69 (51.5%) and 19 (14.2%) in the pemetrexed group, respectively. Univariate Cox regression revealed that age, sex, smoking history, adrenal gland metastasis, stage IV disease, neutrophil-to-lymphocyte ratio (NLR), and serum albumin were associated with unfavorable progression-free survival (PFS). Age, stage IV disease, and NLR were identified as independent predictors of PFS using multivariate analysis. NLR was the only parameter that could predict 3-month and 6-month DCRs. NLR and age were able to predict 12-month DCR, with NLR presenting a larger area under the curve. Kaplan-Meier curves demonstrated that patients with NLR > 2.231 displayed significantly reduced long-term disease control. The group with higher NLR had more male patients, lower ALB levels, and serum sodium levels as well as higher platelet counts. CONCLUSION: NLR was an independent predictor of long-term chemotherapy benefits among non-squamous NSCLC patients without sensitive mutations. Patients with lower NLR were optimal candidates for chemotherapy. Patients with high NLR may receive alternative treatments or be included in clinical trials.

Selection of glucocorticoid-sensitive patients in interstitial lung disease secondary to connective tissue diseases population by radiomics.

PURPOSE: The effect of glucocorticoid(s) on connective tissue disease (CTD)-related interstitial lung disease (ILD) is controversial. This multicenter study aimed to identify glucocorticoid-sensitive patients using a radiomics approach. METHODS: A total of 416 CTD-ILD patients who began glucocorticoid treatment at the discretion of the attending physician, with or without cyclophosphamide, were included in this study. High doses were defined as pulsed intravenous methylprednisolone, an initial dose of 1 mg/kg/day of prednisolone or 0.8 mg/kg/day of methylprednisolone. Low doses were defined as those less than high doses. Radiomics features were manually extracted from primary lung lesions delineated on computed tomography images, and selected by variance, univariate feature selection, and least absolute shrinkage and selection operator regression model. The prediction models were developed using data from 309 patients from two centers and externally validated in 107 patients from four other hospitals. RESULTS: Treatment response in the training and validation groups was 38.5% and 36.4%, respectively. Eleven radiomics features were selected from 1,029 features with predictive value. Random forest models built for radiomics features to predict treatment response yielded a sensitivity of 0.897. The calibration curve of a nomogram demonstrated good agreement between prediction and observation. Decision curve analysis indicated that glucocorticoid was beneficial if the predicted response rate was 50%-60% for an individual. High doses of glucocorticoids and cyclophosphamide yielded superior efficacy. CONCLUSION: Radiomics-based predictive models reliably identified glucocorticoid-sensitive CTD-ILD patients. Short-term, high-dose glucocorticoid with cyclophosphamide yielded promising results as a potential therapy.

Renal aspergillosis after liver transplantation: clinical and imaging manifestations in two cases.

Renal aspergillosis (RAsp) is a rare complication in liver transplant (LT) recipients. Here we report RAsp in two LT recipients. In both patients, RAsp occurred more than 90 d after allogenetic orthotropic LT, and all the clinical findings were unspecific. RAsp involved unilateral kidney in Case one and bilateral kidneys in Case two. Both computed tomography (CT) and magnetic resonance imaging (MRI) revealed renal abscesses, with progressively enhanced walls and separations and unenhanced alveolate areas after contrast agent administration. On unenhanced CT images they showed inhomogeneous hypo-attenuation. On fat-suppressed T2-weighted images (T2WIs), the walls and separations of the abscesses showed slightly low signal intensity and the central parts of the lesions showed slightly high signal intensity. Both on CT and MRI, there were some hints of renal infarction or chronic ischemia. Both cases were treated by radical nephrectomy followed by adjuvant antifungal treatment. They all recovered well.