Enhancing lymph node metastasis prediction in adenocarcinoma of the esophagogastric junction: A study combining radiomic with clinical features.

BACKGROUND: The incidence of adenocarcinoma of the esophagogastric junction (AEJ) is increasing, and with poor prognosis. Lymph node status (LNs) is particularly important for planning treatment and evaluating the prognosis of patients with AEJ. However, the use of radiomic based on enhanced computed tomography (CT) to predict the preoperative lymph node metastasis (PLNM) status of the AEJ has yet to be reported. PURPOSE: We sought to investigate the value of radiomic features based on enhanced CT in the accurate prediction of PLNM in patients with AEJ. METHODS: Clinical features and enhanced CT data of 235 patients with AEJ from October 2017 to May 2023 were retrospectively analyzed. The data were randomly assigned to the training cohort (n = 164) or the external testing cohort (n = 71) at a ratio of 7:3. A CT-report model, clinical model, radiomic model, and radiomic-clinical combined model were developed to predict PLNM in patients with AEJ. Univariate and multivariate logistic regression were used to screen for independent clinical risk factors. Least absolute shrinkage and selection operator (LASSO) regression was used to select the radiomic features. Finally, a nomogram for the preoperative prediction of PLNM in AEJ was constructed by combining Radiomics-score and clinical risk factors. The models were evaluated by area under the receiver operating characteristic curve (AUC-ROC), calibration curve, and decision curve analyses. RESULTS: A total of 181 patients (181/235, 77.02%) had LNM. In the testing cohort, the AUC of the radiomic-clinical model was 0.863 [95% confidence interval (CI) = 0.738-0.957], and the radiomic model (0.816; 95% CI = 0.681-0.929), clinical model (0.792; 95% CI = 0.677-0.888), and CT-report model (0.755; 95% CI = 0.647-0.840). CONCLUSION: The radiomic-clinical model is a feasible method for predicting PLNM in patients with AEJ, helping to guide clinical decision-making and personalized treatment planning.

Early Diagnosis of High-Risk Chronic Obstructive Pulmonary Disease Based on Quantitative High-Resolution Computed Tomography Measurements.

Purpose: Quantitative computed tomography (QCT) techniques, focusing on airway anatomy and emphysema, may help to detect early structural changes of COPD disease. This retrospective study aims to identify high-risk COPD participants by using QCT measurements. Patients and Methods: We enrolled 140 participants from the Second Affiliated Hospital of Shenyang Medical College who completed inspiratory high-resolution CT scans, pulmonary function tests (PFTs), and clinical characteristics recorded. They were diagnosed Non-COPD by PFT value of FEV1/FVC >70% and divided into two groups according percentage predicted FEV1 (FEV1%), low-risk COPD group: FEV1% ≥ 95%, high-risk group: 80% < FEV1% < 95%. The QCT measurements were analyzed by the Student's t-test (or Mann-Whitney U-test) method. Then, feature candidates were identified using the LASSO method. Meanwhile, the correlation between QCT measurements and PFTs was assessed by the Spearman rank correlation test. Furthermore, support vector machine (SVM) was performed to identify high-risk COPD participants. The performance of the models was evaluated in terms of accuracy (ACC), sensitivity (SEN), specificity (SPE), F1-score, and area under the ROC curve (AUC), with p <0.05 considered statistically significant. Results: The SVM based on QCT measurements achieved good performance in identifying high-risk COPD patients with 85.71% of ACC, 88.34% of SEN, 84.00% of SPE, 83.33% of F1-score, and 0.93 of AUC. Further, QCT measurements integration of clinical data improved the performance with an ACC of 90.48%. The emphysema index (%LAA-950) of left lower lung was negatively correlated with PFTs (P < 0.001). The airway anatomy indexes of lumen diameter (LD) were correlated with PFTs. Conclusion: QCT measurements combined with clinical information could provide an effective tool for an early diagnosis of high-risk COPD. The QCT indexes can be used to assess the pulmonary function status of high-risk COPD.

Deep multi-instance transfer learning for pneumothorax classification in chest X-ray images.

PURPOSE: Pneumothorax is a life-threatening emergency that requires immediate treatment. Frontal-view chest X-ray images are typically used for pneumothorax detection in clinical practice. However, manual review of radiographs is time-consuming, labor-intensive, and highly dependent on the experience of radiologists, which may lead to misdiagnosis. Here, we aim to develop a reliable automatic classification method to assist radiologists in rapidly and accurately diagnosing pneumothorax in frontal chest radiographs. METHODS: A novel residual neural network (ResNet)-based two-stage deep-learning strategy is proposed for pneumothorax identification: local feature learning (LFL) followed by global multi-instance learning (GMIL). Most of the nonlesion regions in the images are removed for learning discriminative features. Two datasets are used for large-scale validation: a private dataset (27 955 frontal-view chest X-ray images) and a public dataset (the National Institutes of Health [NIH] ChestX-ray14; 112 120 frontal-view X-ray images). The model performance of the identification was evaluated using the accuracy, precision, recall, specificity, F1-score, receiver operating characteristic (ROC), and area under ROC curve (AUC). Fivefold cross-validation is conducted on the datasets, and then the mean and standard deviation of the above-mentioned metrics are calculated to assess the overall performance of the model. RESULTS: The experimental results demonstrate that the proposed learning strategy can achieve state-of-the-art performance on the NIH dataset with an accuracy, AUC, precision, recall, specificity, and F1-score of 94.4% ± 0.7%, 97.3% ± 0.5%, 94.2% ± 0.3%, 94.6% ± 1.5%, 94.2% ± 0.4%, and 94.4% ± 0.7%, respectively. CONCLUSIONS: The experimental results demonstrate that our proposed CAD system is an efficient assistive tool in the identification of pneumothorax.

Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features.

To assess if quantitative integrated deep learning and radiomics features can predict the PD-L1 expression level in preoperative MRI of hepatocellular carcinoma (HCC) patients. The data in this study consist of 103 hepatocellular carcinoma patients who received immunotherapy in a single center. These patients were divided into a high PD-L1 expression group (30 patients) and a low PD-L1 expression group (73 patients). Both radiomics and deep learning features were extracted from their MRI sequence of T2-WI, which were merged into an integrative feature space for machine learning for the prediction of PD-L1 expression. The five-fold cross-validation was adopted to validate the performance of the model, while the AUC was used to assess the predictive ability of the model. Based on the five-fold cross-validation, the integrated model achieved the best prediction performance, with an AUC score of 0.897 ± 0.084, followed by the deep learning-based model with an AUC of 0.852 ± 0.043 then the radiomics-based model with AUC of 0.794 ± 0.035. The feature set integrating radiomics and deep learning features is more effective in predicting PD-L1 expression level than only one feature type. The integrated model can achieve fast and accurate prediction of PD-L1 expression status in preoperative MRI of HCC patients.