Lung cancer constitutes the most severe cause of cancer-related mortality. Recent evidence supports that early detection by means of computed tomography (CT) scans significantly reduces mortality rates. Given the remarkable progress of Vision Transformers (ViTs) in the field of computer vision, we have delved into comparing the performance of ViTs versus Convolutional Neural Networks (CNNs) for the automatic identification of lung cancer based on a dataset of 212 medical images. Importantly, neither ViTs nor CNNs require lung nodule annotations to predict the occurrence of cancer. To address the dataset limitations, we have trained both ViTs and CNNs with three advanced techniques: transfer learning, self-supervised learning, and sharpness-aware minimizer. Remarkably, we have found that CNNs achieve highly accurate prediction of a patient’s cancer status, with an outstanding recall (93.4%) and area under the Receiver Operating Characteristic curve (AUC) of 98.1%, when trained with self-supervised learning. Our study demonstrates that both CNNs and ViTs exhibit substantial potential with the three strategies. However, CNNs are more effective than ViTs with the insufficient quantities of dataset.
Objectives: Dynamic susceptibility contrast perfusion weighted imaging (DSC-PWI) plays an important role in the differential diagnosis between radionecrosis and recurrence of brain metastases (BMs) after gamma knife radiosurgery (GKRS). While the perfusion condition of preliminary hyperperfusion and hypoperfusion BMs when recur has not been studied, as well the separating performance of quantitative DSC-PWI in both kinds of BMs.Methods: From February 2017 to October 2019, quantitative DSC-PWI was performed in patients with untreated BMs in this observational study. Patients were assigned to hyperperfusion and hypoperfusion group according the quantitative cerebral blood volume (qCBV). During follow-up after GKRS, patients with a diagnostic pitfall of radionecrosis and recurrence accepted second quantitative DSC-PWI. Final diagnosis was based on the histological results or follow-up results. Receiver operating curve analysis was used to explore the performance of qCBV.Results: Twenty-nine patients (mean age: 61.3 ± 9.4 years old; male/female: 13/16) were assigned to the group of hypoperfusion group, and 26 patients (mean age: 58 ± 10.4 years old; male/female: 14/12) to hyperperfusion group. The mean qCBV values between hypoperfusion and hyperperfusion groups when recurred were not significantly different (3.17 ± 0.53 ml/100 g vs. 3.27 ± 0.47 ml/100 g, p = 0.63). qCBV was feasible to separate radionecrosis and recurrence in both groups (AUC=0.94 and AUC=0.93, separately).Conclusion: Both premilitary hyperperfusion and hypoperfusion BMs would transform to a high microvascular density when recurs. qCBV is feasible to distinguish radionecrosis and recurrence among both kinds of BMs after GKRS.
This study aims to refine a radiomics-based diagnostic approach for detecting neonatal respiratory distress syndrome (NRDS) and examines the influence of rib suppression on the diagnostic precision of radiomics models using neonatal chest X-ray (CXR) images. A total of 138 CXR images were collected in this study. The data was partitioned into training and validation subsets based on chronological order. We applied rib suppression to the CXR images and extracted and analyzed radiomic features from lung regions both before and after rib suppression. This approach was designed to identify NRDS, develop radiomics models, and assess the impact of rib suppression on model performance. To establish these radiomics models, six machine learning models were utilized in the study. The performance was evaluated using the area under the receiver operating characteristic curve (AUC). On the validation set, the models demonstrated significant improvements after rib suppression. Specifically, the Gradient Boosting Machine (GBM) achieved an AUC of 0.781 post-suppression compared to 0.556 pre-suppression. Notably, Linear Discriminant Analysis (LDA) and Logistic Regression (LR) performed particularly well when combining features from both scenarios, achieving AUCs of 0.762 and 0.756. The results indicate the feasibility of developing radiomics models for diagnosing NRDS and highlight the enhancement in model performance due to rib suppression. This study provides a promising new method for the imaging diagnosis and prognosis evaluation of neonatal respiratory distress syndrome, showcasing the potential of radiomics in pediatric imaging.