A weakly supervised deep learning model integrating noncontrasted computed tomography images and clinical factors facilitates haemorrhagic transformation prediction after intravenous thrombolysis in acute ischaemic stroke patients.

BACKGROUND: Haemorrhage transformation (HT) is a serious complication of intravenous thrombolysis (IVT) in acute ischaemic stroke (AIS). Accurate and timely prediction of the risk of HT before IVT may change the treatment decision and improve clinical prognosis. We aimed to develop a deep learning method for predicting HT after IVT for AIS using noncontrast computed tomography (NCCT) images. METHODS: We retrospectively collected data from 828 AIS patients undergoing recombinant tissue plasminogen activator (rt-PA) treatment within a 4.5-h time window (n = 665) or of undergoing urokinase treatment within a 6-h time window (n = 163) and divided them into the HT group (n = 69) and non-HT group (n = 759). HT was defined based on the criteria of the European Cooperative Acute Stroke Study-II trial. To address the problems of indiscernible features and imbalanced data, a weakly supervised deep learning (WSDL) model for HT prediction was constructed based on multiple instance learning and active learning using admission NCCT images and clinical information in addition to conventional deep learning models. Threefold cross-validation and transfer learning were performed to confirm the robustness of the network. Of note, the predictive value of the commonly used scales in clinics associated with NCCT images (i.e., the HAT and SEDAN score) was also analysed and compared to measure the feasibility of our proposed DL algorithms. RESULTS: Compared to the conventional DL and ML models, the WSDL model had the highest AUC of 0.799 (95% CI 0.712-0.883). Significant differences were observed between the WSDL model and five ML models (P < 0.05). The prediction performance of the WSDL model outperforms the HAT and SEDAN scores at the optimal operating point (threshold = 1.5). Further subgroup analysis showed that the WSDL model performed better for symptomatic intracranial haemorrhage (AUC = 0.833, F1 score = 0.909). CONCLUSIONS: Our WSDL model based on NCCT images had relatively good performance for predicting HT in AIS and may be suitable for assisting in clinical treatment decision-making.

Identification of benign and malignant pulmonary nodules on chest CT using improved 3D U-Net deep learning framework.

PURPOSE: To accurately distinguish benign from malignant pulmonary nodules with CT based on partial structures of 3D U-Net integrated with Capsule Networks (CapNets) and provide a reference for the early diagnosis of lung cancer. METHOD: The dataset consisted of 1177 samples (benign/malignant: 414/763) from 997 patients provided by collaborating hospital. All nodules were biopsy or surgery proven, and pathologic results were regarded as the "golden standard". This study utilized partial U-Net to capture the low-level (edge, corner, etc.) information and CapNets to preserve high-level (semantic information) information of nodules. For CapNets, each capsule had a 4 × 4 matrix representing the pose and an activation probability representing the presence of an object. Furthermore, we chose accuracy (ACC), area under the curve (AUC), sensitivity (SE) and specificity (SP) to evaluate the generalization of the proposed architecture and compared its identification performance with 3D U-Net and experienced radiologists. RESULTS: The AUC of our architecture (0.84) was superior to that (0.81) of the original 3D U-Net (p = 0.04, DeLong's test). Moreover, ACC (84.5 %) and SE (92.9 %) of our model were clearly higher than radiologists' ACC (81.0 %) and SE (84.3 %) at the optimal operating point. However, SP (70 %) of our model was slightly lower than radiologists' SP (75 %), which might be the result of class imbalance with limited benign samples involved for algorithm training. CONCLUSIONS: Our architecture showed a high performance for identifying benign and malignant pulmonary nodules, indicating the improved model has a promising application in clinic.

Two nomograms based on CT features to predict tumor invasiveness of pulmonary adenocarcinoma and growth in pure GGN: a retrospective analysis.

PURPOSE: The aim of the study is to construct two nomograms for predicting the invasive extent of pulmonary adenocarcinoma and nodule growth in patients with pulmonary pure ground-glass nodules (pGGN). METHOD: Consecutive patients with pGGNs (n = 172) were retrospectively studied at one institution, formed the development cohort in predicting IPAs' nomogram. A separate cohort of patients with pGGNs (n = 116) from another institution was used for validation. For the predicting growth nomogram, the primary cohort of patients with pGGNs (n = 80) was from the former institution. We developed the nomogram for predicting IPA using binary logistic regression model, and a Cox multivariable model for the growth nomogram. We assessed nomogram model performance by calibration and discrimination (C-index). RESULTS: The variables selected in binary logistic regression model (lesion size and shape) had a significant effect on identifying IPA from preinvasive lesion. The C-index of the development and validation cohort were 0.819 (95% CI 0.753-0.874) and 0.811 (95% CI 0.728-0.878), respectively. The risk variables (lesion size, blood vessel types) were selected in the multivariable Cox model. The C-index was 0.880 in the development cohort. CONCLUSION: Our nomograms are reliable prognostic methods that can predict the invasiveness of pulmonary adenocarcinomas and the growth of pure GGN in preoperative.