Background: Early-stage diagnosis and treatment can improve survival rates of liver cancer patients. Dynamic contrast-enhanced MRI provides the most comprehensive information for differential diagnosis of liver tumors. However, MRI diagnosis is affected by subjective experience, so deep learning may supply a new diagnostic strategy. We used convolutional neural networks (CNNs) to develop a deep learning system (DLS) to classify liver tumors based on enhanced MR images, unenhanced MR images, and clinical data including text and laboratory test results. Methods: Using data from 1,210 patients with liver tumors (N = 31,608 images), we trained CNNs to get seven-way classifiers, binary classifiers, and three-way malignancyclassifiers (Model A-Model G). Models were validated in an external independent extended cohort of 201 patients (N = 6,816 images). The area under receiver operating characteristic (ROC) curve (AUC) were compared across different models. We also compared the sensitivity and specificity of models with the performance of three experienced radiologists. Results: Deep learning achieves a performance on par with three experienced radiologists on classifying liver tumors in seven categories. Using only unenhanced images, CNN performs well in distinguishing malignant from benign liver tumors (AUC, 0.946; 95% CI 0.914-0.979 vs. 0.951; 0.919-0.982, P = 0.664). New CNN combining unenhanced images with clinical data greatly improved the performance of classifying malignancies as hepatocellular carcinoma (AUC, 0.985; 95% CI 0.960-1.000), metastatic tumors (0.998; 0.989-1.000), and other primary malignancies (0.963; 0.896-1.000), and the agreement with pathology was 91.9%.These models mined diagnostic information in unenhanced images and clinical data by deepneural-network, which were different to previous methods that utilized enhanced images. The sensitivity and specificity of almost every category in these models reached the same high level compared to three experienced radiologists. Zhen et al. Deep Learning for Liver Tumor Diagnosis Conclusion: Trained with data in various acquisition conditions, DLS that integrated these models could be used as an accurate and time-saving assisted-diagnostic strategy for liver tumors in clinical settings, even in the absence of contrast agents. DLS therefore has the potential to avoid contrast-related side effects and reduce economic costs associated with current standard MRI inspection practices for liver tumor patients.

No abstract

No abstract

High total dissolved gas (TDG) levels and excessive suspended sediment (SS) concentrations pose serious threats to fish survival during flood season. However, little information is available on the effects of TDG supersaturation with varying SS concentrations on fish. In this study, laboratory experiments were performed to investigate the effects of TDG supersaturation with varying SS concentrations on five-month-old river sturgeons (Acipenser dabryanus). The test fish were exposed to combinations of SS concentrations (0, 200, 600 and 1,000 mg/L) and TDG levels (125, 130, 135 and 140%), and their mortality and median lethal time (LT50) were quantified. The fish showed abnormal behaviors (e.g., quick breathing, fast swimming and an agitated escape response) and symptoms of gas bubble disease (GBD). SS increased the mortality of river sturgeon exposed to TDG supersaturation. Furthermore, the LT50 values at 125% TDG were 4.47, 3.11, 3.07 and 2.68 h for the different SS concentrations (0, 200, 600 and 1,000 mg/L, respectively), representing a significant decrease in LT50 with increasing SS. However, at higher TDG levels (130–140%), there was no significant increase in LT50 with increasing SS. Therefore, river sturgeon showed weak tolerance of TDG-supersaturated water with SS.