Deep-learning-based analysis of preoperative MRI predicts microvascular invasion and outcome in hepatocellular carcinoma.

BACKGROUND: Preoperative prediction of microvascular invasion (MVI) is critical for treatment strategy making in patients with hepatocellular carcinoma (HCC). We aimed to develop a deep learning (DL) model based on preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict the MVI status and clinical outcomes in patients with HCC. METHODS: We retrospectively included a total of 321 HCC patients with pathologically confirmed MVI status. Preoperative DCE-MRI of these patients were collected, annotated, and further analyzed by DL in this study. A predictive model for MVI integrating DL-predicted MVI status (DL-MVI) and clinical parameters was constructed with multivariate logistic regression. RESULTS: Of 321 HCC patients, 136 patients were pathologically MVI absent and 185 patients were MVI present. Recurrence-free survival (RFS) and overall survival (OS) were significantly different between the DL-predicted MVI-absent and MVI-present. Among all clinical variables, only DL-predicted MVI status and a-fetoprotein (AFP) were independently associated with MVI: DL-MVI (odds ratio [OR] = 35.738; 95% confidence interval [CI] 14.027-91.056; p < 0.001), AFP (OR = 4.634, 95% CI 2.576-8.336; p < 0.001). To predict the presence of MVI, DL-MVI combined with AFP achieved an area under the curve (AUC) of 0.824. CONCLUSIONS: Our predictive model combining DL-MVI and AFP achieved good performance for predicting MVI and clinical outcomes in patients with HCC.

Experimental investigation of the reliability issue of RRAM based on high resistance state conduction.

In this paper, reliability issues of robust HfO(x)-based RRAM are experimentally investigated in terms of cycling ageing, temperature impact and voltage acceleration. All reliability issues can be estimated by the conduction of the high resistance state (HRS). The conduction current of the HRS exponentially increases as the square root of the applied voltage, which is well explained by 'quasi-Poole-Frenkel-type' trap assistant tunneling. Further experiments on HRS conduction at different temperatures show that the depth of the potential well of the trap in HfO(x) film is about 0.31 eV. The degradation induced by the cycling ageing is possibly ascribed to the increase of the amount of oxygen ions in the TiO(x) layer of the TiN/TiO(x)/HfO(x)/TiN device. The retention times with various stress voltages at different temperatures also exhibit an exponential relationship to the square root of the applied voltage, indicating that stress current plays a dominant role for the degradation of the HRS. An oxygen-release model is proposed to explain the relationship of retention time to HRS conduction current.