Non-contrast CT radiomics-clinical machine learning model for futile recanalization after endovascular treatment in anterior circulation acute ischemic stroke.

OBJECTIVE: To establish a machine learning model based on radiomics and clinical features derived from non-contrast CT to predict futile recanalization (FR) in patients with anterior circulation acute ischemic stroke (AIS) undergoing endovascular treatment. METHODS: A retrospective analysis was conducted on 174 patients who underwent endovascular treatment for acute anterior circulation ischemic stroke between January 2020 and December 2023. FR was defined as successful recanalization but poor prognosis at 90 days (modified Rankin Scale, mRS 4-6). Radiomic features were extracted from non-contrast CT and selected using the least absolute shrinkage and selection operator (LASSO) regression method. Logistic regression (LR) model was used to build models based on radiomic and clinical features. A radiomics-clinical nomogram model was developed, and the predictive performance of the models was evaluated using area under the curve (AUC), accuracy, sensitivity, and specificity. RESULTS: A total of 174 patients were included. 2016 radiomic features were extracted from non-contrast CT, and 9 features were selected to build the radiomics model. Univariate and stepwise multivariate analyses identified admission NIHSS score, hemorrhagic transformation, NLR, and admission blood glucose as independent factors for building the clinical model. The AUC of the radiomics-clinical nomogram model in the training and testing cohorts were 0.860 (95%CI 0.801-0.919) and 0.775 (95%CI 0.605-0.945), respectively. CONCLUSION: The radiomics-clinical nomogram model based on non-contrast CT demonstrated satisfactory performance in predicting futile recanalization in patients with anterior circulation acute ischemic stroke.

Independent dual-single-sideband QPSK signal detection based on a single photodetector.

The two sidebands of the independent dual-single-sideband (dual-SSB) signal can carry different information to achieve higher spectral efficiency. However, the two sidebands of the independent dual-SSB vector signal are received independently. Generally, the receiver divides the signal into two channels. For each channel, we use an optical bandpass filter (OBPF) to select the left sideband (LSB) or right sideband (RSB), respectively. Then a photodetector (PD) is used for photoelectric conversion, followed by subsequent digital signal processing (DSP). To reduce the complexity and cost of the receiver, we propose a new independent dual-SSB vector signal detection scheme based on a single PD combined with conventional DSP. An electric bandpass filter (EBPF) filters out high-frequency components after photoelectric conversion, and then the signal is quadrature demodulated and processed by the DSP algorithm. The LSB and RSB are quadrature phase-shift keying (QPSK) modulated with an initial phase difference of π/4. Simulation results show that the proposed scheme performs better bit error rate (BER). For back-to-back (BTB) transmission, the BER of 2-Gbaud independent dual-SSB vector signal (1-Gbuad RSB and 1-Gbaud LSB) can reach the hard-decision forward error correction (HD-FEC) threshold of 3.8 × 10-3 when the input optical power into PD is -20 dBm. For 1-km and 2-km weak turbulence free-space optical (FSO) channel transmission, the BER of 2-Gbaud independent dual-SSB vector signal can reach the HD-FEC threshold when the input optical power into PD is -18.8 and -17 dBm, respectively. For 1-km weak turbulence FSO channel transmission, the BER of 4-, 8-, and 16-Gbuad independent dual-SSB vector signal can reach the HD-FEC threshold when the input optical power into PD is -17.8, -16, and -15 dBm, respectively.