Currently, several convolutional neural network (CNN)-based methods have been proposed for computer-aided COVID-19 diagnosis based on lung computed tomography (CT) scans. However, the lesions of pneumonia in CT scans have wide variations in appearances, sizes, and locations in the lung regions, and the manifestations of COVID-19 in CT scans are also similar to other types of viral pneumonia, which hinders the further improvement of CNN-based methods. Delineating infection regions manually is a solution to this issue, while excessive workload of physicians during the epidemic makes it difficult for manual delineation. In this article, we propose a CNN called dense connectivity network with parallel attention module (PAM-DenseNet), which can perform well on coarse labels without manually delineated infection regions. The parallel attention module automatically learns to strengthen informative features from both channelwise and spatialwise simultaneously, which can make the network pay more attention to the infection regions without any manual delineation. The dense connectivity structure performs feature maps reuse by introducing direct connections from previous layers to all subsequent layers, which can extract representative features from fewer CT slices. The proposed network is first trained on 3530 lung CT slices selected from 382 COVID-19 lung CT scans, 372 lung CT scans infected by other pneumonia, and 200 normal lung CT scans to obtain a pretrained model for slicewise prediction. We then apply this pretrained model to a CT scans dataset containing 94 COVID-19 CT scans, 93 other pneumonia CT scans, and 93 normal lung scans, and achieve patientwise prediction through a voting mechanism. The experimental results show that the proposed network achieves promising results with an accuracy of 94.29%, a precision of 93.75%, a sensitivity of 95.74%, and a specificity of 96.77%, which is comparable to the methods that are based on manually delineated infection regions.

To overcome the contradiction between wide swath and high resolution in synthetic aperture radar systems, a multichannel azimuth reconstruction method is investigated to unambiguously recover the Doppler spectrum. The proposed method is derived from the least squares principle by exploiting a Vandermonde component of the system matrix. The Vandermonde matrix is Doppler independent and data independent. Reconstruction filter weightings can be easily achieved, and performance, including signal-to-noise ratio (SNR) and azimuth ambiguity-to-signal ratio, can be explicitly expressed. By well-conditioning the Vandermonde matrix and coherent processing of all channels, the proposed method improves the reconstruction performance. In simulated reconstruction, compared with the conventional matrix inversion method, the SNR increases by approximately 30 dB.

A new cross-channel interference suppression method based on the fractional Fourier transform (FRFT) is proposed to eliminate the effect due to cross-channel interference when a full-polarimetric radar adopts the opposite-slope linear frequency modulation transmit signals and de-ramping processing in the simultaneous measurement mode. The FRFT with an appropriate order is operated on the signals in the cross-interference interval. Such order is obtained via the calculation of the frequency-modulation slope of transmitted signals. The cross-channel interference is changed into sinc functions that are detected by a designed threshold and filtered out in the FRFT domain to suppress the cross-channel interference. The simulations show that the proposed method can obviously reduce the peak sidelobe levels and the integrated sidelobe levels of targets in range profiles compared with the traditional method, which is benefit to improve the detection and measurement performances of weak polarimetric scattering components. The proposed method is suitable for stable or slow-moving targets.

An extraction method of the polarimetric atmospheric target has been proposed to obtain most useful information with noise, clutter and artificial signals as less as possible for dual- orthogonal frequency modulation continuous wave (FMCW) polarimetric radar. The signal processing is described for dual- orthogonal FMCW polarimetric radar. The polarimetric range- Doppler spectra of precipitation obtained in a single sweep time are calibrated by radar constant calibration and reciprocity modification. The mask matrix for filtering is constructed based on the double spectral linear depolarization ratios (sLdr) and mathematical morphology methods. The precipitation atmospheric targets are extracted successfully by multiplying the mask matrix with the measured range-Doppler spectra by the polarimetric agile radar SAnd X-band (PARSAX) radar. The proposed technique keeps more atmospheric targets and suppresses more clutter, noise and artificial signals compared with the original data and the data after double sLdr filtering combined with noise clipping.