Search

IntroductionBrain medical image segmentation is a critical task in medical image processing, playing a significant role in the prediction and diagnosis of diseases such as stroke, Alzheimer's disease, and brain tumors. However, substantial distribution discrepancies among datasets from different sources arise due to the large inter-site discrepancy among different scanners, imaging protocols, and populations. This leads to cross-domain problems in practical applications. In recent years, numerous studies have been conducted to address the cross-domain problem in brain image segmentation.MethodsThis review adheres to the standards of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) for data processing and analysis. We retrieved relevant papers from PubMed, Web of Science, and IEEE databases from January 2018 to December 2023, extracting information about the medical domain, imaging modalities, methods for addressing cross-domain issues, experimental designs, and datasets from the selected papers. Moreover, we compared the performance of methods in stroke lesion segmentation, white matter segmentation and brain tumor segmentation.ResultsA total of 71 studies were included and analyzed in this review. The methods for tackling the cross-domain problem include Transfer Learning, Normalization, Unsupervised Learning, Transformer models, and Convolutional Neural Networks (CNNs). On the ATLAS dataset, domain-adaptive methods showed an overall improvement of ~3 percent in stroke lesion segmentation tasks compared to non-adaptive methods. However, given the diversity of datasets and experimental methodologies in current studies based on the methods for white matter segmentation tasks in MICCAI 2017 and those for brain tumor segmentation tasks in BraTS, it is challenging to intuitively compare the strengths and weaknesses of these methods.ConclusionAlthough various techniques have been applied to address the cross-domain problem in brain image segmentation, there is currently a lack of unified dataset collections and experimental standards. For instance, many studies are still based on n-fold cross-validation, while methods directly based on cross-validation across sites or datasets are relatively scarce. Furthermore, due to the diverse types of medical images in the field of brain segmentation, it is not straightforward to make simple and intuitive comparisons of performance. These challenges need to be addressed in future research.

A new photonic scheme is proposed for the generation of a frequency 16-tupling millimeter wave (mm-wave) signal, based on four cascaded polarization modulators (PolMs). Firstly, through the precise control of these four PolMs, odd harmonics can be effectively suppressed sequentially. Next, combined with the modulation index of the PolMs, only the pure ± 8th-order optical harmonics are retained and enter the photodetector to beat the frequency. After multiple rounds of detailed, mathematical formula derivation and computer simulation, the accuracy and advantages of the proposed solution can be demonstrated. As a result, a 160 GHz mm-wave signal is obtained, which is produced from a 10 GHz radio frequency (RF) signal. By properly setting the modulation index and the angle of three phase differences, the optical suppression ratio (OSSR) and the radio frequency suppression ratio (RFSSR) of the acquired signal are 64.21 dB and 60.99 dB, respectively. Further, the impact of the variables on the OSSR and the RFSSR are analyzed and discussed. [ABSTRACT FROM AUTHOR]

Many types of objects are crowdedly distributed on the surface of remote sensing scenes. Global semantics with object mixture and small training samples potentially cause difficulties in the classification of remote sensing scenes. The description of them often requires crucial parts of the scenes and corresponding discriminative features, especially as the convolutional neural network (CNN) goes deeper. In this paper, we propose a novel Location-Aware Multi-code Generator network (LAM-GAN) that incorporates multiple latent codes as the input to a generator network. This network is designed to train from scratch and recover most details of the input (real) image in a principled way. Meanwhile, multiple latent codes are reversely updated using K cluster centres located by the subsequently proposed part co-location module. By doing so, the global features of the real-fake image pair and part-level features are stacked and fed to a joint part classification network for discriminative classification. This approach makes it easier to induce the semantic concepts in a remote sensing scene. With this formulation, our approach generates an internal compact representation of the scene and enables weakly supervised part co-localization. The proposed method provides a unified framework for not only generating high-quality fake images but also facilitating the remote sensing scene classification task. We evaluated LAM-GAN on several benchmark datasets, and the experiment results demonstrate that the proposed method is more effective than previous state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Global Navigation Satellite System(GNSS) is of great significance for anti-interference research. The signal acquisition of anti-interference technology based on antenna array needs multiplex signals, which is difficult for the general signal channel Radio Frequency(RF) front-end. The system was designed for the GPS anti-jamming RF front-end of four-element antenna array. The system received four channels of GPS signals through the four-element antenna array. After the processing of a low noise amplifier, RF filters ,RF chip of GP2015 and down-conversion, the received GPS signals was transformed into the intermediate frequency signal, which was supplied to the A/D sampling behind. Besides, the sampling data was sent to anti-jamming modules to realize anti-jamming. Device selection for each unit is described in detail. Finally, the RF front-end of the whole circuit was justified. The feasibility of the system is verified by practical application.

This paper proposes a novel key distribution method based on the masking effect of fiber channel noise in a power transmission system. The two physical layer signal processing technologies used in this solution are frame synchronization and resampling. The random data sent and received is digitally processed by these two techniques. An experimental platform is built, and the key performance is assessed by analyzing the measured bit error rate (BER) dynamic curve, setting different decision thresholds and the amplitude of the state basis. Experimental results show that the key distribution rate can reach 10 kbit/s with a key consistency rate of 98%. This is of great significance to the development of safe optical communication technology in power transmission systems. In the power communication system, a large number of optical fiber communication devices are used. The key distribution method proposed in this paper can effectively improve the security of optical fiber communication, which is of great significance. [ABSTRACT FROM AUTHOR]