Search

Synthetic digital mammography (SDM), a 2D image generated from digital breast tomosynthesis (DBT), is used as a potential substitute for full-field digital mammography (FFDM) in clinic to reduce the radiation dose for breast cancer screening. Previous studies exploited projection geometry and fused projection data and DBT volume, with different post-processing techniques applied on re-projection data which may generate different image appearance compared to FFDM. To alleviate this issue, one possible solution to generate an SDM image is using a learning-based method to model the transformation from the DBT volume to the FFDM image using current DBT/FFDM combo images. In this study, we proposed to use a deep convolutional neural network (DCNN) to learn the transformation to generate SDM using current DBT/FFDM combo images. Gradient guided conditional generative adversarial networks (GGGAN) objective function was designed to preserve subtle MCs and the perceptual loss was exploited to improve the performance of the proposed DCNN on perceptual quality. We used various image quality criteria for evaluation, including preserving masses and MCs which are important in mammogram. Experiment results demonstrated progressive performance improvement of network using different objective functions in terms of those image quality criteria. The methodology we exploited in the SDM generation task to analyze and progressively improve image quality by designing objective functions may be helpful to other image generation tasks.

Background: Computer-aided diagnosis (CAD) system can provide reference to radiologists in breast mass classification. This study was to verify if a CAD model, based on perceptive features learned from quantitative BI-RADS descriptions, can help radiologists improve diagnosis performance for breast masses in mammography.Methods: A retrospective multi-reader multi-case (MRMC) study was conducted to evaluate a CAD model established on perceptive features. Digital mammograms of 416 patients with breast masses were collected from 2014 to 2017, including 231 benign and 185 malignant masses. Altogether, 214 of them (109 benign, 105 malignant) were selected randomly to train the CAD model which consisted of perceptive feature extractor and classifier. The other 202 patients were used as the test set for evaluation from which 51 patients (29 benign and 22 malignant) were selected. Six radiologists were divided into three groups (junior, middle-senior, and senior).They evaluated 51 patients without and with support from the CAD model. BI-RADS category, benign or malignant diagnosis, probability of malignancy, and diagnosis time were recorded during two evaluation sessions. Results: In the MRMC evaluation, the average AUC of six radiologists with CAD support was significantly higher than that without support (0.896 vs. 0.850, p=0.02). Both of average sensitivity and average specificity increased (p = 0.0253). More cases were assessed as BI-RADS 4 than BI-RADS 2 or 3. Five radiologists showed comparable diagnosis time per case with and without CAD support, and one radiologist showed a significant decrease when the CAD model was involved. Conclusion: The CAD model could improve radiologists’ diagnostic performance for breast masses without improving the diagnosis time.

Architectural distortion (AD) is one of the breast abnormal signs in medical imaging and it is hard to be detected in clinic because of its subtle appearance and similar intensity with surrounding tissues. We previously developed a deep-learning-based model for AD detection in digital breast tomosynthesis (DBT). However, for atypical ADs, the model’s detection performance was not good enough because atypical ADs do not have a radial pattern, which is the main characteristic of AD. Considering that radiologists always take surrounding tissues’ information as reference to locate atypical ADs, an ideal model should not only adapt to the different shape of atypical ADs, but also have a large receptive field. In this study, deformable convolution kernel was employed to establish a novel deep-learning-based AD detection model. A dataset of 265 DBT volumes including 64 typical ADs, 74 atypical ADs and 127 normal volumes were collected for model evaluation. Mean true positive fraction (MTPF) was used as figure-of-merit. The results of six-fold cross-validation showed that after involving deformable convolution, the MTPF improved from 0.53±0.04 to 0.56±0.04 (p=0.028) and the number of false positives (FPs) at 80% sensitivity reduced from 1.95 to 1.09. Especially for atypical AD, the MTPF improved from 0.45±0.05 to 0.51±0.04 (p=0.01) and the number of FPs at 80% sensitivity reduced from 4.79 to 1.51. These results showed that this model has potential to assist radiologists locate more suspicious ADs and improve their diagnosis efficiency.

Aiming at the problem that the frequency offset in the non-cooperative communication system causes the received signal spectrum to shift, which exceeds the passband of the matched filter and affects the subsequent demodulation, a parameter estimation and signal detection algorithm based on adaptive capture is proposed by this paper, which is more convenient for hardware implementation and consumes less resources. The algorithm is divided into three parts. Firstly, use the correlation value between the signal and the preamble sequence as the basis for frequency capture. Secondly, the frequency is accurately estimated based on the interpolation algorithm. Finally, the phase-locked loop structure is used to track the frequency according to the characteristics of the frequency gradually changing and the signal frequency offset is eliminated in the Digital Down Converter stage. It provides necessary conditions for accurate signal detection and phase estimation. The simulation results show that the algorithm has high estimation accuracy, wide esti-mation range and low complexity. It can also achieve better estimation accuracy and detection performance under low signal-to-noise ratio.

Anomaly detection is a critical task for maintaining the performance of a cloud system. Using data-driven methods to address this issue is the mainstream in recent years. However, due to the lack of labeled data for training in practice, it is necessary to enable an anomaly detection model trained on contaminated data in an unsupervised way. Besides, with the increasing complexity of cloud systems, effectively organizing data collected from a wide range of components of a system and modeling spatiotemporal dependence among them become a challenge. In this article, we propose TopoMAD, a stochastic seq2seq model which can robustly model spatial and temporal dependence among contaminated data. We include system topological information to organize metrics from different components and apply sliding windows over metrics collected continuously to capture the temporal dependence. We extract spatial features with the help of graph neural networks and temporal features with long short-term memory networks. Moreover, we develop our model based on variational auto-encoder, enabling it to work well robustly even when trained on contaminated data. Our approach is validated on the run-time performance data collected from two representative cloud systems, namely, a big data batch processing system and a microservice-based transaction processing system. The experimental results show that TopoMAD outperforms some state-of-the-art methods on these two data sets.

Log-based anomaly detection has been widely studied and achieves a satisfying performance on stable log data. But, the existing approaches still fall short meeting these challenges: 1) Log formats are changing continually in practice in those software systems under active development and maintenance. 2) Performance issues are latent causes that may not be detected by trivial monitoring tools. We thus propose SwissLog, namely a robust and unified deep learning based anomaly detection model for detecting diverse faults. SwissLog targets at those faults resulting in log sequence order changes and log time interval changes. To achieve that, an advanced log parser is introduced. Moreover, the semantic embedding and the time embedding approaches are combined to train a unified attention based BiLSTM model to detect anomalies. The experiments on real-world datasets and synthetic datasets show that SwissLog is robust to the changing log data and effective for diverse faults.

Architectural distortion (AD) is one of the most important potentially ominous signs of breast cancer. As a 3D imaging, digital breast tomosynthesis (DBT) is an accurate tool to detect AD. We developed a deep learning approach for AD detection guided by mammary gland spatial pattern (MGSP) in DBT. The approach consists of two stages: 2D detection and 3D aggregation. In 2D detection, prior MGSP information is obtained first. It includes 1) magnitude image and orientation field map produced from Gabor filters and 2) mammary gland convergence map. Second, Faster-RCNN detection network is employed. Region proposal network extracts features and determines locations of AD candidates and the soft classifier is used for reducing false positives. In 3D aggregation, a region fusion strategy is designed to fuse 2D candidates into 3D candidates. For evaluation, 265 DBT volumes (138 with ADs and 127 without any lesion) were collected from 68 patients. Free response receiver operating characteristic curve was obtained and the mean true positive fraction (MTPF) was used as the figure-of-merit of model performance. Compared with a baseline model based on convergence measure, the six-fold cross validation results showed that our proposed approach achieved MTPF of 0.50 ± 0.04, while the baseline achieved 0.37 ± 0.03. The improvement of our approach was statistically significant (p≪0.001).

Background and Objective Simulation of diverse lesions in images is proposed and applied to overcome the scarcity of labeled data, which has hindered the application of deep learning in medical imaging. However, most of current studies focus on generating samples with class labels for classification and detection rather than segmentation, because generating images with precise masks remains a challenge. Therefore, we aim to generate realistic medical images with precise masks for improving lesion segmentation in mammagrams. Methods In this paper, we propose a new framework for improving X-ray breast mass segmentation performance aided by generated adversarial lesion images with precise masks. Firstly, we introduce a conditional generative adversarial network (cGAN) to learn the distribution of real mass images as well as a mapping between images and corresponding segmentation masks. Subsequently, a number of lesion images are generated from various binary input masks using the generator in the trained cGAN. Then the generated adversarial samples are concatenated with original samples to produce a dataset with increased diversity. Furthermore, we introduce an improved U-net and train it on the previous augmented dataset for breast mass segmentation. Results To demonstrate the effectiveness of our proposed method, we conduct experiments on publicly available mammogram database of INbreast and a private database provided by Nanfang Hospital in China. Experimental results show that an improvement up to 7% in Jaccard index can be achieved over the same model trained on original real lesion images. Conclusions Our proposed method can be viewed as one of the first steps toward generating realistic X-ray breast mass images with masks for precise segmentation.

Computer aided detection (CADe) for breast lesions can provide an important reference for radiologists in breast cancer screening. Architectural distortion (AD) is a type of breast lesion that is difficult to detect. A majority of CADe methods focus on detecting the radial pattern, which is a main characteristic of typical ADs. However, a few atypical ADs do not exhibit such a pattern. To improve the performance of CADe for typical and atypical ADs, we propose a deep-learning-based model that used mammary gland distribution as prior information to detect ADs in digital breast tomosynthesis (DBT). First, information about gland distribution, including the Gabor magnitude, the Gabor orientation field, and a convergence map, were produced using a bank of Gabor filters and convergence measures. Then, this prior information and an original slice were input into a Faster R-CNN detection network to obtain the 2-D candidates for each slice. Finally, a 3-D aggregation scheme was employed to fuse these 2-D candidates as 3-D candidates for each DBT volume. Retrospectively, 64 typical AD volumes, 74 atypical AD volumes, and 127 normal volumes were collected. Six-fold cross-validation and mean true positive fraction (MTPF) were used to evaluate the model. Compared to an existing convergence-based model, our proposed model achieved an MTPF of 0.53 ± 0.04, 0.61 ± 0.05, and 0.45 ± 0.04 for all DBT volumes, typical + normal volumes, and atypical + normal volumes, respectively. These results were significantly better than those of 0.36 ± 0.03, 0.46 ± 0.04, and 0.28 ± 0.04 for a convergence-based model (p ≪ 0.01). These results indicate that employing the prior information of gland distribution and a deep learning method can improve the performance of CADe for AD.

This paper mainly introduces automatic driving schemes and algorithms for formula racing car. Formula racing is a good platform for testing the extreme performance of vehicles, but there is a risk of harming the drivers. We propose an automatic driving scheme to avoid such problems. The solution we proposed integrates three modules: environment perception, path planning and vehicle control. Using lidar, camera and GPS/INS integrated navigation as sensors, an innovative data fusion method is proposed. This paper proposes a new path planning method, which uses Delaunay triangulation and topological map-based path search and evaluation to obtain the best path. Finally, a control model based on pure pursuit algorithm is used to control the vehicle precisely. The whole system is developed based on ROS which has a unique loose coupling. This scheme is proved to have high accuracy and good robustness by simulation analysis and multiple vehicle tests. The proposed solution has good portability, and it can also be applied to the field of unmanned passenger cars, robots and drones after appropriate modifications.

We demonstrate flexible multidimensional modulation formats, polarization multiplexed k-symbol check quadrature phase shift keying (PM-kSC-QPSK), based on PM-QPSK constellations for elastic optical networks. The experimental results show a significant optical signal noise ratio (OSNR) tolerance improvement for PM-2SC-QPSK and PM-4SC-QPSK over PM-QPSK in both back-to-back and 500 km transmission scenarios at the expense of spectral efficiency reduction. This flexible modulation method can be used in elastic optical networks to provide a trade-off between the spectral efficiency and OSNR tolerance.

We demonstrate a flexible multi-dimensional modulation method for elastic optical networks. We compare the flexible multi-dimensional modulation formats PM-kSC-mQAM with traditional modulation formats PM-mQAM using numerical simulations in back-to-back and wavelength division multiplexed (WDM) transmission (50 GHz-spaced) scenarios at the same symbol rate of 32 Gbaud. The simulation results show that PM-kSC-QPSK and PM-kSC-16QAM can achieve obvious back-to-back sensitivity gain with respect to PM-QPSK and PM-16QAM at the expense of spectral efficiency reduction. And the WDM transmission simulation results show that PM-2SC-QPSK can achieve 57.5% increase in transmission reach compared to PM-QPSK, and 48.5% increase for PM-2SC-16QAM over PM-16QAM. Furthermore, we also experimentally investigate the back to back performance of PM-2SC-QPSK, PM-4SC-QPSK, PM-2SC-16QAM and PM-3SC-16QAM, and the experimental results agree well with the numerical simulations.

We propose an 8-dimensional modulation format based on polarization multiplexed squared 16-QAM constellations. We compare 8D-16QAM, 128-SP-QAM and PM-16QAM using numerical simulations in WDM transmission scenarios at the same baud rates and net bit rates.

A new Byte-Interleaver with low complexity is proposed to eliminate correlation of errors in OTUk signals. By using the Byte-Interleaver as Error-Decorrelator, the resistance of GFEC to correlated errors in OTUk signals is improved.

This paper propose an object recognition method based on template match that uses both gradient and LBP feature as the template feature. We also design a binary representation and quick bitwise operation for the proposed approach.