Quantifying full left ventricular (LV) metrics including cavity area, myocardium area, cavity dimensions and wall thicknesses from cardiac magnetic resonance (MR) images and then assessing regional and global cardiac function plays a crucial role in clinical practice. However, due to highly variable cardiac structures across different subjects, it is challenging to obtain accurate estimation of LV metrics. In this paper, we propose a novel deep learning framework, called Cascaded Segmentation and Regression Network (CSRNet), to improve the quantification results. The CSRNet consists of two components: segmentation component and regression component. The segmentation component yields myocardial contours of left ventricle from the input cardiac MR images, and then the regression component learns hierarchical representations from the segmented images and estimates the desired LV metrics. By introducing the myocardial contours, the regression component can pay more attention to the left ventricle, which contributes to more accurate quantification results, although the cardiac structures are variable. Extensive experiments on a dataset of 145 subjects demonstrate that our framework outperforms the state-of-the-art methods.

Aiming at the problem that traditional lung nodules detection method can only get low sensitivities with a lot of false positives, we propose a new framework of ensemble of convolutional neural networks (E-CNNs), and use it to significantly reduce the number of false-positive on lung nodules detection in chest radiographs (CXRs). Firstly Unsharp Mask technique is used to enhance the nodules in the CXRs. Then we cut patches in the 229×229 image containing or not containing nodule from the enhanced CXRs, which correspond to the positive and negative samples. Thirdly, 3 optimized CNNs of different input sizes and different depths, namely CNN1, CNN2 and CNN3, are constructed to detect lung nodule separately, and their input sizes are 12×12, 32×32 and 60×60, and the number of layer is 5, 7 and 9, separately. Finally, a logical AND operator is used to fuse the results of CNN1, CNN2 and CNN3, and an ensemble of convolutional neural networks (E-CNNs) are constructed for detecting lung nodules. Our experimental results on the JSRT database show our proposed E-CNNs attain a sensitivity of 94% and 84% with an average of 5.0 false-positives (FPs) per image and 2.0 FPs per image, respectively, in a 5-fold cross-validation test, which far outperforms the state of art.

X-ray images of the lower limb bone are the most commonly used imaging modality for clinical studies, and segmentation of the femur and tibia in an X-ray image is helpful for many medical studies such as diagnosis, surgery and treatment. In this paper, we propose a new approach based on pure dilated residual U-Net for the segmentation of the femur and tibia bones. The proposed approach employs dilated convolution completely to increase the receptive field, in this way, we can make full use of the advantages of dilated convolution. We conducted experiments and evaluations on datasets provided by Tianjin hospital. Comparison with the classical U-net and FusionNet, our method has fewer parameters, higher accuracy, and converges more rapidly, which means the high performance of the proposed method.

The directional total variation (DTV) model has been proposed very recently for image denoising. However, the DTV model works well when there is just one dominant direction in the image. In this Letter, the authors propose to make the DTV model adaptive to image edge direction so that the proposed model can handle images with several dominant directions. Experiment and comparison show the effectiveness of the proposed method.

A 3.25-Gbps VLC-system applying 512QAM SC-FDE is experimentally demonstrated for the first time using an RGB-LED with 3-dB bandwidth of 10MHz. The BERs for all 3 wavelength channels are below the pre-FEC threshold of 3.8x10-3.