Learning rich features with hybrid loss for brain tumor segmentation.

BACKGROUND: Accurately segment the tumor region of MRI images is important for brain tumor diagnosis and radiotherapy planning. At present, manual segmentation is wildly adopted in clinical and there is a strong need for an automatic and objective system to alleviate the workload of radiologists. METHODS: We propose a parallel multi-scale feature fusing architecture to generate rich feature representation for accurate brain tumor segmentation. It comprises two parts: (1) Feature Extraction Network (FEN) for brain tumor feature extraction at different levels and (2) Multi-scale Feature Fusing Network (MSFFN) for merge all different scale features in a parallel manner. In addition, we use two hybrid loss functions to optimize the proposed network for the class imbalance issue. RESULTS: We validate our method on BRATS 2015, with 0.86, 0.73 and 0.61 in Dice for the three tumor regions (complete, core and enhancing), and the model parameter size is only 6.3 MB. Without any post-processing operations, our method still outperforms published state-of-the-arts methods on the segmentation results of complete tumor regions and obtains competitive performance in another two regions. CONCLUSIONS: The proposed parallel structure can effectively fuse multi-level features to generate rich feature representation for high-resolution results. Moreover, the hybrid loss functions can alleviate the class imbalance issue and guide the training process. The proposed method can be used in other medical segmentation tasks.

The application of convolution neural network based cell segmentation during cryopreservation.

For most of the cells, water permeability and plasma membrane properties play a vital role in the optimal protocol for successful cryopreservation. Measuring the water permeability of cells during subzero temperature is essential. So far, there is no perfect segmentation technique to be used for the image processing task on subzero temperature accurately. The ice formation and variable background during freezing posed a significant challenge for most of the conventional segmentation algorithms. Thus, a robust and accurate segmentation approach that can accurately extract cells from extracellular ice that surrounding the cell boundary is needed. Therefore, we propose a convolutional neural network (CNN) architecture similar to U-Net but differs from those conventionally used in computer vision to extract all the cell boundaries as they shrank in the engulfing ice. The images used was obtained from the cryo-stage microscope, and the data was validated using the Hausdorff distance, means ±â€¯standard deviation for different methods of segmentation result using the CNN model. The experimental results prove that the typical CNN model extracts cell borders contour from the background in its subzero state more coherent and effective as compared to other traditional segmentation approaches.

MRF-IUNet: A Multiresolution Fusion Brain Tumor Segmentation Network Based on Improved Inception U-Net.

The automatic segmentation method of MRI brain tumors uses computer technology to segment and label tumor areas and normal tissues, which plays an important role in assisting doctors in the clinical diagnosis and treatment of brain tumors. This paper proposed a multiresolution fusion MRI brain tumor segmentation algorithm based on improved inception U-Net named MRF-IUNet (multiresolution fusion inception U-Net). By replacing the original convolution modules in U-Net with the inception modules, the width and depth of the network are increased. The inception module connects convolution kernels of different sizes in parallel to obtain receptive fields of different sizes, which can extract features of different scales. In order to reduce the loss of detailed information during the downsampling process, atrous convolutions are introduced in the inception module to expand the receptive field. The multiresolution feature fusion modules are connected between the encoder and decoder of the proposed network to fuse the semantic features learned by the deeper layers and the spatial detail features learned by the early layers, which improves the recognition and segmentation of local detail features by the network and effectively improves the segmentation accuracy. The experimental results on the BraTS (the Multimodal Brain Tumor Segmentation Challenge) dataset show that the Dice similarity coefficient (DSC) obtained by the method in this paper is 0.94 for the enhanced tumor area, 0.83 for the whole tumor area, and 0.93 for the tumor core area. The segmentation accuracy has been improved.

Generative Adversarial Network Combined with SE-ResNet and Dilated Inception Block for Segmenting Retinal Vessels.

This study develops an accurate method based on the generative adversarial network (GAN) that targets the issue of the current discontinuity of micro vessel segmentation in the retinal segmentation images. The processing of images has become increasingly efficient since the advent of deep learning method. We have proposed an improved GAN combined with SE-ResNet and dilated inception block for the segmenting retinal vessels (SAD-GAN). The GAN model has been improved with respect to the following points. (1) In the generator, the original convolution block is replaced with SE-ResNet module. Furthermore, SE-Net can extract the global channel information, while concomitantly strengthening and weakening the key features and invalid features, respectively. The residual structure can alleviate the issue of gradient disappearance. (2) The inception block and dilated convolution are introduced into the discriminator, which enhance the transmission of features and expand the acceptance domain for improved extraction of the deep network features. (3) We have included the attention mechanism in the discriminator for combining the local features with the corresponding global dependencies, and for highlighting the interdependent channel mapping. SAD-GAN performs satisfactorily on public retina datasets. On DRIVE dataset, ROC_AUC and PR_AUC reach 0.9813 and 0.8928, respectively. On CHASE_DB1 dataset, ROC_AUC and PR_AUC reach 0.9839 and 0.9002, respectively. Experimental results demonstrate that the generative adversarial model, combined with deep convolutional neural network, enhances the segmentation accuracy of the retinal vessels far above that of certain state-of-the-art methods.

SRV-GAN: A generative adversarial network for segmenting retinal vessels.

In the field of ophthalmology, retinal diseases are often accompanied by complications, and effective segmentation of retinal blood vessels is an important condition for judging retinal diseases. Therefore, this paper proposes a segmentation model for retinal blood vessel segmentation. Generative adversarial networks (GANs) have been used for image semantic segmentation and show good performance. So, this paper proposes an improved GAN. Based on R2U-Net, the generator adds an attention mechanism, channel and spatial attention, which can reduce the loss of information and extract more effective features. We use dense connection modules in the discriminator. The dense connection module has the characteristics of alleviating gradient disappearance and realizing feature reuse. After a certain amount of iterative training, the generated prediction map and label map can be distinguished. Based on the loss function in the traditional GAN, we introduce the mean squared error. By using this loss, we ensure that the synthetic images contain more realistic blood vessel structures. The values of area under the curve (AUC) in the retinal blood vessel pixel segmentation of the three public data sets DRIVE, CHASE-DB1 and STARE of the proposed method are 0.9869, 0.9894 and 0.9885, respectively. The indicators of this experiment have improved compared to previous methods.

Fenretinide inhibits the proliferation and migration of human liver cancer HepG2 cells by downregulating the activation of myosin light chain kinase through the p38­MAPK signaling pathway.

N-(4-hydroxyphenyl)retinamide (4-HPR or fenretinide), which is a synthetic analog of all­trans retinoic acid (ATRA), effectively inhibits the growth of several types of tumor cells; however, its molecular mechanism remains unclear. We found that 4­HPR altered the morphology of human liver cancer HepG2 cells and also inhibited their proliferation and suppressed the colony formation in a dose­ and time­dependent manner. A wound healing assay revealed that 4­HPR significantly hindered HepG2 cell migration, and that this was accompanied by the phosphorylation of p38­MAPK (mitogen­activated protein kinase). Mechanistically, the MAPK­specific inhibitor SB203580 attenuated the inhibitory effects of 4­HPR on the migration of HepG2 cells. Moreover, we also observed that 4­HPR inhibited the activation and expression of myosin light chain kinase (MLCK) in HepG2 cells. Simultaneously, 4­HPR lowered the expression of F­actin and promoted the expression of E­cadherin. ML­7, a selective inhibitor of MLCK, significantly inhibited the migration of HepG2 cells while increasing the phosphorylation of p38­MAPK and the expression of E­cadherin, and decreasing the activation of MLCK and the expression of F­actin. In conclusion, 4­HPR inhibited the proliferation and migration of HepG2 cells, and p38­MAPK plays an important role in regulating these 4­HPR effects by reducing the activation of MLCK. The present study suggests that 4­HPR may be a potent antimetastatic agent.

Hybrid Method Based on Information Gain and Support Vector Machine for Gene Selection in Cancer Classification.

It remains a great challenge to achieve sufficient cancer classification accuracy with the entire set of genes, due to the high dimensions, small sample size, and big noise of gene expression data. We thus proposed a hybrid gene selection method, Information Gain-Support Vector Machine (IG-SVM) in this study. IG was initially employed to filter irrelevant and redundant genes. Then, further removal of redundant genes was performed using SVM to eliminate the noise in the datasets more effectively. Finally, the informative genes selected by IG-SVM served as the input for the LIBSVM classifier. Compared to other related algorithms, IG-SVM showed the highest classification accuracy and superior performance as evaluated using five cancer gene expression datasets based on a few selected genes. As an example, IG-SVM achieved a classification accuracy of 90.32% for colon cancer, which is difficult to be accurately classified, only based on three genes including CSRP1, MYL9, and GUCA2B.