Glioblastoma (GBM) tumor is the most common primary brain malignant tumor. The precise identification of GBM tumors is very important for diagnosis and treatment. Hyperspectral imaging is a fast, noncontact, accurate, and safe modern medical detection technology, which is expected to be a new tool of intraoperative diagnosis. In order to make full use of the spectral and spatial information of hyperspectral images (HSIs) to achieve accurate GBM tumor identification, a method based on the fusion of multiple deep models is proposed for in vivo human brain HSI classification. The proposed method includes the following major steps: 1) spectral phasor analysis and data oversampling; 2) 1-D deep neural network (1D-DNN)-based spectral HSI feature extraction and classification; 3) 2-D convolution neural network (2D-CNN)-based spectral–spatial HSI feature extraction and classification; 4) edge-preserving filtering-based classification result fusion and optimization; and 5) fully convolutional network (FCN)-based background segmentation. To verify the capabilities of the proposed method, experiments are performed on two real human brain hyperspectral datasets, including 36 in vivo HSIs captured from 16 different patients. The proposed method can achieve an overall accuracy of 96.69% for four-class classification and overall accuracy of 96.34% for GBM tumor identification. Experimental results demonstrate that the proposed method exhibits competitive classification performance and can generate satisfactory thematic maps of the location of the GBM tumor, which can provide the surgeon with guidance on successful and precise tumor resection.

In the merged multimedia packet-switched networks, the limited or no end-to-end Quality of Service (QoS) guarantees induce that rate control has been evolved to joint source-channel adjustment architecture based on application-oriented QoS. Based on the statistical analysis under the spatial intra and temporal inter prediction subject to a universal spatial-temporal coding framework and a general error concealment by the decoder, an end-to-end distortion estimation model is proposed. On the basis of the analytic model, this paper fulfills a picture quality parameters selection solution with rate-distortion (R-D) Lagrange optimization for a general coding engine including H.264/AVC, exploiting either the source-driven iterative prediction or feedback recursion. Further, a corresponding joint source-channel rate control strategy is proposed. For the real-time variable bit-rate (VBR) video transmission under a given time-varying network condition, the strategy could estimate an instantaneous available transmission rate on traffic smoothing and codec's buffer control, adopt the proposed an end-to-end distortion regressive model and a global optimal error control parameters selection, and address the consistent bit allocation in group of picture (GOP) level, picture level, and MB level. The extensive network simulation experiments show a better and more consistent end-to-end picture quality, in contrast with the locally optimal control strategy at MB level.

Image segmentation is a long-standing problem in medical image analysis to facilitate the clinical diagnosis and intervention. Progress has been made owing to deep learning via supervised training with elaborate human labelling, however, the segmentation models trained by the labeled source domain cannot perform well in the target domain, making existing approaches lack robustness and generalization ability. Considering the acquisition of medical image labels is quite expensive and time-consuming, we propose a novel feature disentanglement-based unsupervised domain adaptation (UDA) method to improve the robustness of the trained model in the target domain. A segmentation network is designed to learn disentangled features with two parts: I. content-related features, which are responsible for the segmentation task and invariant across domains; II. style-related features, which elucidate the discrepancy between different domains. Feature disentanglement (FD) is achieved by multi-task learning and image translation. Meanwhile, knowledge distillation is introduced to improve the performance on fine-grained segmentations. And for objects with regular shape, we incorporate the adversarial training to predict shape-invariant segmentation masks across domains. Comprehensive experiments are conducted on retina vessel segmentation and sinus surgical instrument segmentation to validate the effectiveness of the proposed method. The average Dice of twenty regular transfer directions achieves 79.26% on five public benchmarks of retina vessel segmentation, the average Dice of two transfer directions from regular to UWF attains 72.63%, and the Dice from cadaveric images to live images reaches 68.1% on sinus surgical instrument segmentation. The results demonstrate that the proposed method achieves the state-of-the-art segmentation performance in the UDA setting.

Although the particle swarm optimisation (PSO) algorithm requires relatively few parameters and is computationally simple and easy to implement, it is not a globally convergent algorithm. In Particle Swarm Optimisation: Classical and Quantum Perspectives, the authors introduce their concept of quantum-behaved particles inspired by quantum mechanics, which leads to the quantum-behaved particle swarm optimisation (QPSO) algorithm. This globally convergent algorithm has fewer parameters, a faster convergence rate, and stronger searchability for complex problems. The book presents the concepts of optimisation problems as well as random search methods for optimisation before discussing the principles of the PSO algorithm. Examples illustrate how the PSO algorithm solves optimisation problems. The authors also analyse the reasons behind the shortcomings of the PSO algorithm. Moving on to the QPSO algorithm, the authors give a thorough overview of the literature on QPSO, describe the fundamental model for the QPSO algorithm, and explore applications of the algorithm to solve typical optimisation problems. They also discuss some advanced theoretical topics, including the behaviour of individual particles, global convergence, computational complexity, convergence rate, and parameter selection. The text closes with coverage of several real-world applications, including inverse problems, optimal design of digital filters, economic dispatch problems, biological multiple sequence alignment, and image processing. MATLAB^®, Fortran, and C++ source codes for the main algorithms are provided on an accompanying downloadable resources. Helping you numerically solve optimisation problems, this book focuses on the fundamental principles and applications of PSO and QPSO algorithms. It not only explains how to use the algorithms, but also covers advanced topics that establish the groundwork for understanding.

Food-related issues have attracted increasing attention recently due to its various applications in our daily life, for example, restaurant service and dietary assessment, which are essential for human health management and understanding food characteristics. Many existing datasets are proposed for various food-relevant tasks, e.g., food detection and segmentation. However, most of the datasets are labelled with only dish-level annotations and lack detailed information for the corresponding ingredients. Hyperspectral imaging (HSI), which can explore the emissive characteristics of different objects with a long region of spectral bands, is of great potential for food and ingredient analysis. In the present work, a new food image dataset HSIFoodIngr-64 containing 3,389 pairs of HSI and RGB images with 21 dish classes and 64 ingredient categories was established. It is the first HSI-based food image dataset, of which all images are labelled with dish-level and ingredient-level annotations and corresponding pixel-wise ingredient masks. Therefore, our dataset can be applied to different food-centric tasks. Furthermore, this research proposed a benchmark method on the food ingredient retrieval task, which consists of two sub-networks called IPSN for ingredient prediction sub-network and ERSN for edge refinement sub-network. Extensive experiments were conducted on HSIFoodIngr-64 dataset and the effectiveness of our proposed method was verified. HSIFoodIngr-64 dataset is expected to provide a new perspective on food analysis and inspire more efforts on various food-related issues. We have made the HSIFoodIngr-64 dataset public at: https://doi.org/10.7910/DVN/E7WDNQ.

As one of the most popular deep learning models, convolution neural network (CNN) has achieved huge success in image information extraction. Traditionally CNN is trained by supervised learning method with labeled data and used as a classifier by adding a classification layer in the end. Its capability of extracting image features is largely limited due to the difficulty of setting up a large training dataset. In this paper, we propose a new unsupervised learning CNN model, which uses a so-called convolutional sparse auto-encoder (CSAE) algorithm pre-train the CNN. Instead of using labeled natural images for CNN training, the CSAE algorithm can be used to train the CNN with unlabeled artificial images, which enables easy expansion of training data and unsupervised learning. The CSAE algorithm is especially designed for extracting complex features from specific objects such as Chinese characters. After the features of articficial images are extracted by the CSAE algorithm, the learned parameters are used to initialize the first CNN convolutional layer, and then the CNN model is fine-trained by scene image patches with a linear classifier. The new CNN model is applied to Chinese scene text detection and is evaluated with a multilingual image dataset, which labels Chinese, English and numerals texts separately. More than 10% detection precision gain is observed over two CNN models.