Search

A deep neural network with invertible hidden layers has a nice property of preserving all the information in the feature learning stage. In this paper, we analyse the hidden layers of residual rectifier neural networks, and investigate conditions for invertibility under which the hidden layers are invertible. A new fixed-point algorithm is developed to invert the hidden layers of residual networks. The proposed inverse algorithms are capable of inverting some residual networks which cannot be inverted by existing inverting algorithms. Furthermore, a special residual rectifier network is designed and trained on MNIST so that it can achieve comparable performance with the state-of-art performance while its hidden layers are invertible. [ABSTRACT FROM AUTHOR]

BACKGROUND: Segmentation of prostate from magnetic resonance images (MRI) is a critical process for guiding prostate puncture and biopsy. Currently, the best results are obtained by Convolutional Neural Network (CNN). However, challenges still exist when applying CNN to segment prostate, such as data distribution issue caused by insubstantial and inconsistent intensity levels and vague boundaries in MRI. OBJECTIVE: To segment prostate gland from a MRI dataset including different prostate images with limited resolution and quality. METHODS: We propose and apply a global histogram matching approach to make intensity distribution of the MRI dataset closer to uniformity. To capture the real boundaries and improve segmentation accuracy, we employ a module of variational models to help improve performance. RESULTS: Using seven evaluation metrics to quantify improvements of our proposed fusion approach compared with the state of art V-net model resulted in increase in the Dice Coefficient (11.2%), Jaccard Coefficient (13.7%), Volumetric Similarity (12.3%), Adjusted Rand Index (11.1%), Area under ROC Curve (11.6%), and reduction of the Mean Hausdorff Distance (16.1%) and Mahalanobis Distance (2.8%). The 3D reconstruction also validates the advantages of our proposed framework, especially in terms of smoothness, uniformity, and accuracy. In addition, observations from the selected examples of 2D visualization show that our segmentation results are closer to the real boundaries of the prostate, and better represent the prostate shapes. CONCLUSIONS: Our proposed approach achieves significant performance improvements compared with the existing methods based on the original CNN or pure variational models. [ABSTRACT FROM AUTHOR]

• We proposed a novel neural network to deal with Raman spectral data and classify six types of oral tissues, including oral cancerous and normal tissues. • The feature fusion part of the proposed network can be used to extract multi-scale features so as to improve the identification ability of the network. • A completed deployment procedure for the intelligent OSCC detection system is designed and proposed in our research. Using fiber optic Raman spectroscopy and deep neural networks, we develop an intelligent system which will be used to assist surgeons accurately and efficiently to identify oral squamous cell carcinomas (OSCC). This system is able to classify 6 types of oral tissues. To achieve this goal, a novel classification framework called deep multi-feature fusion residual network (DMFF-ResNet) is proposed. This model is based on 16,200 Raman spectral data, obtained from the normal oral tissues and the OSCC of 90 patients through the surgical resection. Firstly, the 1-dimensional RestNet50 is taken as its backbone network. Then, the output spectral features of last three blocks are extracted from backbone network for feature fusion, which is expected to learn more spatial representations and have more discriminative power. Lastly, the derived spectral features are sent into a fully-connected neural network for performing the multiclassification task. Experimental results show that the proposed model achieves a competitive classification performance compared with state-of-the-art classifiers, and its accuracy, precision, and sensitivity reach 93.28%, 93.53%, and 93.13%, respectively. Further, the proposed framework is deployed on an edge computing device to form a prototype intelligent system for OSCC detection. To validate this system, we perform an offline test experiment in another 20 patients which demonstrates the developed intelligent system can successfully discriminate OSCC and normal oral tissues, with accuracy, precision, and recall of 92.78%, 92.33%, and 92.57%, respectively. The code was available at https://github.com/ISCLab-Bistu/retinanet-OSCC. [ABSTRACT FROM AUTHOR]

The malignancy risk differentiation of pulmonary nodule is one of the most challenge tasks of computer-aided diagnosis (CADx). Most recently reported CADx methods or schemes based on texture and shape estimation have shown relatively satisfactory on differentiating the risk level of malignancy among the nodules detected in lung cancer screening. However, the existing CADx schemes tend to detect and analyze characteristics of pulmonary nodules from a statistical perspective according to local features only. Enlightened by the currently prevailing learning ability of convolutional neural network (CNN), which simulates human neural network for target recognition and our previously research on texture features, we present a hybrid model that takes into consideration of both global and local features for pulmonary nodule differentiation using the largest public database founded by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). By comparing three types of CNN models in which two of them were newly proposed by us, we observed that the multi-channel CNN model yielded the best discrimination in capacity of differentiating malignancy risk of the nodules based on the projection of distributions of extracted features. Moreover, CADx scheme using the new multi-channel CNN model outperformed our previously developed CADx scheme using the 3D texture feature analysis method, which increased the computed area under a receiver operating characteristic curve (AUC) from 0.9441 to 0.9702. [ABSTRACT FROM AUTHOR]

Face recognition/verification has received great attention in both theory and application for the past two decades. Deep learning has been considered as a very powerful tool for improving the performance of face recognition/verification recently. With large labeled training datasets, the features obtained from deep learning networks can achieve higher accuracy in comparison with shallow networks. However, many reported face recognition/verification approaches rely heavily on the large size and complete representative of the training set, and most of them tend to suffer serious performance drop or even fail to work if fewer training samples per person are available. Hence, the small number of training samples may cause the deep features to vary greatly. We aim to solve this critical problem in this paper. Inspired by recent research in scene domain transfer, for a given face image, a new series of possible scenarios about this face can be deduced from the scene semantics extracted from other face individuals in a face dataset. We believe that the “scene” or background in an image, that is, samples with more different scenes for a given person, may determine the intrinsic features among the faces of the same individual. In order to validate this belief, we propose a Bayesian scene-prior-based deep learning model in this paper with the aim to extract important features from background scenes. By learning a scene model on the basis of a labeled face dataset via the Bayesian idea, the proposed method transforms a face image into new face images by referring to the given face with the learnt scene dictionary. Because the new derived faces may have similar scenes to the input face, the face-verification performance can be improved without having background variance, while the number of training samples is significantly reduced. Experiments conducted on the Labeled Faces in the Wild (LFW) dataset view #2 subset illustrated that this model can increase the verification accuracy to 99.2% by means of scenes’ transfer learning (99.12% in literature with an unsupervised protocol). Meanwhile, our model can achieve 94.3% accuracy for the YouTube Faces database (DB) (93.2% in literature with an unsupervised protocol). [ABSTRACT FROM AUTHOR]

Artificial neural networks are computational approaches based on machine learning to learn and make predictions based on data, and have been applied successfully in diverse applications including structural health monitoring in civil engineering. It is difficult to optimize the weights in the neural networks that have multiple hidden layers due to the vanishing gradient issue. This paper proposes an autoencoder based framework for structural damage identification, which can support deep neural networks and be utilized to obtain optimal solutions for pattern recognition problems of highly non-linear nature, such as learning a mapping between the vibration characteristics and structural damage. Two main components are defined in the proposed framework, namely, dimensionality reduction and relationship learning. The first component is to reduce the dimensionality of the original input vector while preserving the required necessary information, and the second component is to perform the relationship learning between the features with the reduced dimensionality and the stiffness reduction parameters of the structure. Vibration characteristics, such as natural frequencies and mode shapes, are used as the input and the structural damage are considered as the output vector. A pre-training scheme is performed to train the hidden layers in the autoencoders layer by layer, and fine tuning is conducted to optimize the whole network. Numerical and experimental investigations on steel frame structures are conducted to demonstrate the accuracy and efficiency of the proposed framework, comparing with the traditional ANN methods. [ABSTRACT FROM AUTHOR]