Dynamically aggregating MLPs and CNNs for skin lesion segmentation with geometry regularization

BACKGROUND AND OBJECTIVE

Melanoma is a highly malignant skin tumor. Accurate segmentation of skin lesions from dermoscopy images is pivotal for computer-aided diagnosis of melanoma. However, blurred lesion boundaries, variable lesion shapes, and other interference factors pose a challenge in this regard.

METHODS

This work proposes a novel framework called CFF-Net (Cross Feature Fusion Network) for supervised skin lesion segmentation. The encoder of the network includes dual branches, where the CNNs branch aims to extract rich local features while MLPs branch is used to establish both the global-spatial-dependencies and global-channel-dependencies for precise delineation of skin lesions. Besides, a feature-interaction module between two branches is designed for strengthening the feature representation by allowing dynamic exchange of spatial and channel information, so as to retain more spatial details and inhibit irrelevant noise. Moreover, an auxiliary prediction task is introduced to learn the global geometric information, highlighting the boundary of the skin lesion.

RESULTS

Comprehensive experiments using four publicly available skin lesion datasets (i.e., ISIC 2018, ISIC 2017, ISIC 2016, and PH2) indicated that CFF-Net outperformed the state-of-the-art models. In particular, CFF-Net greatly increased the average Jaccard Index score from 79.71% to 81.86% in ISIC 2018, from 78.03% to 80.21% in ISIC 2017, from 82.58% to 85.38% in ISIC 2016, and from 84.18% to 89.71% in PH2 compared with U-Net. Ablation studies demonstrated the effectiveness of each proposed component. Cross-validation experiments in ISIC 2018 and PH2 datasets verified the generalizability of CFF-Net under different skin lesion data distributions. Finally, comparison experiments using three public datasets demonstrated the superior performance of our model.

CONCLUSION

The proposed CFF-Net performed well in four public skin lesion datasets, especially for challenging cases with blurred edges of skin lesions and low contrast between skin lesions and background. CFF-Net can be employed for other segmentation tasks with better prediction and more accurate delineation of boundaries.

Computational Intelligence for Biometric Applications: a Survey

Biometric systems consist of devices, procedures, and algorithms used to recognize people based on their physiological or behavioral features, known as biometric traits. Computational intelligence (CI) approaches are widely adopted in establishing identity based on biometrics and also to overcome non-idealities typically present in the samples. Typical areas include sample enhancement, feature extraction, classification, indexing, fusion, normalization, and anti-spoofing. In this context, computational intelligence plays an important role in performing of complex non-linear computations by creating models from the training data. These approaches are based on supervised as well as unsupervised training techniques. This work presents computational intelligence techniques applied to biometrics, from both a theoretical and an application point of view.

Hierarchical approach for multiscale support vector regression

Support vector regression (SVR) is based on a linear combination of displaced replicas of the same function, called a kernel. When the function to be approximated is nonstationary, the single kernel approach may be ineffective, as it is not able to follow the variations in the frequency content in the different regions of the input space. The hierarchical support vector regression (HSVR) model presented here aims to provide a good solution also in these cases. HSVR consists of a set of hierarchical layers, each containing a standard SVR with Gaussian kernel at a given scale. Decreasing the scale layer by layer, details are incorporated inside the regression function. HSVR has been widely applied to noisy synthetic and real datasets and it has shown the ability in denoising the original data, obtaining an effective multiscale reconstruction of better quality than that obtained by standard SVR. Results also compare favorably with multikernel approaches. Furthermore, tuning the SVR configuration parameters is strongly simplified in the HSVR model.

A hierarchical RBF online learning algorithm for real-time 3-D scanner

In this paper, a novel real-time online network model is presented. It is derived from the hierarchical radial basis function (HRBF) model and it grows by automatically adding units at smaller scales, where the surface details are located, while data points are being collected. Real-time operation is achieved by exploiting the quasi-local nature of the Gaussian units: through the definition of a quad-tree structure to support their receptive field local network reconfiguration can be obtained. The model has been applied to 3-D scanning, where an updated real-time display of the manifold to the operator is fundamental to drive the acquisition procedure itself. Quantitative results are reported, which show that the accuracy achieved is comparable to that of two batch approaches: batch HRBF and support vector machines (SVMs). However, these two approaches are not suitable to real-time online learning. Moreover, proof of convergence is also given.

Function approximation--a fast-convergence neural approach based on spectral analysis

We propose a constructive approach to building single-hidden-layer neural networks for nonlinear function approximation using frequency domain analysis. We introduce a spectrum-based learning procedure that minimizes the difference between the spectrum of the training data and the spectrum of the network's estimates. The network is built up incrementally during training and automatically determines the appropriate number of hidden units. This technique achieves similar or better approximation with faster convergence times than traditional techniques such as backpropagation.

Reducing and Filtering Point Clouds With Enhanced Vector Quantization

Modern scanners are able to deliver huge quantities of three-dimensional (3-D) data points sampled on an object's surface, in a short time. These data have to be filtered and their cardinality reduced to come up with a mesh manageable at interactive rates. We introduce here a novel procedure to accomplish these two tasks, which is based on an optimized version of soft vector quantization (VQ). The resulting technique has been termed enhanced vector quantization (EVQ) since it introduces several improvements with respect to the classical soft VQ approaches. These are based on computationally expensive iterative optimization; local computation is introduced here, by means of an adequate partitioning of the data space called hyperbox (HB), to reduce the computational time so as to be linear in the number of data points N, saving more than 80% of time in real applications. Moreover, the algorithm can be fully parallelized, thus leading to an implementation that is sublinear in N. The voxel side and the other parameters are automatically determined from data distribution on the basis of the Zador's criterion. This makes the algorithm completely automatic. Because the only parameter to be specified is the compression rate, the procedure is suitable even for nontrained users. Results obtained in reconstructing faces of both humans and puppets as well as artifacts from point clouds publicly available on the web are reported and discussed, in comparison with other methods available in the literature. EVQ has been conceived as a general procedure, suited for VQ applications with large data sets whose data space has relatively low dimensionality.

Designing Information Technology Architectures: A Cost-Oriented Methodology

This paper proposes a design methodology of information technology architectures tying organizational requirements to technical choices and costs. The primary goal is to provide a structured support for the selection of the minimum-cost architecture satisfying given organizational requirements. Previous empirical studies have attempted absolute cost comparisons of different architectural solutions, primarily relying on the expertise of practitioners and a priori beliefs, but have rarely taken into account the impact of organizational requirements on costs. Requirements are modelled as information processes, composed of tasks exchanging information and characterized by varying levels of computational complexity. Different architectural distributions of presentation, computation and data management applications are compared. The cost implications of organizational requirements for processing intensity, communication intensity and networking are analysed. The results show a relationship between structural features of information processes and architectural costs and indicate how architectural design should be based on organizational as well as technology considerations.

Entropic analysis and incremental synthesis of multilayered feedforward neural networks

Neural network architecture optimization is often a critical issue, particularly when VLSI implementation is considered. This paper proposes a new minimization method for multilayered feedforward ANNs and an original approach to their synthesis, both based on the analysis of the information quantity (entropy) flowing through the network. A layer is described as an information filter which selects the relevant characteristics until the complete classification is performed. The basic incremental synthesis method, including the supervised training procedure, is derived to design application-tailored neural paradigms with good generalization capability.