Melanoma localization and classification through faster region-based convolutional neural network and SVM

Multimedia Tools and Applications - Melanoma is a lethal skin cancer disease affecting millions of people around the globe and has a high mortality rate. Dermatologists perform the manual...     

Development of Efficient Classification Systems for the Diagnosis of Melanoma

Skin cancer is usually classified as melanoma and non-melanoma. Melanoma now represents 75% of humans passing away worldwide and is one of the most brutal types of cancer. Previously, studies were not mainly focused on feature extraction of Melanoma, which caused the classification accuracy. However, in this work, Histograms of orientation gradients and local binary patterns feature extraction procedures are used to extract the important features such as asymmetry, symmetry, boundary irregularity, color, diameter, etc., and are removed from both melanoma and non-melanoma images. This proposed Efficient Classification Systems for the Diagnosis of Melanoma (ECSDM) framework consists of different schemes such as preprocessing, segmentation, feature extraction, and classification. We used Machine Learning (ML) and Deep Learning (DL) classifiers in the classification framework. The ML classifier is Naïve Bayes (NB) and Support Vector Machines (SVM). And also, DL classification framework of the Convolution Neural Network (CNN) is used to classify the melanoma and benign images. The results show that the Neural Network (NNET) classifier’ achieves 97.17% of accuracy when contrasting with ML classifiers.     

Robust optimization of SegNet hyperparameters for skin lesion segmentation

Multimedia Tools and Applications - Melanoma is considered the deadliest form of skin cancer, and the number of cases is increasing day by day. The early diagnosis of melanoma is critical, as it...     

Fuzzy decision ontology for melanoma diagnosis using KNN classifier

Multimedia Tools and Applications - Melanoma is the most dangerous type of skin cancer when discovered in an advanced stage. Early detection of melanoma improves survival. Several Computer -Aided...     

Computational methods for pigmented skin lesion classification in images: review and future trends

Skin cancer is considered as one of the most common types of cancer in several countries, and its incidence rate has increased in recent years. Melanoma cases have caused an increasing number of deaths worldwide, since this type of skin cancer is the most aggressive compared to other types. Computational methods have been developed to assist dermatologists in early diagnosis of skin cancer. An overview of the main and current computational methods that have been proposed for pattern analysis and pigmented skin lesion classification is addressed in this review. In addition, a discussion about the application of such methods, as well as future trends, is also provided. Several methods for feature extraction from both macroscopic and dermoscopic images and models for feature selection are introduced and discussed. Furthermore, classification algorithms and evaluation procedures are described, and performance results for lesion classification and pattern analysis are given.

     

A coarse-to-fine approach for segmenting melanocytic skin lesions in standard camera images

Melanoma is a type of malignant melanocytic skin lesion, and it is among the most life threatening existing cancers if not treated at an early stage. Computer-aided prescreening systems for melanocytic skin lesions is a recent trend to detect malignant melanocytic skin lesions in their early stages, and lesion segmentation is an important initial processing step. A good definition of the lesion area and its border is very important for discriminating between benign and malignant cases. In this paper, we propose to segment melanocytic skin lesions using a sequence of steps. We start by pre-segmenting the skin lesion, creating a new image representation (channel) where the lesion features are more evident. This new channel is thresholded, and the lesion border pre-detection is refined using an active-contours algorithm followed by morphological operations. Our experimental results based on a publicly available dataset suggest that our method potentially can be more accurate than comparable state-of-the-art methods proposed in literature.     

A decision support system for the diagnosis of melanoma: A comparative approach

Melanoma is the most deathful of all skin cancers and the number of cases grows every year. The extirpation in early phases implies a high degree of survival so it is fundamental to diagnose it as soon as possible. In this paper we present a clinical decision support system for melanoma diagnosis using as input an image set of the skin lesion to be diagnosed. The system analyses the image sequence to extract the affected area, determinates the characteristics which indicate the degree of damage and, according to them, it makes a decision. Several methods of classification are proposed: a multilayered perceptron, a Bayesian classifier and the algorithm of the K nearest neighbours. These methods work independently and also in combination making a collaborative decision support system. The classification rates obtained are around 87%.     

HGDBMS: a human genetics database management system

Human genetics research involves a large number of complex data sets naturally organized in hierarchical structures. Data collection is performed on different levels, e.g., the project level, pedigree level, individual level, and sample level. Different aspects of a study utilize different views of the data, requiring a flexible database management system (DBMS) which satisfies these different needs for data collection and retrieval. We describe HGDBMS, a comprehensive relational DBMS, implemented as an application of the GENISYS I DBMS, which allows embedding the hierarchical structure of pedigrees in a relational structure. The system's file structure is described in detail. Currently our Melanoma and Chromosome 17 map studies are managed with HGDBMS. Our initial experience demonstrates the value of a flexible system which supports the needs for data entry, update, storage, reporting, and analysis required during different phases of genetic research. Further developments will focus on the integration of HGDBMS with a human genetics expert system shell and analysis programs.     

A Hybrid Artificial Intelligence Model for Skin Cancer Diagnosis

Melanoma or skin cancer is the most dangerous and deadliest disease. As the incidence and mortality rate of skin cancer increases worldwide, an automated skin cancer detection/classification system is required for early detection and prevention of skin cancer. In this study, a Hybrid Artificial Intelligence Model (HAIM) is designed for skin cancer classification. It uses diverse multi-directional representation systems for feature extraction and an efficient Exponentially Weighted and Heaped Multi-Layer Perceptron (EWHMLP) for the classification. Though the wavelet transform is a powerful tool for signal and image processing, it is unable to detect the intermediate dimensional structures of a medical image. Thus the proposed HAIM uses Curvelet (CurT), Contourlet (ConT) and Shearlet (SheT) transforms as feature extraction techniques. Though MLP is very flexible and well suitable for the classification problem, the learning of weights is a challenging task. Also, the optimization process does not converge, and the model may not be stable. To overcome these drawbacks, EWHMLP is developed. Results show that the combined qualities of each transform in a hybrid approach provides an accuracy of 98.33% in a multi-class approach on PH² database.     

A system on chip for melanoma detection using FPGA-based SVM classifier

Support Vector Machine (SVM) is a robust machine learning model that shows high accuracy with different classification problems, and is widely used for various embedded applications. However, implementation of embedded SVM classifiers is challenging, due to the inherent complicated computations required. This motivates implementing the SVM on hardware platforms for achieving high performance computing at low cost and power consumption. Melanoma is the most aggressive form of skin cancer that increases the mortality rate. We aim to develop an optimized embedded SVM classifier dedicated for a low-cost handheld device for early detection of melanoma at the primary healthcare. In this paper, we propose a hardware/software co-design for implementing the SVM classifier onto FPGA to realize melanoma detection on a chip. The implemented SVM on a recent hybrid FPGA (Zynq) platform utilizing the modern UltraFast High-Level Synthesis design methodology achieves efficient melanoma classification on chip. The hardware implementation results demonstrate classification accuracy of 97.9%, and a significant hardware acceleration rate of 21 with only 3% resources utilization and 1.69 W for power consumption. These results show that the implemented system on chip meets crucial embedded system constraints of high performance and low resources utilization, power consumption, and cost, while achieving efficient classification with high classification accuracy.     

医学影像疾病诊断的残差神经网络优化算法研究进展

残差神经网络（residual neural network,ResNet）及其优化是深度学习研究的热点之一,在医学图像领域应用广泛,在肿瘤、心脑血管和神经系统疾病等重大疾病的临床诊断、分期、转移、治疗决策和靶区勾画方面取得良好效果。本文对残差神经网络的学习优化进行了总结：阐述了残差神经网络学习算法优化,从激活函数、损失函数、参数优化算法、学习衰减率、归一化和正则化技术等6方面进行总结,其中激活函数的改进方法主要有Sigmoid、tanh、ReLU、PReLU（parameteric ReLU）、随机化ReLU（randomized leaky ReLU,RReLU）、ELU（exponential linear units）、Softplus函数、NoisySoftplus函数以及Maxout共9种;损失函数主要有交叉熵损失、均方损失、欧氏距离损失、对比损失、合页损失、Softmax-Loss、L-Softmax Loss、A-Softmax Loss、L2 Softmax Loss、Cosine Loss、Center Loss和焦点损失共12种;学习率衰减总结了8种,即分段常数衰减、多项式衰减、指数衰减、反时限衰减、自然指数衰减、余弦衰减、线性余弦衰减和噪声线性余弦衰减;归一化算法有批量归一化和提出批量重归一化算法;正则化方法主要有增加输入数据、数据增强、早停法、L1正则化、L2正则化、Dropout和Dropout Connect共7种。综述了残差网络模型在医学图像疾病诊断中的应用研究,梳理了残差神经网络在肺部肿瘤、皮肤疾病、乳腺癌、大脑疾病、糖尿病和血液病等6种疾病诊断中的应用研究;对深度学习在医学图像未来发展进行了总结和展望。     

Zigbee和Wi-Fi的干扰和共存

Zigbee是近年来出现的一种新兴的短距离无线通信技术,它采用了IEEE802.15.4标准作为其物理层和媒体接入层规范,具有低功耗、低成本和低复杂度的特点.它和Wi-Fi有着不同的应用空间,主要适用于自动控制、远程监控等领域,是Wi-Fi的有效补充.但是由于它们使用的是相同的频段,不可避免地会出现相互之间的干扰.对Zigbee和Wi-Fi的主要特性作了比较,分析了两者产生干扰的原因,在室内环境下具体分析了Zigbee对Wi-Fi的干扰情况,并且提出了两者共存问题的解决方法.     

航天器交会对接的模型预测与反演制导控制

面向空间交会对接和停靠的任务需求,将航天器相对制导控制系统视为离散时间控制系统.利用系统状态转移模型外推预测相对运动状态偏差,在每个控制周期中推力恒定的假设下,根据轨控作用对系统状态的影响规律,采用广义逆方法反演得到交会对接制导控制序列.对时间约束下的基于空间相对运动状态转移预测与反演的相对制导控制律进行设计,讨论该方法在实际应用中的一些特点.预测与反演制导控制中的控制输出直接表示为轨控加速度,更符合工程实际情况.近圆轨道的交会对接仿真结果表明,所提出的方法能够实现精度更高、更为柔顺平滑的交会对接,在轨控速度增量和推力器输出上也具有更好的工程适用性.     

IPSec和NAT兼容性研究及解决方案

网络地址转换技术（NAT）与IP安全体系结构（IPSec）在因特网上都是得到广泛应用的技术,但是它们之间却是不兼容的.分别介绍了NAT和IPSec两种协议的基本原理,并对两者存在的不兼容性进行了详细的分析,介绍了RSIP和UDP封装法两种解决方案,并对两个方案进行了比较分析,提出UDP封装法是目前更为可行的方案,最后分析实现NAT透明穿透会对IPSec造成那些影响.     

System threats and vulnerabilities and the contrary principle

Security literature exhibits many instances where the terms “threats” and “vulnerabilities” are often used in error and, more than occasionally, wrongly interchanged. Threats are confused with vulnerabilities and vice versa. The reason for the confusion is that almost everyone starts with two false premises. One is the assumption that threats and vulnerabilities are always separate and distinct throughout their analysis. The second error is the assumption that the names historically attached to the technical processes of determining threats and vulnerabilities are valid.Why do very intelligent, credentialed writers consistently commit these errors? The author believes the security industry has, itself, created and continued the problem. The apparent confusion is precisely that which is supposed to occur. It is the writer's contention that what is needed is an infusion of contrary thought. The work product of a vulnerability analysis is not vulnerabilities but threat identification. The work product of a threat analysis is not threats, but rather vulnerabilities. In both cases, the result created is precisely the opposite effect from that which the task's name would imply. A step-by-step illustrative example drives the discussion.     

Definition and analysis of hardware- and software-fault-tolerantarchitectures

A structured definition of hardware- and software-fault-tolerant architectures is presented. Software-fault-tolerance methods are discussed, resulting in definitions for soft and solid faults. A soft software fault has a negligible likelihood or recurrence and is recoverable, whereas a solid software fault is recurrent under normal operations or cannot be recovered. A set of hardware- and software-fault-tolerant architectures is presented, and three of them are analyzed and evaluated. Architectures tolerating a single fault and architectures tolerating two consecutive faults are discussed separately. A sidebar addresses the cost issues related to software fault tolerance. The approach taken throughout is as general as possible, dealing with specific classes of faults or techniques only when necessary     

Semantics and verification of monitors and systems of monitors and processes

In this paper we present a sound and complete semantics for the monitor concept of C.A.R. Hoare. First a method for specification of monitors, introduced by O.-J. Dahl, is reviewed. This method is based on the relation between the historic sequence of monitor procedure calls and the historic sequence of monitor procedure exits. Based on such specifications and our new monitor semantics we present a method by which it is possible to prove that a concrete monitor is an implementation of an abstract one. In the last part of the paper an axiomatic semantics for systems of concurrent processes and monitors is introduced. The method supports verification by separation of concerns: Properties of the communication to and from each process are proven in isolation by a usual Hoare style axiomatic semantics, while abstract monitors are also specified in isolation by the method reviewed in the first part of the paper. These properties of the components of the system are then used in a new proof rule to conclude properties of the complete system. Stein Gjessing received a Ph.D. (actually a Dr. philos.) from the University of Oslo (Norway) in 1985. Presently he is an Associate Professor at the Institute of informatics, University of Oslo, Norway. Dr. Gjessings research interests are in the area of concurrent and distributed programming, operating systems, formal specification and verification and programming languages.