Recognizing Occlusal Caries in Dental Intraoral Images Using Deep Learning

Based on an image dataset of 88 in-vivo dental images taken with an intra-oral camera, we show that a Deep Learning model (Mask R-CNN) can detect and classify dental caries on occlusal surfaces across the whole 7-class ICDAS (International Caries Detection and Assessment System) scale. This is accomplished without any image pre-processing method and by utilizing superpixels segmentation for the experts' annotations and the evaluation of the classifier. In the proposed methodology, transfer learning and data augmentation are employed during the training of the model. The paper discusses technical details, provides initial results and denotes points for further improvement by fine-tuning the classifier along with an extended dataset.

Real-time integration of emotion analysis into homecare platforms

The scientific and technological advancements in the area of affective computing enable the development of services in various domains that facilitate the interaction between humans and computers, and can considerably improve decision-making. This work presents the integration and operation of an emotion analysis service in a homecare/mHealth application. In the described approach, the developed emotion analysis service follows the IoT paradigm and it is combined with features for connectivity such as biosignal sensors and wearables, while it is fully integrated in the WebRTC video communication functionality offered by the homecare platform. Thus, it supports the medical experts to perform real-time analysis of their patients' emotional status during interactive video-conference sessions. The paper discusses the technical details of the implementation and the integration of the proposed service and provides initial results from its operation in practice.

On the Reusability of Sentiment Analysis Datasets in Applications with Dissimilar Contexts

The main goal of this paper is to evaluate the usability of several algorithms on various sentiment-labeled datasets. The process of creating good semantic vector representations for textual data is considered a very demanding task for the research community. The first and most important step of a Natural Language Processing (NLP) system, is text preprocessing, which greatly affects the overall accuracy of the classification algorithms. In this work, two vector space models are created, and a study consisting of a variety of algorithms, is performed on them. The work is based on the IMDb dataset which contains movie reviews along with their associated labels (positive or negative). The goal is to obtain the model with the highest accuracy and the best generalization. To measure how well these models generalize in other domains, several datasets, which are further analyzed later, are used.

An overview of platforms for cloud based development

This paper provides an overview of the state of the art technologies for software development in cloud environments. The surveyed systems cover the whole spectrum of cloud-based development including integrated programming environments, code repositories, software modeling, composition and documentation tools, and application management and orchestration. In this work we evaluate the existing cloud development ecosystem based on a wide number of characteristics like applicability (e.g. programming and database technologies supported), productivity enhancement (e.g. editor capabilities, debugging tools), support for collaboration (e.g. repository functionality, version control) and post-development application hosting and we compare the surveyed systems. The conducted survey proves that software engineering in the cloud era has made its initial steps showing potential to provide concrete implementation and execution environments for cloud-based applications. However, a number of important challenges need to be addressed for this approach to be viable. These challenges are discussed in the article, while a conclusion is drawn that although several steps have been made, a compact and reliable solution does not yet exist.

A novel tool for segmenting 3D medical images based on generalized cylinders and active surfaces

Three-dimensional (3D) medical imaging has been incorporated in routine clinical practice, since the required infrastructure has become increasingly affordable. New algorithms and applications are needed to serve the additional image processing and analysis functions in 3D space. In this work we propose a system for semi-automatic modeling and segmentation of elongated salient and anatomical objects in 3D medical images. The proposed methodology is based on a novel mathematical formalization of a well-known class of geometric primitives, namely generalized cylinders (GCs), which exhibits advantages over the existing parametric definition. Since the anatomical objects have to be modeled by their intersection with the transverse image planes, the proposed methodology includes also a new seeded region growing (SRG) segmentation algorithm for ellipse detection in 2D images, based on a priori shape knowledge. Finally, the resulting GC model is used to initialize an active surface (AS) segmentation method, in order to accurately delineate the required object. In this work we present the proposed algorithms in detail, along with the evaluation of the accuracy of the model-based segmentation by experts. Results show that elongated objects like the aorta and the trachea may be segmented with sensitivity between 90% and 95%. The proposed SRG-ellipse detector requires minimal user-initialization and its executions requires only few seconds for each image slice on an average laptop. The evolution of the AS requires less than one second per iteration for a typical CT image. Comparisons are provided with state of the art semi-automatic medical image processing software, which validate the merit of the proposed work.

A collaborative biomedical image mining framework: application on the image analysis of microscopic kidney biopsies

The analysis and characterization of biomedical image data is a complex procedure involving several processing phases, like data acquisition, preprocessing, segmentation, feature extraction and classification. The proper combination and parameterization of the utilized methods are heavily relying on the given image data set and experiment type. They may thus necessitate advanced image processing and classification knowledge and skills from the side of the biomedical expert. In this work, an application, exploiting web services and applying ontological modeling, is presented, to enable the intelligent creation of image mining workflows. The described tool can be directly integrated to the RapidMiner, Taverna or similar workflow management platforms. A case study dealing with the creation of a sample workflow for the analysis of kidney biopsy microscopy images is presented to demonstrate the functionality of the proposed framework.

Statistical data mining of streaming motion data for fall detection in assistive environments

The analysis of human motion data is interesting for the purpose of activity recognition or emergency event detection, especially in the case of elderly or disabled people living independently in their homes. Several techniques have been proposed for identifying such distress situations using either motion, audio or video sensors on the monitored subject (wearable sensors) or the surrounding environment. The output of such sensors is data streams that require real time recognition, especially in emergency situations, thus traditional classification approaches may not be applicable for immediate alarm triggering or fall prevention. This paper presents a statistical mining methodology that may be used for the specific problem of real time fall detection. Visual data captured from the user's environment, using overhead cameras along with motion data are collected from accelerometers on the subject's body and are fed to the fall detection system. The paper includes the details of the stream data mining methodology incorporated in the system along with an initial evaluation of the achieved accuracy in detecting falls.

Delineation and interpretation of gene networks towards their effect in cellular physiology- a reverse engineering approach for the identification of critical molecular players, through the use of ontologies

Exploiting ontologies, provides clues regarding the involvement of certain molecular processes in the cellular phenotypic manifestation. However, identifying individual molecular actors (genes, proteins, etc.) for targeted biological validation in a generic, prioritized, fashion, based in objective measures of their effects in the cellular physiology, remains a challenge. In this work, a new meta-analysis algorithm is proposed for the holistic interpretation of the information captured in -omic experiments, that is showcased in a transcriptomic, dynamic, DNA microarray dataset, which examines the effect of mastic oil treatment in Lewis lung carcinoma cells. Through the use of the Gene Ontology this algorithm relates genes to specific cellular pathways and vice versa in order to further reverse engineer the critical role of specific genes, starting from the results of various statistical enrichment analyses. The algorithm is able to discriminate candidate hub-genes, implying critical biochemical cross-talk. Moreover, performance measures of the algorithm are derived, when evaluated with respect to the differential expression gene list of the dataset.

Classification of apoptosis using advanced clustering techniques on digital microscopic images

Programmed cell death, also known as apoptosis is of fundamental importance in many biological processes and also highly associated with serious diseases like cancer and HIV. The current paper presents an innovative method for apoptosis phenomenon characterization based on apoptotic cell quantification and detection using active contours. Subsequently, we employ appropriate data mining techniques and perform characterization of apoptosis on digital microscopic images. A particular class of clustering algorithms, utilizing information driven by the Principal Component Analysis, has been very successful in dealing with such data. In this work, we employ a recently proposed clustering algorithm to solve this real world clustering task.

Classification of dermatological images using advanced clustering techniques

Computer vision-based diagnosis systems have been widely used in dermatology, aiming at the early detection of skin cancer and more specifically the recognition of malignant melanoma tumor. This paper proposes a novel clustering technique for the characterization and categorization of pigmented skin lesions in dermatological images. Appropriate image processing techniques (i.e. segmentation, border detection, color and texture processing) are utilized for feature extraction. The proposed method uses Principal Component Analysis and is considered appropriate, since it is suitable for problems with high dimensional data. Initial experimental results have proved the superiority of this method against traditional ones.

EmerLoc: Location-based services for emergency medical incidents

BACKGROUND

Recent developments in positioning systems and telecommunications have provided the technology needed for the development of location aware medical applications. We developed a system, named EmerLoc, which is based upon this technology and uses a set of sensors that are attached to the patient's body, a micro-computing unit which is responsible for processing the sensor readings and a central monitoring unit, which coordinates the data flow.

OBJECTIVE

To demonstrate that the proposed system is technically feasible and acceptable for the potential users.

METHOD

Transmission speed is assessed mostly by means of transmission of DICOM compliant images in various operational scenarios. The positioning functionality was established both outdoor using GPS and indoor using the UCLA Nibble system. User acceptability was assessed in a hospital setting by 15 physicians who filled in a questionnaire after having used the system in an experimental setting.

RESULTS

Transmission speeds ranged from 88kB/s for a IEEE 802.11 infrastructure to 2.5kB/s for a GSM/GPRS scenario. Positioning accuracy based on GPS was 5-10m. The physicians rated the technical aspects on average above 3 on a 5-point scale. Only the data presentation was assessed to be not satisfactory (2.81 on a 5-point scale).

CONCLUSION

The reported results prove the feasibility of the proposed architecture and its alignment with widely established practices and standards, while the reaction of potential users who evaluated the system is quite positive.

Medical Image Compression using Wavelet Transform on Mobile Devices with ROI coding support

Medical applications have already been integrated into mobile devices (e.g. Tablet PC's and PDA's) and are being used by medical personnel in treatment centers, for retrieving and examining patient data and medical images. Network transmission and image data processing are key issues in such platforms, due to the significant image file sizes. Wavelet transform has been considered to be a highly efficient technique of image compression resulting in both lossless and lossy compressed images of great accuracy, enabling its use on medical images. This paper discusses a Picture Archiving and Communication Systems (PACS) application designed for viewing DICOM compliant medical images using Wavelet compression with ROI coding support, on mobile devices. In addition, it presents initial results from its pilot application and demonstrates its performance over heterogeneous radio network segments, like IEEE 802.11b, GPRS and DVB-H.

An integrated computer supported acquisition, handling, and characterization system for pigmented skin lesions in dermatological images

This paper describes an integrated prototype computer-based system for the characterization of skin digital images. The first stage includes an image acquisition arrangement designed for capturing skin images, under reproducible conditions. The system processes the captured images and performs unsupervised image segmentation and image registration utilizing an efficient algorithm based on the log-polar transform of the images' Fourier spectrum. Border- and color-based features, extracted from the digital images of skin lesions, were used to construct a classification module for the recognition of malignant melanoma versus dysplastic nevus. Different methods, drawn from the fields of artificial intelligence (neural networks) and statistical modeling (discriminant analysis), were used in order to find the best classification rules and to compare the results of different approaches to the problem.

PKI-based secure mobile access to electronic health services and data

Recent research works examine the potential employment of public-key cryptography schemes in e-health environments. In such systems, where a Public Key Infrastructure (PKI) is established beforehand, Attribute Certificates (ACs) and public key enabled protocols like TLS, can provide the appropriate mechanisms to effectively support authentication, authorization and confidentiality services. In other words, mutual trust and secure communications between all the stakeholders, namely physicians, patients and e-health service providers, can be successfully established and maintained. Furthermore, as the recently introduced mobile devices with access to computer-based patient record systems are expanding, the need of physicians and nurses to interact increasingly with such systems arises. Considering public key infrastructure requirements for mobile online health networks, this paper discusses the potential use of Attribute Certificates (ACs) in an anticipated trust model. Typical trust interactions among doctors, patients and e-health providers are presented, indicating that resourceful security mechanisms and trust control can be obtained and implemented. The application of attribute certificates to support medical mobile service provision along with the utilization of the de-facto TLS protocol to offer competent confidentiality and authorization services is also presented and evaluated through experimentation, using both the 802.11 WLAN and General Packet Radio Service (GPRS) networks.