Ioannis Constantinou

An integrated CAD system facilitating the endometrial cancer diagnosis

In this study we present an integrated system for supporting the diagnosis of endometrial cancer. The system consists of an electronic patient record that incoporates a hysteroscopy imaging CAD system for the early detection of endometrial cancer. The electronic patient record is based on information collected from: appointments, patient info, hysteroscopy reporting and pharmacy. The CAD system is based on ROI manual or semi-automated extraction, texture feature computation and SVM and C4.5 classification into normal/abnormal. The highest percentage of correct classifications score (%CC) for the SVM classifier was 79% for the YCrCb color system using the SF+SGLDS texture feature sets for differentiating between normal vs abnormal ROIs. The C4.5 algorithm gave slightly lower classification scores, but also classification rules. The proposed system offers an integrated platform to the physician for assessing suspicious areas of endometrial cancer. However, further work is needed to validate the system with more cases and more users of the prototype.

Computer-Aided Diagnosis in Hysteroscopic Imaging

The paper presents the development of a computer-aided diagnostic (CAD) system for the early detection of endometrial cancer. The proposed CAD system supports reproducibility through texture feature standardization, standardized multifeature selection, and provides physicians with comparative distributions of the extracted texture features. The CAD system was validated using 516 regions of interest (ROIs) extracted from 52 subjects. The ROIs were equally distributed among normal and abnormal cases. To support reproducibility, the RGB images were first gamma corrected and then converted into HSV and YCrCb. From each channel of the gamma-corrected YCrCb, HSV, and RGB color systems, we extracted the following texture features: 1) statistical features (SFs), 2) spatial gray-level dependence matrices (SGLDM), and 3) gray-level difference statistics (GLDS). The texture features were then used as inputs with support vector machines (SVMs) and the probabilistic neural network (PNN) classifiers. After accounting for multiple comparisons, texture features extracted from abnormal ROIs were found to be significantly different than texture features extracted from normal ROIs. Compared to texture features extracted from normal ROIs, abnormal ROIs were characterized by lower image intensity, while variance, entropy, and contrast gave higher values. In terms of ROI classification, the best results were achieved by using SF and GLDS features with an SVM classifier. For this combination, the proposed CAD system achieved an 81% correct classification rate.

Electronic Health Record Application Support Service Enablers.

There is a huge need for open source software solutions in the healthcare domain, given the flexibility, interoperability and resource savings characteristics they offer. In this context, this paper presents the development of three open source libraries - Specific Enablers (SEs) for eHealth applications that were developed under the European project titled “Future Internet Social and Technological Alignment Research” (FI-STAR) funded under the “Future Internet Public Private Partnership” (FI-PPP) program. The three SEs developed under the Electronic Health Record Application Support Service Enablers (EHR-EN) correspond to: a) an Electronic Health Record enabler (EHR SE), b) a patient summary enabler based on the EU project “European patient Summary Open Source services” (epSOS SE) supporting patient mobility and the offering of interoperable services, and c) a Picture Archiving and Communications System (PACS) enabler (PACS SE) based on the dcm4che open source system for the support of medical imaging functionality. The EHR SE follows the HL7 Clinical Document Architecture (CDA) V2.0 and supports the Integrating the Healthcare Enterprise (IHE) profiles (recently awarded in Connectathon 2015). These three FI-STAR platform enablers are designed to facilitate the deployment of innovative applications and value added services in the health care sector. They can be downloaded from the FI-STAR cataloque website. Work in progress focuses in the validation and evaluation scenarios for the proving and demonstration of the usability, applicability and adaptability of the proposed enablers.

Evaluation of Spatial Dependence Matrices on Multiscale Instantaneous Amplitude for Mammogram Classification

Breast cancer is the most common cancer in women. Mammography is the only breast cancer screening method that has proven to be effective. Mammographic breast density is increasingly assessed towards the development of more personalized screening routines. This work presents the estimation of spatial dependence (SD) or otherwise called co-occurrence matrices on the Instantaneous Amplitude (IA) evaluated for different frequency scales using Amplitude-Modulation Frequency-Modulation (AM-FM) methods. Texture has been shown to be an important feature for mammographic image analysis. This multiscale texture analysis method captures both spatial and statistical information and is thus used to quantify image characteristics for breast density classification. AM-FM demodulation is used to estimate the IA at different frequency scales using multiscale Dominant Analysis. Following normalized SD matrices are evaluated on the IA estimates for each scale, for the segmented breast region, providing IA amplitude co-occurrence relative frequencies. These are used to represent the relative variations in the breast tissue, characteristic to the different breast density classes. Classification of a new mammogram into one of the density categories is achieved using the k-nearest neighbor method and the Euclidean distance metric. The method is evaluated using the Breast Imaging Reporting and Data System density classification on the Medical Image Analysis Society mammographic database and the results are presented and compared to other methods in the literature. The incorporation of IA spatial dependencies allows for breast density classification accuracy reaching over 82.5%. This classification accuracy is better using IA SD matrices when compared to IA histograms, warranting further investigation.

A comparison of color correction algorithms for endoscopic cameras

Quantitative color tissue analysis in endoscopy examinations requires color standardization procedures to be applied, so as to enable compatibility among computer aided diagnosis application from different endoscopy labs. The objective of this study was to examine the usefulness of different color correction algorithms (thus facilitating color standardization), evaluated on four different endoscopy cameras. The following five color correction algorithms were investigated: two gamma correction based algorithms (the classical and a modified one), and three (2nd, 3rd, and 4th order) polynomial based correction algorithms. The above algorithms were applied to four different endoscopy cameras: (a) Circon, (b) Karl-Stortz, (c) Olympus, and (d) Snowden-Pencer. The color correction algorithms and the endoscopic cameras evaluation, was carried out using the testing color palette (24 colors of known digital values) provided by the Edmund Industrial Optics Company. In summary, we have that: (a) the modified gamma correction algorithm gave significantly smaller mean square error compared to the other four algorithms, and (b) the smallest mean square error was obtained for the Circon camera. Future work will focus on evaluating the proposed color correction algorithm in different endoscopy clinics and compare their tissue characterization results.

An adaptive multiscale AM-FM texture analysis system with application to hysteroscopy imaging

The use of multiscale AM-FM analysis systems has been recently demonstrated in a variety of applications in medical image analysis. In all of these applications, a fixed filter-bank is used as a preprocessing step for estimating different AM-FM components from different scales. In this paper, for the first time, we introduce the use of an adaptive, multiscale AM-FM approach that searches for the optimal filter-bank specification for use in image classification. We demonstrate an example application in hysteroscopy imaging, for identification of gynaecological cancer, where the optimal filter-bank turns out to be circularly symmetric.

Reliable Hysteroscopy Color Imaging

The aim of this study was to investigate the reli- ability of two hysteroscopy cameras, the Circon IP 4 and Karl Storz HD, in relation to white balance, camera response over time, and color correction. Experimental results, show that for both the Circon and Karl Storz cameras: (i) for white balancing, either guaze, or white sheet, or the white color cheker can be used, (ii) white balance can be carried out at any distance between 0.5 to 3.0 cm, (iii) white balance can be carried out at 1cm and at any angle between 0 to 45 degrees, (iv) there was no camera color variation over both short (60 min) and long (4 weeks) time intervalls, and (v) color correction algorithm 2 gave better results. Most imortantantly, there was no significant difference between the MSE of the Circon and Storz cameras. The above results will be incorporated in a standardized protocol for texture feature analysis of endoscopic imaging for gyneacological cancer developed by our group, and will enable multi-center quantitative analysis (constrained by the use of the two cameras investigated).

TeleRehabilitation: A novel service oriented platform to support tele-supervised rehabilitation programs for ICU patients

This paper introduces a novel service oriented pilot platform developed to support Tele-Supervised rehabilitation programs for patients after hospitalization in Intensive Care Units. The platform is developed under the framework of the TeleRehabilitation project funded by the Cross Border Cooperation Programme Greece Cyprus 2007-2013 in order to successfully meet the main technological and clinical objectives of the project. The design and development of the platform is based on composite service architecture (aggregates smaller and fine-grained services such as Web Based applications, Clinical Information Systems and Video Communication Systems). The platform delivers sustainable, maintainable and high quality services and enables multiparty, interregional bidirectional audio/visual communication between clinical practitioners and post-ICU patients, enables patient group-based vital sign real time monitoring, individualized and group-based patient online training and patients clinical record bookkeeping.

Investigation of AM-FM methods for mammographic breast density classification

Breasts are composed of a mixture of fibrous and glandular tissue as well as adipose tissue and breast density describes the prevalence of fibroglandular tissue as it appears on a mammogram. Over the past few years, evaluation and reporting of breast density as it appears on mammograms has received a lot of attention because it impacts ones risk of developing breast cancer but also the capability of detecting breast cancer on mammograms. In addition, mammography fails in the identification of breast cancer in almost half of the women with dense breasts. Different image analysis methods have been investigated for automatic breast density classification. The presented method investigates the use of AmplitudeModulation Frequency-Modulation (AM-FM) multi-scale feature sets for characterization of breast density as the first step in the development of a density specific Computer Aided Detection System. AM-FM decompositions use different scales and bandpass filters to extract the instantaneous frequencies (IF), instantaneous amplitude (IA) and instantaneous phase (IP) components from an image. Normalized histograms of the maximum IA across all frequencies and scales are used to model the different breast density classes. Classification of a new mammogram into one of the breast density classes is achieved using the k-nearest neighbor method with k =5 and the euclidean distance metric. The method is evaluated on the Medical Image Analysis Society (MIAS) mammographic database and the results are presented. The presented method allows breast density classification accuracy reaching over 84%. Future work will involve a new AM-FM methodology approach based on adaptive filterbank design and performance index decision.

Multiscale AM-FM image reconstructions based on elastic net regression and Gabor filterbanks

The paper proposes the use of elastic net regression for reconstructing images from AM-FM components. Current AM-FM reconstruction methods are based on Dominant Component Analysis (DCA), multi-scale DCA, and Channel Component Analysis (CCA). The paper introduce a variation on CCA that uses elastic net regression to minimize the number of channels that are used in the reconstruction. The new approach is validated using a family of Gabor filterbanks that is parameterized by an overlap index. The results show that the elastic net regression component selection algorithm performs significantly better than multiscale DCA.