Near infrared image processing to quantitate and visualize oxygen saturation during vascular occlusion.

The assessment of microcirculation spatial heterogeneity on the hand skin is the main objective of this work. Near-infrared spectroscopy based 2D imaging is a non-invasive technique for the assessment of tissue oxygenation. The haemoglobin oxygen saturation images were acquired by a dedicated camera (Kent Imaging) during baseline, ischaemia (brachial artery cuff occlusion) and reperfusion. Acquired images underwent a preliminary restoration process aimed at removing degradations occurring during signal capturing. Then, wavelet transform based multiscale analysis was applied to identify edges by detecting local maxima and minima across successive scales. Segmentation of test areas during different conditions was obtained by thresholding-based region growing approach. The method identifies the differences in microcirculatory control of blood flow in different regions of the hand skin. The obtained results demonstrate the potential use of NIRS images for the clinical evaluation of skin disease and microcirculatory dysfunction.

Decision Making Concepts for the Remote, Personalized Evaluation of COPD Patients' Health Status.

INTRODUCTION: This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Neural Signals and Images". OBJECTIVES: This paper presents the main concepts of a decision making approach for the remote management of COPD patients based on the early detection of disease exacerbation episodes. METHODS: An e-diary card is defined to evaluate a number of physiological variables and clinical parameters acquired remotely by means of wearable and environmental sensors deployed in patients' long-stay settings. The automatic evaluation of the card results in a so-called Chronic Status Index (CSI) whose computation is tailored to patients' specific manifestation of the disease (i.e., patient's phenotype). The decision support method relies on a parameterized analysis of CSI variations so as to early detect worsening changes, identify exacerbation severity and track the patterns of recovery. RESULTS: A preliminary study, carried out in real settings with 30 COPD patients monitored at home, has shown the validity and sensitivity of the method proposed, which was effectively able to timely and correctly identify patients' critical situation. CONCLUSION: The preliminary results showed that the proposed e-diary card, which presents several novel features with respect to other solutions presented in the literature, can be practically used to remotely monitor COPD patients.

A knowledge editing service for multisource data management in remote health monitoring.

Remote Health Monitoring (RHM) programmes are being increasingly developed to face the pervasive diffusion of chronic diseases. RHM strongly relies on ICT intelligent platforms devised to remotely acquire multisource data, process these according to specific domain knowledge and support clinical decision making. However, since RHM domain is continuously evolving and the pertinent knowledge is not yet consolidated, there is a great demand for services and tools that allow the encoded knowledge to be modified and enriched. This paper presents a Knowledge Editing Service (KES), which aims at enabling clinicians to insert novel knowledge, in a controlled fashion, into an ICT intelligent platform. The solution proposed is innovative since it addresses synergistically peculiar issues related to (i) RHM knowledge format; (ii) controlled editing patterns; (iii) knowledge verification and (iv) cooperative knowledge editing. None of the existing methods and systems for knowledge authoring tackles all these aspects at the same time. A prototype of the KES has been implemented and evaluated in real operational conditions.

CHRONIOUS: an open, ubiquitous and adaptive chronic disease management platform for chronic obstructive pulmonary disease (COPD), chronic kidney disease (CKD) and renal insufficiency.

CHRONIOUS is an highly innovative Information and Communication Technologies (ICT) research Initiative that aspires to implement its vision for ubiquitous health and lifestyle monitoring. The 17 European project partners are strictly working together since February 2008 to realize and open platform to manage and monitor elderly patients with chronic diseases and many difficulties to reach hospital centers for routine controls. The testing activities will be done in Italy and Spain involving COPD (Chronic Obstructive Pulmonary Disease) and CKD (Chronic Kidney Disease) patients, these being widespread and highly expensive in terms of social and economic costs. Patients, equipped by wearable technologies and sensors and interacting with lifestyle interfaces, will be assisted by healthcare personnel able to check the health record and critical conditions through the Chronious platform data analysis and decision support system. Additionally, the new ontology based literature search engine will help the clinicians in the standardization of care delivery process. This paper is to present the main project objectives and its principal components from the intelligent system point of view.

Volumetric analysis of CT orbital images.

The determination of the volume of eye muscles is a problem of considerable interest in Graves' ophtalmopathy both with respect to the diagnostic quantisation of the disease and to the measured assessment of the effectiveness of pharmacological treatment. The aim of this research is to design and test an advanced method for processing computerised tomography (CT) orbital images in order to obtain a three-dimensional reconstruction of infra-orbital muscle structures and to analyse them from a morphometric viewpoint. CT images of subjects suffering from Graves' disease were acquired before and after pharmacological treatment with immunosuppressors. They were then processed along with CT images of an anatomical phantom of known volume and fusiform morphology in order to assess the reliability of the procedure and to calculate the effect of the different modalities of acquisition and processing of CT images on the error in volume calculation.

Deformation analysis of brain regions.

The analysis of 2D and 3D deformations applied to structures having non regular geometry is presented. Deformations are studied in order to understand complex dynamic problems coded into image sequences. In particular, methods have been developed suitable to control the reconstruction and the spatial deformation of cerebral structures, in their different aspects of morphometry, isometry and densitometry. Finally, a simulation process of brain deformation caused by a neoplasia in a real relevant clinical case has been performed.

An intelligent system for the diagnosis of complex images.

An intelligent system suitable to perform a computer aided diagnosis of complex images should have a knowledge base containing all information related both to the images to be interpreted and to their symbolic description. In this paper, a system able to classify unknown medical digital images into four classes is proposed (searched pathology recognized, searched pathology absent, different pathology from the searched one recognized, unknown pathology). A main component of this system is a knowledge base that, startling from information deduced from sample images, can be processed to create synthetic reference models that, in turn, permit the interpretation of real scenes. The system has been tested on digitized plain film of the thorax, in order to perform a computer-aided diagnosis of pneumothorax cases.

[Quantitative evaluation of the dynamics of the coronary wall in man: description of a new method based on tridimensional time-dependent reconstruction of intravascular ultrasonographic images]. / Valutazione quantitativa della dinamica della parete coronarica nell'uomo: descrizione di un nuovo metodo basato sulla ricostruzione tridimensionale tempo dipendente di immagini ecografiche intravascolari.

BACKGROUND: Intravascular ultrasound imaging provides information on vascular lumen and arterial wall structure and it has potential application in arterial wall dynamic study. The aim of this study was to develop a computer assisted system for analysing digitised cross sectional ultrasound images of coronaries to easily display and quantify coronary dynamic and its relationship with arterial wall morphology. METHODS AND RESULTS: To extract the anatomical regions of interest from the digitised sonograms, automatic image segmentation and interactive procedures for manual correction were implemented. This step included the recognition of the lumen edge and an analysis of gray level intensity of the wall. Subsequently, a virtual 3D reconstruction of lumen and vessel wall was done in a Cartesian system where the XY plane was parallel to each cross-sectional sonogram, while the Z axis corresponded to the acquisition time. The baricentre of vascular lumen was used as a reference for alignment. We obtained a cylinder-like solid representing the behavior of the arterial cross-sectional sonogram in time, with the possibility to look either at the wall or at the lumen. In this virtual solid it was possible to measure the variation of lumen area and of 16 hemidiameters; in addition, the derivatives of these values, allowing an estimate of the velocity of events, can be obtained. CONCLUSIONS: The described computerised system for the analysis of intravascular ultrasound images could become a very useful tool for 3D representation and quantitative monitoring of coronary compliance and their relationship with segmental arterial wall morphology.

[The evaluation of a digital system for the automatic analysis of the density of abdominal radiograms]. / Valutazione di un sistema digitale per l'analisi automatica delle densità nei radiogrammi dell'addome.

This paper reports the results of the evaluation of an automatic system developed to analyze radiographic densities. This system, called RADEN, has been implemented at the Institute for Information Processing of the Italian National Research Council in Pisa. Forty-three pairs of abdominal X-ray films were obtained before and after the administration of ionic iodate contrast medium (i.i.c.m.) during urographic examinations. The 86 X-ray films were acquired and digitized using a computer-controlled optoelectronic device with a sampling step ranging 125 microns to 250 microns. The resulting images were arrays of 512 x 512 pixels, each one quantified on a byte (256 gray levels). The computing system included a high-performance personal computer equipped with a video RAM board having built-in facilities for image processing and with an optical disk to archive the images. Automatic and semi-automatic procedures were developed to segment, recognize and classify the images and to characterize three homogeneous regions--i.e., bone, water and air. The output data were compared with the area values of the air densities computed directly on the X-ray films by a radiologist. Furthermore, both data sets were compared with the scores given in a blind study by four observers. The subsequent statistic analysis showed the increase in air density areas after i.i.c.m. administration and the applicability of the implemented system to the automatic examination of abdominal radiographic densities. The results encourage to believe that the proposed approach could be employed as a first step for the development of quite a more complex system oriented to X-ray image understanding and to assisted diagnosis.

Morphometric analysis of sonographic images by spatial geometric modeling.

A methodology able to derive spatial geometric models from input sequences of sonographic slices is proposed. The developed modeling procedure can be utilized to perform computer-assisted anatomic 3D analysis both on all echo space and selected subregions. The modeling procedure is mainly composed of three sequential phases: a) automatic acquisition and preprocessing of time sequences of 2D echotomograms; b) 3D reconstruction of images and computing of discrete distance maps of selected echoes according to predefined projective laws; and c) generation of a spatial geometric model of the examined object starting from the previously computed maps.

Decrease of diffusion of glycosylated albumin in retinal microcirculation by peptide fraction from bovine factor VIII.

The diffusion of the glycosylated albumin in the retinal vascular system has been studied in male New Zealand rabbits, using fluorangiographic techniques. A first group of animals was treated for 15 days with the peptide fraction from bovine Factor VIII (Vueffe); a second group, used as control group, was treated with physiological solution. At the end of treatment, glycosylated albumin was made fluorescent and then injected into the marginal vein of the rabbit. The direct observation and the photometric measurements performed on the digitized photograms with an image processing system showed a considerable reduction in retinic capillary diffusion of glycosylated albumin in the animals treated with the peptide fraction. The substance used in the study might therefore be of importance in the treatment of systemic disease with retinic vascular damage.