Search

This paper reports an experimental study designed for the in-depth investigation of how the radial basis function network (RBFN) estimates snow cover thickness as a function of climate and topographic parameters. The estimation problem is modeled in terms of both function regression and classification, obtaining continuous and discrete thickness values, respectively. The model is based on a minimal set of climatic and topographic data collected from a limited number of stations located in the Italian Central Alps. Several experiments have been conceived and conducted adopting different evaluation indexes. A comparison analysis was also developed for a quantitative evaluation of the advantages of the RBFN method over to conventional widely used spatial interpolation techniques when dealing with critical situations originated by lack of data and limited n-homogeneously distributed instrumented sites. The RBFN model proved competitive behavior and a valuable tool in critical situations in which conventional techniques suffer from a lack of representative data.

Reversible cerebral vasoconstriction syndrome (RCVS) is a complex and etiologically diverse neurovascular disorder that typically presents with severe thunderclap headaches (TCH) as the primary symptom, accompanied by reversible vasoconstriction of the cerebral arteries. The clinical course may include focal neurological deficits or epileptic seizures. There are two types: idiopathic RCVS and secondary RCVS, the latter triggered by various substances, medical interventions, or diseases. In clinical practice, various medical specialists may initially encounter this condition, underscoring the importance of accurate recognition and diagnosis of RCVS. The clinical course often appears monophasic and self-limiting, with recurrences reported in only 1.7% of cases annually. Complications such as cerebral hemorrhages and cerebral ischemia can lead to death in 5-10% of cases. This article utilizes a case study to explore RCVS, its complications, and the diagnostic procedures involved., (© 2024. The Author(s).)

Accurate and efficient segmentation of the whole brain in magnetic resonance (MR) images is a key task in many neuroscience and medical studies either because the whole brain is the final anatomical structure of interest or because the automatic extraction facilitates further analysis. The problem of segmenting brain MRI images has been extensively addressed by many researchers. Despite the relevant achievements obtained, automated segmentation of brain MRI imagery is still a challenging problem whose solution has to cope with critical aspects such as anatomical variability and pathological deformation. In the present paper, we describe and experimentally evaluate a method for segmenting brain from MRI images basing on two-dimensional graph searching principles for border detection. The segmentation of the whole brain over the entire volume is accomplished slice by slice, automatically detecting frames including eyes. The method is fully automatic and easily reproducible by computing the internal main parameters directly from the image data. The segmentation procedure is conceived as a tool of general applicability, although design requirements are especially commensurate with the accuracy required in clinical tasks such as surgical planning and post-surgical assessment. Several experiments were performed to assess the performance of the algorithm on a varied set of MRI images obtaining good results in terms of accuracy and stability., (Copyright © 2012 John Wiley & Sons, Ltd.)

In this study new evaluation strategies for comparing different Statistical Parametric Maps computed from fMRI time-series analysis software tools are proposed. The aim of our work is to assess and quantitatively evaluate the statistical agreement of activation maps. Some pre-processing steps are necessary to compare SPMs (Statistical Parametric Maps), including segmentation and co-registration. The study of the statistical agreement is carried out following two ways. The first way considers SPMs as the result of two classification processes and extracts confusion matrix and Cohen's kappa index to assess agreement. Some considerations will be made on the statistical dependence of classes and a new formulation of kappa index will be used for overcoming this problem. The second way considers SPMs as two 3D images, and computes the similarity of SPMs images with a fuzzy formulation of the Jaccard Index. Several experiments were conducted both to assess the performance of the proposed evaluation tools and to compare activation maps computation pipelines from two widely used software tools in a clinical context., (Copyright © 2013 Elsevier Inc. All rights reserved.)

Objective: To develop a general purpose web-based system for active support in using protocols., Methods: The conceptual model underlying the design of the overall decision support system is drawn from fuzzy set theory and fuzzy logic giving rise to a framework for both acquiring and representing descriptive and operational protocol knowledge. It has been conceived as a web application, designed and implemented according to the technological standards of Internet, in particular XML language and web services, to guarantee distributed functionalities for multicentric studies and the re-use of domain knowledge and problem solving strategies., Results: Solutions have been evaluated experimentally addressing the specific domain of Temporomandibular disorders (TMD) specializing the general purpose procedures to the dedicated "Research Diagnostic Criteria" (RDC)/TMD protocol. The accuracy of the system was correlated with a set of 50 clinically cases consecutively selected from the Gnatology Department. The results were consistent in 100% of cases. The systematic observation by physicians of both activated rules and diagnostic judgements identified and explicitly formalized additional diagnostic rules in the same context., Conclusions: Active protocol support based on fuzzy diagnostic reasoning and advanced web-based technologies shows great potentialities for the renewed role DSSs are called to play in the increasingly wide scale context of evidence-based medicine.

The corrosion casting method represents one of the most widely used technique to study the 3D microvascularization of many tissues, both in their normal and pathological conditions. For a long time this technique was used only to perform a qualitative evaluation of the images obtained by scanning electron microscopy (SEM). A quantitative evaluation of vascular parameters (e.g., interbranching and intervascular distances, angle measurements, lengths and diameters) was lacking, mainly because of the difficulties found in the measurement performed on 2D SEM images. Then, some authors reported a quantitative method based on the analyses of stereo-pair images that allowed precise morphometric measurements. To visualize the specimens in 3D, it was necessary to use red-green glasses. In this article we describe a new approach by which we can automatically obtain a 3D reconstruction of vascular cast specimen's surface directly from stereo-images. Moreover, we developed a software that performed micrometric measurements on the 3D construct generated from the stereo-pictures. In conclusion, implementing together these two softwares and applying them to corrosion casting samples made it possible to render in 3D the surface of corrosion cast as well as make quantitative measurements on the corrosion casts.

High-resolution, detailed 3D reconstructions of biological specimens obtained from scanning electron microscopy stereo-micrographs and proprietary software were compared with Tapping-Mode AFM datasets of the same fields. The reconstruction software implements several original solutions including a neural adaptive point-matching technique, the ability to build an irregular triangulated mesh rather than a regular orthogonal grid, and the ability to re-map one of the original images exactly onto the reconstructed surface. The technique was applied to human nerve tissue to obtain 1,424 x 968-pixel, texture-mapped datasets, which were subsequently compared against 512 x 512-pixel AFM datasets from the same viewfields. Accounting for the inherent differences of the two techniques, direct comparison revealed an excellent visual match. The correspondence was also quantified by calculating the cross-correlation coefficient between corresponding altimetric profiles in SEM and AFM data, which consistently exceeded a figure of 0.9, with a rate of point mismatch in the order of 0.01%. Research is still underway to improve the robustness of the technique when applied to arbitrary images, (Copyright 2005 Wiley-Liss, Inc.)

This paper shows how the AMDIS (Automated Medical Diagnosis with Intelligent Systems) integrated system can be employed to build a fuzzy medical expert system in the domain of postmenopausal osteoporosis. The fundamental aims of the expert system are to standardize knowledge and support physicians in the early detection of postmenopausal osteoporosis. A wide range of diagnostic situations has been considered for both categories of the disease, with judgments that range from disease is excluded to disease is definite. The salient aspects of the approach are the use of fuzzy logic as an analytic language for the representation and manipulation of knowledge and strategies and the integration of structured interview techniques and learning-by-example to address the knowledge acquisition task.