Development and Implementation of an Innovative Framework for Automated Radiomics Analysis in Neuroimaging.

Radiomics represents an innovative approach to medical image analysis, enabling comprehensive quantitative evaluation of radiological images through advanced image processing and Machine or Deep Learning algorithms. This technique uncovers intricate data patterns beyond human visual detection. Traditionally, executing a radiomic pipeline involves multiple standardized phases across several software platforms. This could represent a limit that was overcome thanks to the development of the matRadiomics application. MatRadiomics, a freely available, IBSI-compliant tool, features its intuitive Graphical User Interface (GUI), facilitating the entire radiomics workflow from DICOM image importation to segmentation, feature selection and extraction, and Machine Learning model construction. In this project, an extension of matRadiomics was developed to support the importation of brain MRI images and segmentations in NIfTI format, thus extending its applicability to neuroimaging. This enhancement allows for the seamless execution of radiomic pipelines within matRadiomics, offering substantial advantages to the realm of neuroimaging.

Development of a microfluidic-assisted open-source 3D bioprinting system (MOS3S) for the engineering of hierarchical tissues.

The engineering of new 3D bioprinting approaches has shown great promise in the field of tissue engineering and disease modelling. However, the high cost of commercial 3D bioprinters has limited their accessibility, especially to those laboratories in resource-limited settings. Moreover, the need for a 3D bioprinting system capable of dispensing multiple materials is growing apace. Therefore, the development of a Microfluidic-assisted Open Source 3D bioprinting System (MOS3S) for the engineering of hierarchical tissues is needed to progress in fabricating functional tissues, but with a technology accessible to a wider range of researchers. The MOS3S platform is designed to allow the deposition of biomaterial inks using microfluidic printheads or coaxial nozzles for the in-situ crosslinking and scaffolds fabrication. The coupling of 3D printed syringe pumps with the motion control system is used for driving the tunable extrusion of inks for the fabrication of centimeter scale hierarchical lattice constructs for tissue engineering purposes. MOS3S performance have been validated to fabricate high-resolution structures with coaxial microfluidic technology, opening to new frontiers for seminal studies in pre-clinical disease modelling and tissue regeneration.

Michelangelo Effect in Virtual Sculpturing: Prospective for Motor Neurorehabilitation in the Metaverse.

We investigated the Michelangelo effect, i.e. the facilitatory effect of a virtual art therapy in motor rehabilitation (Iosa et al. 2021), with a novel virtual reality paradigm in which users are engaged in motor exercises with 3D sculptures. In particular, thirty young adults were immersed in a virtual environment where they could sculpt, by using the real hands, some famous sculptures in the history of art, such as the David of Michelangelo, the Venus of Milo and the statue of Laocoon and His Sons, and their control stimuli, i.e. statues in very low resolution or cubes. We recorded the kinematics (length, the time to complete each trial, mean normalized jerk) and questionnaire answers (objective and subjective beauty, User Satisfaction Evaluation Questionnaire and Nasa Task Load Index). In general, we found that the perception of subjective and objective beauty was higher when sculpting the statues than control stimuli, the judgment of usability of the system was high. The perceived fatigue was not higher when sculpting the statues despite the longer time spent in completing the task that with respect to the control stimuli. Moreover, we found that the interaction with the experimental statues affected the fluidity and symmetry of hands movements. Finally, we discuss this evidence regarding the art therapy and neuroaesthetics principles for motor rehabilitation in the Metaverse with VR, including the possible role of virtual embodiment (illusory feeling to have a virtual body) for boosting the efficacy of the clinical applications.

A Critical Analysis of the Robustness of Radiomics to Variations in Segmentation Methods in 18F-PSMA-1007 PET Images of Patients Affected by Prostate Cancer.

BACKGROUND: Radiomics shows promising results in supporting the clinical decision process, and much effort has been put into its standardization, thus leading to the Imaging Biomarker Standardization Initiative (IBSI), that established how radiomics features should be computed. However, radiomics still lacks standardization and many factors, such as segmentation methods, limit study reproducibility and robustness. AIM: We investigated the impact that three different segmentation methods (manual, thresholding and region growing) have on radiomics features extracted from 18F-PSMA-1007 Positron Emission Tomography (PET) images of 78 patients (43 Low Risk, 35 High Risk). Segmentation was repeated for each patient, thus leading to three datasets of segmentations. Then, feature extraction was performed for each dataset, and 1781 features (107 original, 930 Laplacian of Gaussian (LoG) features, 744 wavelet features) were extracted. Feature robustness and reproducibility were assessed through the intra class correlation coefficient (ICC) to measure agreement between the three segmentation methods. To assess the impact that the three methods had on machine learning models, feature selection was performed through a hybrid descriptive-inferential method, and selected features were given as input to three classifiers, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Linear Discriminant Analysis (LDA), Random Forest (RF), AdaBoost and Neural Networks (NN), whose performance in discriminating between low-risk and high-risk patients have been validated through 30 times repeated five-fold cross validation. CONCLUSIONS: Our study showed that segmentation methods influence radiomics features and that Shape features were the least reproducible (average ICC: 0.27), while GLCM features the most reproducible. Moreover, feature reproducibility changed depending on segmentation type, resulting in 51.18% of LoG features exhibiting excellent reproducibility (range average ICC: 0.68-0.87) and 47.85% of wavelet features exhibiting poor reproducibility that varied between wavelet sub-bands (range average ICC: 0.34-0.80) and resulted in the LLL band showing the highest average ICC (0.80). Finally, model performance showed that region growing led to the highest accuracy (74.49%), improved sensitivity (84.38%) and AUC (79.20%) in contrast with manual segmentation.

Analysis of Connectome Graphs Based on Boundary Scale.

The purpose of this work is to advance in the computational study of connectome graphs from a topological point of view. Specifically, starting from a sequence of hypergraphs associated to a brain graph (obtained using the Boundary Scale model, BS2), we analyze the resulting scale-space representation using classical topological features, such as Betti numbers and average node and edge degrees. In this way, the topological information that can be extracted from the original graph is substantially enriched, thus providing an insightful description of the graph from a clinical perspective. To assess the qualitative and quantitative topological information gain of the BS2 model, we carried out an empirical analysis of neuroimaging data using a dataset that contains the connectomes of 96 healthy subjects, 52 women and 44 men, generated from MRI scans in the Human Connectome Project. The results obtained shed light on the differences between these two classes of subjects in terms of neural connectivity.

Model-Optimizing Radiofrequency Parameters of 3D Finite Element Analysis for Ablation of Benign Thyroid Nodules.

Radiofrequency (RF) ablation represents an efficient strategy to reduce the volume of thyroid nodules. In this study, a finite element model was developed with the aim of optimizing RF parameters, e.g., input power and treatment duration, in order to achieve the target volume reduction rate (VRR) for a thyroid nodule. RF ablation is modelled as a coupled electro-thermal problem wherein the electric field is applied to induce tissue heating. The electric problem is solved with the Laplace equation, the temperature distribution is estimated with the Pennes bioheat equation, and the thermal damage is evaluated using the Arrhenius equation. The optimization model is applied to RF electrode with different active tip lengths in the interval from 5 mm to 40 mm at the 5 mm step. For each case, we also explored the influence of tumour blood perfusion rate on RF ablation outcomes. The model highlights that longer active tips are more efficient as they require lesser power and shorter treatment time to reach the target VRR. Moreover, this condition is characterized by a reduced transversal ablation zone. In addition, a higher blood perfusion increases the heat dispersion, requiring a different combination of RF power and time treatment to achieve the target VRR. The model may contribute to an improvement in patient-specific RF ablation treatment.

Harnessing Biofabrication Strategies to Re-Surface Osteochondral Defects: Repair, Enhance, and Regenerate.

Osteochondral tissue (OC) is a complex and multiphasic system comprising cartilage and subchondral bone. The discrete OC architecture is layered with specific zones characterized by different compositions, morphology, collagen orientation, and chondrocyte phenotypes. To date, the treatment of osteochondral defects (OCD) remains a major clinical challenge due to the low self-regenerative capacity of damaged skeletal tissue, as well as the critical lack of functional tissue substitutes. Current clinical approaches fail to fully regenerate damaged OC recapitulating the zonal structure while granting long-term stability. Thus, the development of new biomimetic treatment strategies for the functional repair of OCDs is urgently needed. Here, we review recent developments in the preclinical investigation of novel functional approaches for the resurfacing of skeletal defects. The most recent studies on preclinical augmentation of OCDs and highlights on novel studies for the in vivo replacement of diseased cartilage are presented.

Effects on Corticospinal Tract Homology of Faremus Personalized Neuromodulation Relieving Fatigue in Multiple Sclerosis: A Proof-of-Concept Study.

OBJECTIVES: Fatigue in multiple sclerosis (MS) is a frequent and invalidating symptom, which can be relieved by non-invasive neuromodulation, which presents only negligible side effects. A 5-day transcranial direct-current stimulation, 15 min per day, anodically targeting the somatosensory representation of the whole body against a larger occipital cathode was efficacious against MS fatigue (fatigue relief in multiple sclerosis, Faremus treatment). The present proof-of-concept study tested the working hypothesis that Faremus S1 neuromodulation modifies the homology of the dominant and non-dominant corticospinal (CST) circuit recruitment. METHODS: CST homology was assessed via the Fréchet distance between the morphologies of motor potentials (MEPs) evoked by transcranial magnetic stimulation in the homologous left- and right-hand muscles of 10 fatigued MS patients before and after Faremus. RESULTS: In the absence of any change in MEP features either as differences between the two body sides or as an effect of the treatment, Faremus changed in physiological direction the CST's homology. Faremus effects on homology were more evident than recruitment changes within the dominant and non-dominant sides. CONCLUSIONS: The Faremus-related CST changes extend the relevance of the balance between hemispheric homologs to the homology between body sides. With this work, we contribute to the development of new network-sensitive measures that can provide new insights into the mechanisms of neuronal functional patterning underlying relevant symptoms.

3D Tortuosity and Diffusion Characterization in the Human Mineralized Collagen Fibril Using a Random Walk Model.

Bone tissue is mainly composed at the nanoscale of apatite minerals, collagen molecules and water that form the mineralized collagen fibril (MCF). In this work, we developed a 3D random walk model to investigate the influence of bone nanostructure on water diffusion. We computed 1000 random walk trajectories of water molecules within the MCF geometric model. An important parameter to analyse transport behaviour in porous media is tortuosity, computed as the ratio between the effective path length and the straight-line distance between initial and final points. The diffusion coefficient is determined from the linear fit of the mean squared displacement of water molecules as a function of time. To achieve more insight into the diffusion phenomenon within MCF, we estimated the tortuosity and diffusivity at different quotes in the longitudinal direction of the model. Tortuosity is characterized by increasing values in the longitudinal direction. As expected, the diffusion coefficient decreases as tortuosity increases. Diffusivity outcomes confirm the findings achieved by experimental investigations. The computational model provides insights into the relation between the MCF structure and mass transport behaviour that may contribute to the improvement of bone-mimicking scaffolds.

Augmented Virtual Reality in Vestibular Assessment: A Dynamic Gait Application.

INTRODUCTION: Dizziness is a common complaint affecting up to 23% of the world population. Diagnosis is of utmost importance and routinely involves several tests to be performed in specialized centers. The advent of a new generation of technical devices would make envision their use for a valid objective vestibular assessment. Microsoft HoloLens 2 (HL2) mixed reality headset has the potential to be a valuable wearable technology that provides interactive digital stimuli and inertial measurement units (IMUs) to objectively quantify the movements of the user in response to various exercises. The aim of this study was to validate the integration of HoloLens with traditional methods used to analyze the vestibular function in order to obtain precise diagnostic values. METHODS: Twenty-six healthy adults completed the Dynamic Gait Index tests both with a traditional evaluation and while wearing HL2 headset, thus allowing to collect kinematic data of the patients' head and eyes. The subjects had to perform 8 different tasks, and the scores were independently assigned by two otolaryngology specialists. RESULTS: The maximum of the mean position of the walking axis of the subjects was found in the second task (-0.14 ± 0.23 m), while the maximum value of the standard deviation of the walking axis was found in the fifth task (-0.12 ± 0.27 m). Overall, positive results were obtained in regard to the validity of the HL2 use to analyze kinematic features. CONCLUSION: The accurate quantification of gait, movement along the walking axis, and deviation from the normality using HL2 provide an initial evidence for its useful adoption as a valuable tool in gait and mobility assessment.

Phenotyping the Histopathological Subtypes of Non-Small-Cell Lung Carcinoma: How Beneficial Is Radiomics?

The aim of this study was to investigate the usefulness of radiomics in the absence of well-defined standard guidelines. Specifically, we extracted radiomics features from multicenter computed tomography (CT) images to differentiate between the four histopathological subtypes of non-small-cell lung carcinoma (NSCLC). In addition, the results that varied with the radiomics model were compared. We investigated the presence of the batch effects and the impact of feature harmonization on the models' performance. Moreover, the question on how the training dataset composition influenced the selected feature subsets and, consequently, the model's performance was also investigated. Therefore, through combining data from the two publicly available datasets, this study involves a total of 152 squamous cell carcinoma (SCC), 106 large cell carcinoma (LCC), 150 adenocarcinoma (ADC), and 58 no other specified (NOS). Through the matRadiomics tool, which is an example of Image Biomarker Standardization Initiative (IBSI) compliant software, 1781 radiomics features were extracted from each of the malignant lesions that were identified in CT images. After batch analysis and feature harmonization, which were based on the ComBat tool and were integrated in matRadiomics, the datasets (the harmonized and the non-harmonized) were given as an input to a machine learning modeling pipeline. The following steps were articulated: (i) training-set/test-set splitting (80/20); (ii) a Kruskal-Wallis analysis and LASSO linear regression for the feature selection; (iii) model training; (iv) a model validation and hyperparameter optimization; and (v) model testing. Model optimization consisted of a 5-fold cross-validated Bayesian optimization, repeated ten times (inner loop). The whole pipeline was repeated 10 times (outer loop) with six different machine learning classification algorithms. Moreover, the stability of the feature selection was evaluated. Results showed that the batch effects were present even if the voxels were resampled to an isotropic form and whether feature harmonization correctly removed them, even though the models' performances decreased. Moreover, the results showed that a low accuracy (61.41%) was reached when differentiating between the four subtypes, even though a high average area under curve (AUC) was reached (0.831). Further, a NOS subtype was classified as almost completely correct (true positive rate ~90%). The accuracy increased (77.25%) when only the SCC and ADC subtypes were considered, as well as when a high AUC (0.821) was obtained-although harmonization decreased the accuracy to 58%. Moreover, the features that contributed the most to models' performance were those extracted from wavelet decomposed and Laplacian of Gaussian (LoG) filtered images and they belonged to the texture feature class.. In conclusion, we showed that our multicenter data were affected by batch effects, that they could significantly alter the models' performance, and that feature harmonization correctly removed them. Although wavelet features seemed to be the most informative features, an absolute subset could not be identified since it changed depending on the training/testing splitting. Moreover, performance was influenced by the chosen dataset and by the machine learning methods, which could reach a high accuracy in binary classification tasks, but could underperform in multiclass problems. It is, therefore, essential that the scientific community propose a more systematic radiomics approach, focusing on multicenter studies, with clear and solid guidelines to facilitate the translation of radiomics to clinical practice.

A Proof of Concept Combined Using Mixed Reality for Personalized Neurorehabilitation of Cerebellar Ataxic Patients.

BACKGROUND: Guidelines for degenerative cerebellar ataxia neurorehabilitation suggest intensive coordinative training based on physiotherapeutic exercises. Scientific studies demonstrate virtual exergaming therapeutic value. However, patient-based personalization, post processing analyses and specific audio-visual feedbacks are not provided. This paper presents a wearable motion tracking system with recording and playback features. This system has been specifically designed for ataxic patients, for upper limbs coordination studies with the aim to retrain movement in a neurorehabilitation setting. Suggestions from neurologists and ataxia patients were considered to overcome the shortcomings of virtual systems and implement exergaming. METHODS: The system consists of the mixed-reality headset Hololens2 and a proprietary exergaming implemented in Unity. Hololens2 can track and save upper limb parameters, head position and gaze direction in runtime. RESULTS: Data collected from a healthy subject are reported to demonstrate features and outputs of the system. CONCLUSIONS: Although further improvements and validations are needed, the system meets the needs of a dynamic patient-based exergaming for patients with cerebellar ataxia. Compared with existing solutions, the mixed-reality system is designed to provide an effective and safe therapeutic exergaming that supports both primary and secondary goals of an exergaming: what a patient should do and how patient actions should be performed.

A Comparative Study on a Novel Quality Assessment Protocol Based on Image Analysis Methods for Color Doppler Ultrasound Diagnostic Systems.

Color Doppler (CD) imaging is widely used in diagnostics since it allows real-time detection and display of blood flow superimposed on the B-mode image. Nevertheless, to date, a shared worldwide standard on Doppler equipment testing is still lacking. In this context, the study herein proposed would give a contribution focusing on the combination of five test parameters to be included in a novel Quality Assessment (QA) protocol for CD systems testing. A first approach involving the use of the Kiviat diagram was investigated, assuming the diagram area, normalized with respect to one of the gold standards, as an index of the overall Doppler system performance. The QA parameters were obtained from the post-processing of CD data through the implementation of custom-written image analysis methods and procedures, here applied to three brand-new high-technology-level ultrasound systems. Experimental data were collected through phased and convex array probes, in two configuration settings, by means of a Doppler flow phantom set at different flow rate regimes. The outcomes confirmed that the Kiviat diagram might be a promising tool applied to quality controls of Doppler equipment, although further investigations should be performed to assess the sensitivity and specificity of the proposed approach.

Inside the Michelangelo effect: The role of art and aesthetic attractiveness on perceived fatigue and hand kinematics in virtual painting.

It has recently been discovered that during a virtual reality task of painting, if the subjects have the illusion of recreating an artistic masterpiece, they improve their performances and perceive less fatigue compared to simply coloring a virtual canvas. This phenomenon has been called the Michelangelo effect. However, it was unclear if this effect was related to the aesthetic experience of beauty or if it was specific to artistic stimuli. To clarify this point, 26 healthy subjects performed the virtual task of erasing a blank sheet on the canvas, revealing an image that could be a painting or a photo, classified as beautiful or not. Beautiful paintings were famous artistic portraits, non-beautiful paintings were rough reproductions of them. Photos of popular people were matched with paintings according to their similarity for somatic traits, posture, and clothes. Beautiful and non-beautiful photos were classified according to whether the pictured person was famous or not for their beauty. For each stimulus the objective beauty, subjective beauty, and effort to complete the task perceived by the subject were self-assessed on a numerical rating scale, recorded and analyzed. Furthermore, the hand kinematic trajectory was instrumentally recorded and its spatiotemporal parameters were computed. Less fatigue was perceived for the paintings than for the photos (p = .020), but not for beautiful versus non-beautiful stimuli (p = .325). Only in the artistic stimuli, subjective beauty was found to be negatively correlated with perceived fatigue (p = .030) and performed errors (p = .005). The kinematic parameters were found to be affected by the interactions between the gender of the participant and that of the person in the photo. These results supported the idea that the Michelangelo effect was stronger when subjects interacted with artefacts, modulated by the perceived beauty of the artistic stimulus.

matRadiomics: A Novel and Complete Radiomics Framework, from Image Visualization to Predictive Model.

Radiomics aims to support clinical decisions through its workflow, which is divided into: (i) target identification and segmentation, (ii) feature extraction, (iii) feature selection, and (iv) model fitting. Many radiomics tools were developed to fulfill the steps mentioned above. However, to date, users must switch different software to complete the radiomics workflow. To address this issue, we developed a new free and user-friendly radiomics framework, namely matRadiomics, which allows the user: (i) to import and inspect biomedical images, (ii) to identify and segment the target, (iii) to extract the features, (iv) to reduce and select them, and (v) to build a predictive model using machine learning algorithms. As a result, biomedical images can be visualized and segmented and, through the integration of Pyradiomics into matRadiomics, radiomic features can be extracted. These features can be selected using a hybrid descriptive-inferential method, and, consequently, used to train three different classifiers: linear discriminant analysis, k-nearest neighbors, and support vector machines. Model validation is performed using k-fold cross-Validation and k-fold stratified cross-validation. Finally, the performance metrics of each model are shown in the graphical interface of matRadiomics. In this study, we discuss the workflow, architecture, application, future development of matRadiomics, and demonstrate its working principles in a real case study with the aim of establishing a reference standard for the whole radiomics analysis, starting from the image visualization up to the predictive model implementation.

Prognostic value of texture analysis of the primary tumour in high-risk neuroblastoma: An 18 F-DOPA PET study.

PURPOSE: To evaluate the prognostic value of texture analysis of the primary tumour with 18 fluorine-dihydroxyphenylalanine positron emission tomography/X-ray computed tomography (18 F-DOPA PET/CT) in patients affected by high-risk neuroblastoma (HR-NBL). METHODS: We retrospectively analysed 18 patients with HR-NBL, which had been prospectively enrolled in the course of a previous trial investigating the diagnostic role of 18 F-DOPA PET/CT at the time of the first onset. Texture analysis of the primary tumour was carried out on the PET images using LifeX. Conventional indices, histogram parameters, grey level co-occurrence (GLCM), run-length (GLRLM), neighbouring difference (NGLDM) and zone-length (GLZLM) matrices parameter were extracted; their values were compared with the overall metastatic load, expressed by means of whole-body metabolic burden (WBMB) score and the progression-free/overall survival (PFS and OS). RESULTS: There was a direct correlation between WBMB and radiomics parameter describing uptake intensity (SUVmean : p = .004) and voxel heterogeneity (entropy: p = .026; GLCM_Contrast: p = .001). Conversely, texture indices of homogeneity showed an inverse correlation with WBMB (energy: p = .026; GLCM_Homogeneity: p = .006). On the multivariate model, WBMB (p < .01) and the first standardised uptake value (SUV) quartile (p < .001) predicted PFS; OS was predicted by WBMB and the N-myc proto-oncogene protein (MYCN) amplification (p < .05) for both. CONCLUSIONS: Textural parameters describing heterogeneity and metabolic intensity of the primary HR-NBL are closely associated with its overall metastatic burden. In turn, the whole-body tumour load appears to be one of the most relevant predictors of progression-free and overall survival.

Role of Dynamic Parameters of 18F-DOPA PET/CT in Pediatric Gliomas.

PURPOSE OF THE REPORT: PET with 18F-DOPA can be used to evaluate grading and aggressiveness of pediatric cerebral gliomas. However, standard uptake parameters may underperform in circumscribed lesions and in diffuse pontine gliomas. In this study, we tested whether dynamic 18F-DOPA PET could overcome these limitations. PATIENTS AND METHODS: Patients with available dynamic 18F-DOPA PET were included retrospectively. Static parameters (tumor/striatum ratio [T/S] and tumor/cortex ratio [T/N]) and dynamic ones, calculated on the tumor time activity curve (TAC), including time-to-peak (TTP), slope steepness, the ratio between tumor and striatum TAC steepness (dynamic slope ratio [DSR]), and TAC shape (accumulation vs plateau), were evaluated as predictors of high/low grading (HG and LG) and of progression-free survival and overall survival. RESULTS: Fifteen patients were included; T/S, T/N, TTP, TAC slope steepness, and DSR were not significantly different between HG and LG. The accumulation TAC shape was more prevalent in the LG than in the HG group (75% vs 27%). On progression-free survival univariate analysis, TAC accumulation shape predicted longer survival (P < 0.001), whereas T/N and DSR showed borderline significance; on multivariate analyses, only TAC shape was retained (P < 0.01, Harrell C index, 0.93-0.95). On overall survival univariate analysis, T/N (P < 0.05), DSR (P < 0.05), and TAC "accumulating" shape predicted survival (P < 0.001); once more, only this last parameter was retained in the multivariate models (P < 0.05, Harrell C index, 0.86-0.89). CONCLUSIONS: Dynamic 18F-DOPA PET analysis outperforms the static parameter evaluation in grading assessment and survival prediction. Evaluation of the curve shape is a simple-to-use parameter with strong predictive power.

Validation of SuPerSense, a Sensorized Surface for the Evaluation of Posture Perception in Supine Position.

This study aimed to validate a sensorized version of a perceptive surface that may be used for the early assessment of misperception of body midline representation in subjects with right stroke, even when they are not yet able to stand in an upright posture. This device, called SuPerSense, allows testing of the load distribution of the body weight on the back in a supine position. The device was tested in 15 patients with stroke, 15 age-matched healthy subjects, and 15 young healthy adults, assessing three parameters analogous to those conventionally extracted by a baropodometric platform in a standing posture. Subjects were hence tested on SuPerSense in a supine position and on a baropodometric platform in an upright posture in two different conditions: with open eyes and with closed eyes. Significant correlations were found between the lengths of the center of pressure path with the two devices in the open-eyes condition (R = 0.44, p = 0.002). The parameters extracted by SuPerSense were significantly different among groups only when patients were divided into those with right versus left brain damage. This last result is conceivably related to the role of the right hemisphere of the brain in the analysis of spatial information.

Effects of a posture shirt with back active correction keeper on static and dynamic balance in Parkinson's disease.

BACKGROUND: Patients with Parkinson's disease (PD) suffer from postural disorders. This study aims at investigating the short- and medium-term effects of a shirt with appropriate tie-rods that allows to correct the posture of the trunk. METHODS: This is a longitudinal clinical study in which a pressure platform was used to assess the static and dynamic baropodometry and the static stabilometry of 20 patients with PD (70.95 ± 8.39 years old; 13 males, time from the onset of symptoms: 6.95 ± 4.04 years, Unified Parkinson's Disease Rating Scale score: UPDRS = 7.25 ± 6.26) without and with a shirt, specifically designed for improving posture, at baseline and after one month of wearing. RESULTS: The results showed a significant improvement in symmetry of loads (p = 0.015) and an enlargement of the foot contact surface (p = 0.038). A significant correlation was found between the change in forefoot load and time spent daily in wearing the shirt (R = 0.575, p = 0.008), with an optimal value identified at 8 h per day. CONCLUSION: The use of a postural shirt in patients with PD symmetrized the postural load and enlarged the foot contact surface improving their balance.

Artificial Intelligence in Thyroid Field-A Comprehensive Review.

Artificial intelligence (AI) uses mathematical algorithms to perform tasks that require human cognitive abilities. AI-based methodologies, e.g., machine learning and deep learning, as well as the recently developed research field of radiomics have noticeable potential to transform medical diagnostics. AI-based techniques applied to medical imaging allow to detect biological abnormalities, to diagnostic neoplasms or to predict the response to treatment. Nonetheless, the diagnostic accuracy of these methods is still a matter of debate. In this article, we first illustrate the key concepts and workflow characteristics of machine learning, deep learning and radiomics. We outline considerations regarding data input requirements, differences among these methodologies and their limitations. Subsequently, a concise overview is presented regarding the application of AI methods to the evaluation of thyroid images. We developed a critical discussion concerning limits and open challenges that should be addressed before the translation of AI techniques to the broad clinical use. Clarification of the pitfalls of AI-based techniques results crucial in order to ensure the optimal application for each patient.