(1) Background: The purpose of this study is to evaluate the impact of an augmented reality navigation system (SIRIO) for percutaneous biopsies and ablative treatments on bone lesions, compared to a standard CT-guided technique. (2) Methods: Bioptic and ablative procedures on bone lesions were retrospectively analyzed. All procedures were divided into SIRIO and Non-SIRIO groups and in <2 cm and >2 cm groups. Number of CT-scans, procedural time and patient’s radiation dose were reported for each group. Diagnostic accuracy was obtained for bioptic procedures. (3) Results: One-hundred-ninety-three procedures were evaluated: 142 biopsies and 51 ablations. Seventy-four biopsy procedures were performed using SIRIO and 68 under standard CT-guidance; 27 ablative procedures were performed using SIRIO and 24 under standard CT-guidance. A statistically significant reduction in the number of CT-scans, procedural time and radiation dose was observed for percutaneous procedures performed using SIRIO, in both <2 cm and >2 cm groups. The greatest difference in all variables examined was found for procedures performed on lesions <2 cm. Higher diagnostic accuracy was found for all SIRIO-assisted biopsies. No major or minor complications occurred in any procedures. (4) Conclusions: The use of SIRIO significantly reduces the number of CT-scans, procedural time and patient’s radiation dose in CT-guided percutaneous bone procedures, particularly for lesions <2 cm. An improvement in diagnostic accuracy was also achieved in SIRIO-assisted biopsies.

The employment of image processing techniques The problem of evaluating the shaped or textured information appean to he wide-spmading in several application amas, with content of a digitalised image has been frequently tackled in reference 10 Ihe medica1 context. In this p a w a nenro-literature and different methods have heen proposed [3], [7], fuzzy approach for pixel classification is detailed and its ap- [12]. Most of them are characterised by the need of some plication is proposed lo the analysis of dermatological images of nevi. A,, of is provided to kind of knowledge insertion (e.g. threshold definition) and demonstrate the usefulness of the introduced methodology and are not able to perform 3 simultaneous discernment between lo show the possible benefits deriving from its employment in contour, texture and regular points (generally each technique is devoted to the identification of a single image feature). clinical diagnosis.The approach we are going to discuss, in contrast, performs I. INTRODUCTIONa classification involving all the pixel categories together. Computer images have come to occupy a dominant part Moreover, the employment of a neuro-fuzzy strategy brings of the computer culture and the established research fields of forward additional benefits, since the comprehensibility of image analysis and processing attract the interest of scien-fuzzy models finds profitable combination when coupled with tists from different domains. The development of computer-the learning capabilities of neural networks. In this way a fuzzy supported systems for clinical diagnosis represents an issue rule base for pixel classification can be derived using solely a of increasing importance: the wedding of classical medical set of observational data, without any expert intervention. knowledge with new technology achievements produced -In the present work we describe a neuro-fuzzy approach for and continuously produces -successful developments and pixel classification with application to the analysis of dermaresults. The image processing challenge consists in tackling tological images. Studies have been conducted to investigate the vagueness and uncertainty typical of data involved in real-the possibility of detecting melanomas using image analysis world problems.techniques and the development of computer-supported sys-In this paper we aim at applying an approach to computer-tems for melanoma diagnosis results of increasing importance. supported diagnosis in dermatology based on Fuzzy Image On the one hand, the diagnosis of this kind of cancer is Processing (FIP) techniques. FIP is intended to understand, difficult and requires a well-trained dermatologist, since the represent, process an image and its features as fuzzy sets [26] early lesions can have a benign appearance: studies show that and it is not a unique theory, but a collection of different the diagnostic accuracy of early melanomas ranges between approaches. The reasons for the employment of fuzzy tech-30% and 75% [9]. On the other hand, it is a major issue in ...

Background: Coronavirus disease 2019 (COVID-19) pneumonia and immune checkpoint inhibitor (ICI) therapy-related pneumonitis share common features. The aim of this study was to determine on chest computed tomography (CT) images whether a deep convolutional neural network algorithm is able to solve the challenge of differential diagnosis between COVID-19 pneumonia and ICI therapy-related pneumonitis. Methods: We enrolled three groups: a pneumonia-free group (n = 30), a COVID-19 group (n = 34), and a group of patients with ICI therapy-related pneumonitis (n = 21). Computed tomography images were analyzed with an artificial intelligence (AI) algorithm based on a deep convolutional neural network structure. Statistical analysis included the Mann–Whitney U test (significance threshold at p < 0.05) and the receiver operating characteristic curve (ROC curve). Results: The algorithm showed low specificity in distinguishing COVID-19 from ICI therapy-related pneumonitis (sensitivity 97.1%, specificity 14.3%, area under the curve (AUC) = 0.62). ICI therapy-related pneumonitis was identified by the AI when compared to pneumonia-free controls (sensitivity = 85.7%, specificity 100%, AUC = 0.97). Conclusions: The deep learning algorithm is not able to distinguish between COVID-19 pneumonia and ICI therapy-related pneumonitis. Awareness must be increased among clinicians about imaging similarities between COVID-19 and ICI therapy-related pneumonitis. ICI therapy-related pneumonitis can be applied as a challenge population for cross-validation to test the robustness of AI models used to analyze interstitial pneumonias of variable etiology.

Background: Augmented reality navigation system for percutaneous computed tomography (CT)-guided pulmonary biopsies has recently been introduced. There are no studies in literature about its use for ground glass lesions biopsies. The aim of this study is to evaluate the effectiveness of an augmented reality infrared navigation system performance on CT-guided percutaneous lung ground glass opacity (GGO) biopsy compared to a standard CT-guided technique.Methods: A total of 80 patients with lung GGO who underwent to a percutaneous CT-guided lung biopsy with an augmented reality infrared navigation system were retrospectively enrolled in the study. Comparison was performed with a group of 80 patients who underwent to lung biopsy with the standard CT-guided technique. Evaluation of maximum lesion diameter (MLD), distance between lesion and pleural surface (DPS), distance travelled by the needle (DTP), procedural time, validity of histological sample, procedural complications and the radiation dose to the patient's chest were recorded for each patient of both groups. In addition, each group was divided into two subgroups based on lesion size, according to a cut-off of 1.5 cm (<1.5 cm; ≥1.5 cm).Results: Augmented reality navigation system showed a significant reduction in procedural time, radiation dose administrated to patients and complications rate compared to a standard CT-guided technique.Technical success was achieved in the 100% of cases in both groups, but the diagnostical success was higher in the group where patients underwent to lung biopsies with the use of navigation system. We also found that using an augmented reality navigation system increases the diagnostical success rate for lesion <1.5 cm.MLD, DPS and DTP did not differ significantly between the two groups of patients. Conclusions:The use of an augmented reality navigation system for percutaneous CT-guided pulmonary GGO biopsies has demonstrated a lower incidence of post-procedural complications, a significantly reduction of the radiation dose administered to patients and a higher diagnostical success rate.

Background:The aim of the study was to analyze the relationship between patient characteristics, including anagraphic and laboratoristic data and amount of adipose tissue measured in computed tomography (CT) scans in coronavirus disease 2019 (COVID-19) patients, and incidence of soft tissue bleeding requiring medical and/or interventional radiology management.Methods: A total of 132 patients hospitalized for COVID-19 pathology from October 2020 to May 2021 were included in the study and divided into two groups: a bleeding group of 70 cases with soft tissue bleeding occurring during hospitalization, and a control group of 62 hospitalized COVID-19 patients without bleeding events. In the bleeding group, two subgroups were considered: an embolization group including soft tissue bleeding cases requiring interventional radiology with transarterial embolization (TAE) (16/70; 22.9%) and a non-embolization group, clinically managed without TAE (54/70; 77.1%). Demographics and clinical data, visceral adipose tissue (VAT) area and subcutaneous adipose tissue (SAT) area measured on CT images and VAT/SAT ratio were compared between bleeding and control groups and between embolization and non-embolization subgroups.Results: Bleeding and control groups did not significantly differ for sex distribution, COVID-19, platelet (PLT) count, international normalized ratio (INR), SAT area, VAT area, and VAT/SAT ratio. Embolization and non-embolization groups did not significantly differ for age, COVID-19, PLT count, INR, SAT area, and VAT/SAT ratio.Bleeding group had lower body mass index (BMI) than control group as well as embolization group compared to non-embolization group. A statistically significant difference was observed between embolization and non-embolization groups for VAT area, with smaller values in embolization group (mean difference: 64.2 cm 2 , 95% confidence interval: 8.3 -120.1; P < 0.05). Conclusion:Soft tissue bleeding in COVID-19 is more frequent and severe in patients with low amount of VAT, demonstrating that fat mass may have a containing function on bleeding, limiting its progression in surrounding structures. There are some other factors that influence the risk of bleeding, such as age, thromboprophylaxis therapy and BMI.