(1) Background: Computed tomography (CT) plays a paramount role in the characterization and follow-up of COVID-19. Several score systems have been implemented to properly assess the lung parenchyma involved in patients suffering from SARS-CoV-2 infection, such as the visual quantitative assessment score (VQAS) and software-based quantitative assessment score (SBQAS) to help in managing patients with SARS-CoV-2 infection. This study aims to investigate and compare the diagnostic accuracy of the VQAS and SBQAS with two different types of software based on artificial intelligence (AI) in patients affected by SARS-CoV-2. (2) Methods: This is a retrospective study; a total of 90 patients were enrolled with the following criteria: patients' age more than 18 years old, positive test for COVID-19 and unenhanced chest CT scan obtained between March and June 2021. The VQAS was independently assessed, and the SBQAS was performed with two different artificial intelligence-driven software programs (Icolung and CT-COPD). The Intraclass Correlation Coefficient (ICC) statistical index and Bland-Altman Plot were employed. (3) Results: The agreement scores between radiologists (R1 and R2) for the VQAS of the lung parenchyma involved in the CT images were good (ICC = 0.871). The agreement score between the two software types for the SBQAS was moderate (ICC = 0.584). The accordance between Icolung and the median of the visual evaluations (Median R1-R2) was good (ICC = 0.885). The correspondence between CT-COPD and the median of the VQAS (Median R1-R2) was moderate (ICC = 0.622). (4) Conclusions: This study showed moderate and good agreement upon the VQAS and the SBQAS; enhancing this approach as a valuable tool to manage COVID-19 patients and the combination of AI tools with physician expertise can lead to the most accurate diagnosis and treatment plans for patients.
Vascular calcifications in aorto-iliac arteries are emerging as crucial risk factors for cardiovascular diseases (CVDs) with profound clinical implications. This systematic review, following PRISMA guidelines, investigated methodologies for measuring these calcifications and explored their correlation with CVDs and clinical outcomes. Out of 698 publications, 11 studies met the inclusion criteria. In total, 7 studies utilized manual methods, while 4 studies utilized automated technologies, including artificial intelligence and deep learning for image analyses. Age, systolic blood pressure, serum calcium, and lipoprotein(a) levels were found to be independent risk factors for aortic calcification. Mortality from CVDs was correlated with abdominal aorta calcification. Patients requiring reintervention after endovascular recanalization exhibited a significantly higher volume of calcification in their iliac arteries. Conclusions: This review reveals a diverse landscape of measurement methods for aorto-iliac calcifications; however, they lack a standardized reproducibility assessment. Automatic methods employing artificial intelligence appear to offer broader applicability and are less time-consuming. Assessment of calcium scoring could be routinely employed during preoperative workups for risk stratification and detailed surgical planning. Additionally, its correlation with clinical outcomes could be useful in predicting the risk of reinterventions and amputations.
(1) Background: Systemic inflammation stands as a well-established risk factor for ischemic cardiovascular disease, as well as a contributing factor in the development of cardiac arrhythmias, notably atrial fibrillation. Furthermore, scientific studies have brought to light the pivotal role of localized vascular inflammation in the initiation, progression, and destabilization of coronary atherosclerotic disease. (2) Methods: We comprehensively review recent, yet robust, scientific evidence elucidating the use of perivascular adipose tissue attenuation measurement on computed tomography applied to key anatomical sites. Specifically, the investigation extends to the internal carotid artery, aorta, left atrium, and coronary arteries. (3) Conclusions: The examination of perivascular adipose tissue attenuation emerges as a non-invasive and indirect means of estimating localized perivascular inflammation. This measure is quantified in Hounsfield units, indicative of the inflammatory response elicited by dense adipose tissue near the vessel or the atrium. Particularly noteworthy is its potential utility in assessing inflammatory processes within the coronary arteries, evaluating coronary microvascular dysfunction, appraising conditions within the aorta and carotid arteries, and discerning inflammatory states within the atria, especially in patients with atrial fibrillation. The widespread applicability of perivascular adipose tissue attenuation measurement underscores its significance as a diagnostic tool with considerable potential for enhancing our understanding and management of cardiovascular diseases.
There is currently a shift in surgical training from traditional methods to simulation-based approaches, recognizing the necessity of more effective and controlled learning environments. This study introduces a completely new 3D-printed modular system for endovascular surgery training (M-SET), developed to allow various difficulty levels. Its design was based on computed tomography angiographies from real patient data with femoro-popliteal lesions. The study aimed to explore the integration of simulation training via a 3D model into the surgical training curriculum and its effect on their performance. Our preliminary study included 12 volunteer trainees randomized 1:1 into the standard simulation (SS) group (3 stepwise difficulty training sessions) and the random simulation (RS) group (random difficulty of the M-SET). A senior surgeon evaluated and timed the final training session. Feedback reports were assessed through the Student Satisfaction and Self-Confidence in Learning Scale. The SS group completed the training sessions in about half time (23.13 ± 9.2 min vs. 44.6 ± 12.8 min). Trainees expressed high satisfaction with the training program supported by the M-SET. Our 3D-printed modular training model meets the current need for new endovascular training approaches, offering a customizable, accessible, and effective simulation-based educational program with the aim of reducing the time required to reach a high level of practical skills.
OBJECTIVES: The main factors associated with coronavirus disease-19 (COVID-19) mortality are age, comorbidities, pattern of inflammatory response, and SARS-CoV-2 lineage involved in infection. However, the clinical course of the disease is extremely heterogeneous, and reliable biomarkers predicting adverse prognosis are lacking. Our aim was to elucidate the prognostic role of a novel marker of coronary artery disease inflammation, peri-coronary adipose tissue attenuation (PCAT), available from high-resolution chest computed tomography (HRCT) in COVID-19 patients with severe disease requiring hospitalization. METHODS: Two distinct groups of patients were admitted to Parma University Hospital in Italy with COVID-19 in March 2020 and March 2021 (first- and third-wave peaks of the COVID-19 pandemic in Italy, with the prevalence of wild-type and B.1.1.7 SARS-CoV-2 lineage, respectively) were retrospectively enrolled. The primary endpoint was in-hospital mortality. Demographic, clinical, laboratory, HRCT data, and coronary artery HRCT features (coronary calcium score and PCAT attenuation) were collected to show which variables were associated with mortality. RESULTS: Among the 769 patients enrolled, 555 (72%) were discharged alive, and 214 (28%) died. In multivariable logistic regression analysis age (p < 0.001), number of chronic illnesses (p < 0.001), smoking habit (p = 0.006), P/F ratio (p = 0.001), platelet count (p = 0.002), blood creatinine (p < 0.001), non-invasive mechanical ventilation (p < 0.001), HRCT visual score (p < 0.001), and PCAT (p < 0.001), but not the calcium score, were independently associated with in-hospital mortality. CONCLUSION: Coronary inflammation, measured with PCAT on non-triggered HRCT, appeared to be independently associated with higher mortality in patients with severe COVID-19, while the pre-existent coronary atherosclerotic burden was not associated with adverse outcomes after adjustment for covariates. CLINICAL RELEVANCE STATEMENT: The current study demonstrates that a relatively simple measurement, peri-coronary adipose tissue attenuation (PCAT), available ex-post from standard high-resolution computed tomography, is strongly and independently associated with in-hospital mortality. KEY POINTS: ⢠Coronary inflammation can be measured by the attenuation of peri-coronary adipose tissue (PCAT) on high-resolution CT (HRCT) without contrast media. ⢠PCAT is strongly and independently associated with in-hospital mortality in SARS-CoV-2 patients. ⢠PCAT might be considered an independent prognostic marker in COVID-19 patients if confirmed in other studies.
Writing is a complex task that is acquired in the early primary school years and continues to develop through adolescence and beyond. Studying the cognitive processes that support writing skills during the acquisition phase may be crucial to support this complex skill especially in less-skilled writers. Executive Functions (EF) could have an important role as they are high cognitive control processes that allow individuals to control and plan thoughts and actions in order to achieve a goal. Given that EF have a crucial development during childhood, when the basic writing skills are acquired, this systematic review aims to investigate the contribution of the main EF components to the writing process in children. Search string focused on three main concepts: executive functions, writing, and children. Twenty-six studies were included following the guidelines of the PRISMA Statement. From the analyzed studies, working memory, in comparison to inhibition, cognitive flexibility, and planning, emerged as the most studied and the most related to writing skills. Nevertheless, the results also support the involvement of all EF basic components in writing, with a role that could vary depending on the considered writing process.0.
Executive Function , Memory, Short-Term , Writing , Adolescent , Child , Humans , Executive Function/physiology , Inhibition, Psychological , Memory, Short-Term/physiology , Motivation
Stroke represents the third cause of long-term disability in the world. About 80% of stroke patients have an impairment of bio-motor functions and over half fail to regain arm functionality, resulting in motor movement control disorder with serious loss in terms of social independence. Therefore, rehabilitation plays a key role in the reduction of patient disabilities, and 3D printing (3DP) has showed interesting improvements in related fields, thanks to the possibility to produce customized, eco-sustainable and cost-effective orthoses. This study investigated the clinical use of 3DP orthosis in rehabilitation compared to the traditional ones, focusing on the correlation between 3DP technology, therapy and outcomes. We screened 138 articles from PubMed, Scopus and Web of Science, selecting the 10 articles fulfilling the inclusion criteria, which were subsequently examined for the systematic review. The results showed that 3DP provides substantial advantages in terms of upper limb orthosis designed on the patient's needs. Moreover, seven research activities used biodegradable/recyclable materials, underlining the great potential of validated 3DP solutions in a clinical rehabilitation setting. The aim of this study was to highlight how 3DP could overcome the limitations of standard medical devices in order to support clinicians, bioengineers and innovation managers during the implementation of Healthcare 4.0.
The efficacy and complication rates of percutaneous radiofrequency ablation (RFA) and cryoablation (CA) in the treatment of T1 renal masses in two Northern Italy hospitals were retrospectively investigated. Eighty-two patients with 80 T1a tumors and 10 T1b tumors treated with thermal ablation from 2015 through 2020 were included. A total of 43 tumors in 38 patients were treated with RFA (2.3 ± 0.9 cm), and 47 tumors in 44 patients were treated with CA (2.1 ± 0.8 cm). The mean follow-up observation period was 26 ± 19 months. The major complications and efficacy, as measured using the technical success and local tumor recurrence rates, were recorded. There were three (6.9%) technical failures with RFA and one (2.1%) with cryoablation (p = 0.30). Among the 40 tumors that were successfully treated with RFA, 1 tumor (2.5%) developed local tumor recurrence; 5/46 tumors that were treated with cryoablation (10.8%) developed local tumor recurrence (p = 0.17). T1b lesions (4.0 ± 0.7 cm) resulted in 1/6 technically unsuccessful cases with RFA and 0/4 with CA. No recurrent disease was detected in the T1b lesions. Major complications occurred after 2.3% (1/43) of RFAs and 0/47 of cryoablation procedures. RFA and cryoablation are both effective in the treatment of renal masses. Major complications with either procedure are uncommon.
(1) Background and (2) Methods: In this retrospective, observational, monocentric study, we selected a cohort of eighty-five patients (age range 38-87 years old, 51 men), enrolled between January 2014 and December 2020, with a newly diagnosed renal mass smaller than 4 cm (SRM) that later underwent nephrectomy surgery (partial or total) or tumorectomy with an associated histopatological study of the lesion. The radiomic features (RFs) of eighty-five SRMs were extracted from abdominal CTs bought in the portal venous phase using three different CT scanners. Lesions were manually segmented by an abdominal radiologist. Image analysis was performed with the Pyradiomic library of 3D-Slicer. A total of 108 RFs were included for each volume. A machine learning model based on radiomic features was developed to distinguish between benign and malignant small renal masses. The pipeline included redundant RFs elimination, RFs standardization, dataset balancing, exclusion of non-reproducible RFs, feature selection (FS), model training, model tuning and validation of unseen data. (3) Results: The study population was composed of fifty-one RCCs and thirty-four benign lesions (twenty-five oncocytomas, seven lipid-poor angiomyolipomas and two renal leiomyomas). The final radiomic signature included 10 RFs. The average performance of the model on unseen data was 0.79 ± 0.12 for ROC-AUC, 0.73 ± 0.12 for accuracy, 0.78 ± 0.19 for sensitivity and 0.63 ± 0.15 for specificity. (4) Conclusions: Using a robust pipeline, we found that the developed RFs signature is capable of distinguishing RCCs from benign renal tumors.
INTRODUCTION: The COVID-19 pandemic had a huge impact on radiology departments all over the world, affecting both management and healthcare workers (HCWs). Therefore, it became challenging to guarantee high standards of diagnosis while keeping up with the workload. METHODS: The study was approved by the institutional review board. Its aim was to assess the impact of the COVID-19 pandemic over the radiology departments and HCWs through a survey. The questionnaire was available online from January to March 2022. Twelve areas of interest (sessions) were highlighted in the survey. RESULTS: The number of total responders was 1376 and 73.7% of participants worked in public healthcare facilities. Comparisons between participants working in public versus private healthcare facilities were carried out using chi-square tests and Fisher tests. Within public healthcare workers, 82% affirmed having operating instruction protocols regarding confirmed or suspected COVID-19 patient CT management (p< 0.001). Private healthcare facilities had fewer CT scanners available in general (p< 0.001); in fact, only 18% of them affirmed having two or more CT scanners, and did not have CT scanners dedicated to confirmed or suspected COVID-19 patients (p< 0.001). Finally, public facilities strongly reduced (by 88%) the number of examinations booked during the first wave, compared to private healthcare facilities (p< 0.001). CONCLUSION: This survey showed that public facilities appeared to be better prepared from an organizational point of view than private facilities. Rescheduling the examinations booked during the first COVID-19 wave was challenging and not always possible.
COVID-19 , Humans , COVID-19/epidemiology , Pandemics , Health Personnel , Surveys and Questionnaires , Italy/epidemiology
BACKGROUND: Implantable cardioverter-defibrillator (ICD) therapy is the most effective prophylactic strategy against sudden cardiac death (SCD) in patients with ischemic cardiomyopathy (ICM) and left ventricle ejection fraction (LVEF) ≤35% as detected by transthoracic echocardiograpgy (TTE). This approach has been recently questioned because of the low rate of ICD interventions in patients who received implantation and the not-negligible percentage of patients who experienced SCD despite not fulfilling criteria for implantation. OBJECTIVES: The DERIVATE-ICM registry (CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy; NCT03352648) is an international, multicenter, and multivendor study to assess the net reclassification improvement (NRI) for the indication of ICD implantation by the use of cardiac magnetic resonance (CMR) as compared to TTE in patients with ICM. METHODS: A total of 861 patients with ICM (mean age 65 ± 11 years, 86% male) with chronic heart failure and TTE-LVEF <50% participated. Major adverse arrhythmic cardiac events (MAACE) were the primary endpoints. RESULTS: During a median follow-up of 1,054 days, MAACE occurred in 88 (10.2%). Left ventricular end-diastolic volume index (HR: 1.007 [95% CI: 1.000-1.011]; P = 0.05), CMR-LVEF (HR: 0.972 [95% CI: 0.945-0.999]; P = 0.045) and late gadolinium enhancement (LGE) mass (HR: 1.010 [95% CI: 1.002-1.018]; P = 0.015) were independent predictors of MAACE. A multiparametric CMR weighted predictive derived score identifies subjects at high risk for MAACE compared with TTE-LVEF cutoff of 35% with a NRI of 31.7% (P = 0.007). CONCLUSIONS: The DERIVATE-ICM registry is a large multicenter registry showing the additional value of CMR to stratify the risk for MAACE in a large cohort of patients with ICM compared with standard of care.
Cardiomyopathies , Defibrillators, Implantable , Myocardial Ischemia , Humans , Male , Middle Aged , Aged , Female , Defibrillators, Implantable/adverse effects , Contrast Media , Magnetic Resonance Imaging, Cine , Predictive Value of Tests , Gadolinium , Myocardial Ischemia/complications , Myocardial Ischemia/diagnostic imaging , Myocardial Ischemia/therapy , Death, Sudden, Cardiac/etiology , Death, Sudden, Cardiac/prevention & control , Cardiomyopathies/diagnostic imaging , Cardiomyopathies/therapy , Cardiomyopathies/complications , Magnetic Resonance Spectroscopy/adverse effects , Registries , Risk Factors
AIMS: This study aimed to assess which variables on coronary computed tomography angiography (CTA) and vasodilator stress-echocardiography (SE) are best associated with long-term cardiac outcome in patients presenting for suspected chronic coronary syndrome (CCS) who performed both tests. METHODS: We identified 397 patients with suspected CCS who, between 2007 and 2019, underwent both SE and CTA within 30 days. Coronary artery calcium score (CACS) and the number of coronary arteries with diameter stenosis >50% were assessed on CTA. The presence of reversible regional wall motion abnormalities (RWMA) and reduced Doppler coronary flow velocity reserve in the left-anterior descending coronary artery (CFVR) were assessed on SE. The association of SE and CTA variables with cardiac outcome (cardiac death or myocardial infarction) was evaluated using Fine and Gray competing risk models. RESULTS: During a median follow-up of 10 years, 38 (9.6%) patients experienced a nonfatal myocardial infarction and 19 (4.8%) died from a cardiac cause. RWMA (HR 7.189, p < 0.001) and a lower CFVR (HR 0.034, p < 0.001) on SE, along with CACS (HR 1.004, p < 0.001) and the number of >50% stenosed coronary vessels (HR 1.975, p < 0.001) on CTA, were each associated with cardiac events. After adjusting for covariates, only CACS and CFVR remained associated (both p < 0.001) with cardiac outcome. CONCLUSION: Our data suggest that only CFVR on vasodilatory SE and CACS on CTA are independently and strongly associated with long-term cardiac outcome, unlike RWMA or the number of stenosed coronary arteries, usually considered the hallmarks of coronary artery disease on each test.
In recent years, next to conventional rehabilitation's techniques, new technologies have been applied in stroke rehabilitation. In this context, fully immersive virtual reality (FIVR) has showed interesting results thanks to the level of immersion of the subject in the illusional world, with the feeling of being a real part of the virtual environment. This study aims to investigate the efficacy of FIVR in stroke rehabilitation. PubMed, Web of Science and Scopus were screened up to November 2022 to identify eligible randomized controlled trials (RCTs). Out of 4623, we included 12 RCTs involving post-acute and chronic stroke survivors, with a total of 350 patients (234 men and 115 women; mean age 58.36 years). High heterogeneity of the outcomes considered, the results showed that FIVR provides additional benefits, in comparison with standard rehabilitation. In particular, results showed an improvement in upper limb dexterity, gait performance and dynamic balance, influencing patient independence. Therefore, FIVR represents an adaptable, multi-faceted rehabilitation tool that can be considered in post-stroke rehabilitation, improving the compliance of the patients to the treatment and increasing the level of functioning and quality of life of stroke survivors.
Stroke Rehabilitation , Stroke , Virtual Reality , Male , Female , Humans , Middle Aged , Stroke Rehabilitation/methods , Stroke/therapy , Activities of Daily Living , Gait
Small renal masses (SRM) are increasingly detected incidentally during imaging. They vary widely in histology and aggressiveness, and include benign renal tumors and renal cell carcinomas that can be either indolent or aggressive. Imaging plays a key role in the characterization of these small renal masses. While a confident diagnosis can be made in many cases, some renal masses are indeterminate at imaging and can present as diagnostic dilemmas for both the radiologists and the referring clinicians. This review focuses on CT characterization of small renal masses, perhaps helping us understand small renal masses. The following aspects were considered for the review: (a) assessing the presence of fat, (b) assessing the enhancement, (c) differentiating renal tumor subtype, and (d) identifying valuable CT signs.
Over the last two decades the detection rate of small renal masses has increased, due to improving diagnostic accuracy, and nephron-sparing treatments have become the first-choice curative option for small renal masses. As a minimally invasive alternative, thermal ablation has increased in popularity, offering a good clinical outcome and low recurrence rate. Radiofrequency ablation, Cryoablation, and Microwave ablation are the main ablative techniques. All of them are mostly overlapping in term of cancer specific free survival and outcomes. These techniques require imaging study to assess lesions features and to plan the procedure: US, CT, and both of them together are the leading guidance alternatives. Imaging findings guide the interventional radiologist in assessing the risk of complication and possible residual disease after procedure. The purpose of this review is to compare different ablative modalities and different imaging guides, underlining the effectiveness, outcomes, and complications related to each of them, in order to assist the interventional radiologist in choosing the best option for the patient.
Amputation has a big impact on the functioning of patients, with negative effects on locomotion and dexterity. In this context, inertial measurement units represent a useful tool in clinical practice for motion analysis, and in the development of personalized aids to improve a patient's function. To date, there is still a gap of knowledge in the scientific literature on the application of inertial sensors in amputee patients. Thus, the aim of this narrative review was to collect the current knowledge on this topic and stimulate the publication of further research. Pubmed, Embase, Scopus, and Cochrane Library publications were screened until November 2022 to identify eligible studies. Out of 444 results, we selected 26 articles focused on movement analysis, risk of falls, energy expenditure, and the development of sensor-integrated prostheses. The results showed that the use of inertial sensors has the potential to improve the quality of life of patients with prostheses, increasing patient safety through the detection of gait alteration; enhancing the socio-occupational reintegration through the development of highly technologic and personalized prosthesis; and by monitoring the patients during daily life to plan a tailored rehabilitation program.
Amputees , Humans , Quality of Life , Gait , Amputation, Surgical , Locomotion
AIMS: Right ventricular systolic dysfunction (RVSD) is an important determinant of outcomes in heart failure (HF) cohorts. While the quantitative assessment of RV function is challenging using 2D-echocardiography, cardiac magnetic resonance (CMR) is the gold standard with its high spatial resolution and precise anatomical definition. We sought to investigate the prognostic value of CMR-derived RV systolic function in a large cohort of HF with reduced ejection fraction (HFrEF). METHODS AND RESULTS: Study cohort comprised of patients enrolled in the CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DefibrillAtor ThErapy registry who had HFrEF and had simultaneous baseline CMR and echocardiography (n = 2449). RVSD was defined as RV ejection fraction (RVEF) <45%. Kaplan-Meier curves and cox regression were used to investigate the association between RVSD and all-cause mortality (ACM). Mean age was 59.8 ± 14.0 years, 42.0% were female, and mean left ventricular ejection fraction (LVEF) was 34.0 ± 10.8. Median follow-up was 959 days (interquartile range: 560-1590). RVSD was present in 936 (38.2%) and was an independent predictor of ACM (adjusted hazard ratio = 1.44; 95% CI [1.09-1.91]; P = 0.01). On subgroup analyses, the prognostic value of RVSD was more pronounced in NYHA I/II than in NYHA III/IV, in LVEF <35% than in LVEF ≥35%, and in patients with renal dysfunction when compared to those with normal renal function. CONCLUSION: RV systolic dysfunction is an independent predictor of ACM in HFrEF, with a more pronounced prognostic value in select subgroups, likely reflecting the importance of RVSD in the early stages of HF progression.
Cardiomyopathies , Defibrillators, Implantable , Heart Failure , Ventricular Dysfunction, Right , Humans , Female , Middle Aged , Aged , Male , Prognosis , Stroke Volume , Ventricular Function, Left , Heart Failure/diagnostic imaging , Heart Failure/therapy , Heart Failure/complications , Defibrillators, Implantable/adverse effects , Risk Factors , Magnetic Resonance Imaging, Cine/methods , Cardiomyopathies/complications , Magnetic Resonance Spectroscopy/adverse effects , Ventricular Function, Right , Ventricular Dysfunction, Right/diagnostic imaging , Ventricular Dysfunction, Right/therapy , Ventricular Dysfunction, Right/etiology
(1) Background: In the last decade, the number of detected renal cancer cases has increased, with the highest incidence in Western countries. Although renal biopsy is reported as a safe procedure, it is not adopted in all centres. As it is not possible to accurately distinguish benign tumours using imaging, this may lead to overtreatment. Most of the cancer detected on imaging is treated by surgery, radiofrequency ablation (RFA), or cryotherapy. (2) Methods: This was a single-centre retrospective study of 225 patients studied preoperatively with ultrasound (US)/CT-guided renal biopsy, with the aim of supporting clinical management. Decisions regarding the biopsy were based on either MDT indication or physician preference. US-guided renal biopsy was the first option for all patients; CT-guided biopsy was used when US-guided biopsy was not feasible. The efficacy of renal biopsy in terms of diagnostic performance and the concordance between biopsy results and definitive pathology were investigated. Additionally, adverse events related to the biopsy were recorded and analysed. Data collected throughout the study were analysed using binary logistic regression, Fisher's exact test, and Pearson's chi-square test to investigate possible correlations between post-procedural complications and the size of the lesion. (3) Results: Renal biopsy was not diagnostic in 23/225 (10.2%) patients. A CT-guided approach was necessary in 20/225 patients after failure of US-guided biopsy. The complication rate of renal biopsy was 4.8% overall-all Clavien grade I and without any serious sequelae. Interestingly, complications occurred in patients with very different sizes of renal cell carcinoma. No correlation between complications and anticoagulant/antiplatelet drugs was found. No seeding was reported among the patients who underwent partial/radical nephrectomy. (4) Conclusions: Renal biopsy was shown to be safe and effective, with a high concordance between biopsy results and definitive pathology and a low rate of complications. The use of a CT-guided approach whenever the US-guided approach failed improved the diagnostic performance of renal biopsy.
(1) Background: Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is a long-established estimation methodology for medical diagnosis using image classification illustrating conditions in coronary artery disease. For these procedures, convolutional neural networks have proven to be very beneficial in achieving near-optimal accuracy for the automatic classification of SPECT images. (2) Methods: This research addresses the supervised learning-based ideal observer image classification utilizing an RGB-CNN model in heart images to diagnose CAD. For comparison purposes, we employ VGG-16 and DenseNet-121 pre-trained networks that are indulged in an image dataset representing stress and rest mode heart states acquired by SPECT. In experimentally evaluating the method, we explore a wide repertoire of deep learning network setups in conjunction with various robust evaluation and exploitation metrics. Additionally, to overcome the image dataset cardinality restrictions, we take advantage of the data augmentation technique expanding the set into an adequate number. Further evaluation of the model was performed via 10-fold cross-validation to ensure our model's reliability. (3) Results: The proposed RGB-CNN model achieved an accuracy of 91.86%, while VGG-16 and DenseNet-121 reached 88.54% and 86.11%, respectively. (4) Conclusions: The abovementioned experiments verify that the newly developed deep learning models may be of great assistance in nuclear medicine and clinical decision-making.
