Cardiac magnetic resonance (CMR) is an established tool for risk stratification in several cardiomyopathies, and its role in muscular dystrophies (MuD) looks promising. We sought to assess how CMR performs in predicting cardiac events in a real cohort of MuD patients. A prospective single-center study with the enrollment of consecutive adult MuD patients referred to cardiac screening from 2012 to 2018 with the collection of clinical and CMR data. During follow-up (FUP), major adverse cardiac events were considered a composite of device implantation, ventricular tachycardia (VT), hospitalization due to heart failure, and death. Sixty-five patients were included (mean age of 32±16, 51% female); the majority had myotonic dystrophy (34; 52.3%); most were asymptomatic (60; 92.3%) and at sinus rhythm (64; 98.5%). CMR was abnormal in 23 (43.3%) patients: left ventricle ejection fraction (LVEF) <55% was found in 7 patients, and late gadolinium enhancement (LGE) was present in 23 patients, mainly intra-myocardial or subepicardial (10 and 8 patients, respectively). During a median FUP of 77 months (interquartile range: 33), there were 7 deaths, 8 implanted devices, and one sustained VT. LVEF<55% and the presence of LGE were associated with the occurrence of all events (log rank test, p=0.002 and p=0.045, respectively). LVEF<55% was associated with a 6-fold higher risk of events (crude hazard ratio of 6.15; 95% confidence interval of 1.65-22.93), that remained significant after adjusting for LGE presence (adjusted hazard ratio of 4.81, 95% confidence interval of 1.07-15.9). In our cohort, CMR LVEF<55% and the presence of LGE were significantly associated with adverse events during follow-up, reinforcing the role of this technique on risk stratification of MuD populations.

The objective of this paper is to analyse the steady state and dynamic behaviour of a MicroGrid system containing one microturbine generating Combined Heat and Power feeding some small local loads in islanded mode of operation. Future operating scenarios were also analysed and simulated, namely considering the installation of photovoltaic panels near consumers

The data were obtained by measuring several power quality parameters and other quantities in three different locations in SEWF: in two wind turbines and in the wind farm’s substation. The primary aim of the study is to obtain harmonics and flicker levels at those specific sites. Two different types of power quality measurement devices were used: UNILYZER 812 from UNIPOWER and MEMOBOX 300 smart from LEM.

Humeral shaft fractures are common, but proximal metadiaphyseal fractures are unusual and represent challenging injuries.Their treatment is still controversial and debatable.Lateral minimally invasive osteosynthesis (MIPO) represents an alternative treatment for those fractures, but there is still a lack of studies describing this technique.We retrospectively reviewed six patients with proximal metadiaphyseal humeral fractures treated with lateral MIPO.All the patients reached consolidation.We had one case of postoperative radial neuropraxia that entirely resolved with time, and there was no other complication.We reviewed and summarized the available literature, and our outcomes were similar to those described.The mean shoulder ROM was 143º ± 12,4º of abduction; 145º ± 9,1º of forward elevation; 33,8º ± 4,8º of external rotation; most patients reached L1 level with internal rotation, with no statistically significant difference between the affected and non-affected arm.The mean Constant score was 88 ± 5,4; the mean Q-DASH score was 8 ± 1,3; and the mean UCLA score was 28,8 ± 2,6º.The lateral MIPO approach permits a good shoulder function and a high union rate.Radial neuropraxia is the most common complication described in the literature and usually entirely resolves with time.Orthopaedic and trauma surgeons dedicated to shoulder injuries should know different approaches and fixation methods.MIPO should also be in their arsenal, with the lateral approach advantageous in proximal metadyaphiseal fractures and a reproductive technique.

Most of the Power Quality surveys in industrialized countries are performed according to the parameters defined in the EN50160 standard, which sets oneweek measurement periods with ten-minute sampling time for most power quality disturbances such as flicker and harmonics.Both the sampling periods and the measurement period have a great influence on the significance of the values obtained as well as on the conclusions taken.In this paper, an attempt is made to compare the values obtained with different sample frequencies and time windows, working on instantaneous flicker (Ifl) values for a wind turbine over three weeks.

Biomedical engineering has been targeted as a potential research candidate for machine learning applications, with the purpose of detecting or diagnosing pathologies. However, acquiring relevant, high-quality, and heterogeneous medical datasets is challenging due to privacy and security issues and the effort required to annotate the data. Generative models have recently gained a growing interest in the computer vision field due to their ability to increase dataset size by generating new high-quality samples from the initial set, which can be used as data augmentation of a training dataset. This study aimed to synthesize artificial lung images from corresponding positional and semantic annotations using two generative adversarial networks and databases of real computed tomography scans: the Pix2Pix approach that generates lung images from the lung segmentation maps; and the conditional generative adversarial network (cCGAN) approach that was implemented with additional semantic labels in the generation process. To evaluate the quality of the generated images, two quantitative measures were used: the domain-specific Frechet Inception Distance and Structural Similarity Index. Additionally, an expert assessment was performed to measure the capability to distinguish between real and generated images. The assessment performed shows the high quality of synthesized images, which was confirmed by the expert evaluation. This work represents an innovative application of GAN approaches for medical application taking into consideration the pathological findings in the CT images and the clinical evaluation to assess the realism of these features in the generated images.

Kaposiform hemangioendothelioma is a rare, locally aggressive or borderline vascular tumor that typically affects infants. It presents as a purpuric cutaneous lesion and may be associated with life-threatening coagulation disorders, such as the Kasabach-Merritt phenomenon. The differential diagnosis can be challenging based on clinical presentation alone. Imaging plays a crucial role in the diagnostic workup, particularly magnetic resonance imaging.We present a case report of a 4-month-old patient with an enlarging vinous cutaneous mass on the thigh and coagulation abnormalities. Magnetic resonance imaging revealed a large, infiltrative, soft-tissue lesion with poorly defined margins and heterogeneous enhancement, that involved all muscle compartments of the thigh and was associated with lymphedema, stranding of the subcutaneous fat and cutaneous thickening. These findings were consistent with kaposiform hemangioendothelioma of the thigh and the diagnosis was confirmed by histopathological characterization.

Abstract Funding Acknowledgements Type of funding sources: None. Background Neuromuscular disorders (NMD) have a wide range of different cardiac presentations. Cardiac magnetic resonance (CMR) has an established role in diagnosis and risk stratification. We sought to access how CMR performs in predicting events in a real cohort of NMD patients (pts). Methods We included consecutive pts followed in a tertiary clinical center with NMD from January 2012 to December 2018. Clinical and CMR data were collected. During follow-up (FUP), we considered major adverse cardiovascular events (MACE) as a composite of device implantation, ventricular tachycardia/appropriate shock therapy and death. Results A total of 65 patients (pts) were included, 33 (51%) women, with mean age of 32 ± 16 years. Most patients had myotonic dystrophy (34, 52%), followed by limb–girdle muscular dystrophy (22; 34%); the remained 9 (13%) had other NMD. About half had inferior limbs predominantly affected and 74% had none, mild or moderate functional impairment. Regarding cardiac manifestations, 18% had cardiac symptoms, 97% were in sinus rhythm, median PR and QRS duration were 169 (IQR 47) ms and 101 (IQR 11) ms, respectively; median BNP was 26 (IQR 25) mg/dl. Regarding CMR, 43,3% of pts had ≥ one abnormality. Six pts had left ventricle dilation and 7 had left ventricle ejection fraction (LVEF) 55%. Three pts had significant hypertrophy (>12 mm) and there were isolated cases of hypertrabeculation, segmental alterations or right ventricle dilation. Regarding tissue characterization, 2 pts had T2 hyperintensity, 8 had early gadolinium enhancement (EGE) and 22 had late gadolinium enhancement (LGE). LGE was located mainly intramyocardium (45%) or subepicardial (36%) and the most affected segments were basal and medium inferolateral (40%). During a median FUP of 77 (IQR 33) months there were 7 deaths, 8 implanted devices (4 pacemakers and 4 CRT-D, 3 in primary prevention) and one sustained ventricular tachycardia in holter; there were no shock therapies. Table 1 describes some CMR parameters according to the occurrence of events. Using Kaplan Meier curves, there were associations between LVEF<55% and presence of LGE with occurrence of allevents (log rank test, p = 0,002 and p = 0,045, respectively), but no association were found with age, LGE pattern nor number/distribution of affected segments. Using Cox Regression, we found that the LVEF<55% was associated with 6 fold higher risk of events (HR crude 6,15; 95% CI 1,65–22,93), that remained significant after adjusting for LGE (HR adjusted 4,81, 95% CI 1,07–15,9). Conclusion In our cohort, CMR LVEF<55% and the presence of LGE were significantly associated with events during FUP, reinforcing the role of this technique on risk stratification of NMD populations

Objective: Identify lung sequelae of COVID-19 through radiological and pulmonary function assessment. Design: Prospective, longitudinal, cohort study from March 2020 to March 2021. Setting: Intensive Care Units (ICU) in a tertiary hospital in Portugal. Patients: 254 patients with COVID-19 admitted to ICU due to respiratory illness. Interventions: A chest computed tomography (CT) scan and pulmonary function tests (PFT) were performed at 3 to 6 months. Main variables of interest: CT-scan; PFT; decreased diffusion capacity of carbon monoxide (DLCO). Results: All CT scans revealed improvement in the follow-up, with 72% of patients still showing abnormalities, 58% with ground glass opacities and 62% with evidence of fibrosis. PFT had abnormalities in 94 patients (46%): thirteen patients (7%) had an obstructive pattern, 35 (18%) had a restrictive pattern, and 58 (30%) had decreased DLCO. There was a statistically significant association between abnormalities in the follow-up CT scan and older age, more extended hospital and ICU stay, higher SAPS II and APACHE scores and invasive ventilation. Mechanical ventilation, especially with no lung protective parameters, was associated with abnormalities in PFT. Multivariate regression showed more abnormalities in lung function with more extended ICU hospitalization, chronic obstructive pulmonary disease (COPD), chronic kidney disease, invasive mechanical ventilation, and ventilation with higher plateau pressure, and more abnormalities in CT-scan with older age, more extended ICU stay, organ solid transplants and ventilation with higher positive end-expiratory pressure (PEEP). Conclusions: Most patients with severe COVID-19 still exhibit abnormalities in CT scans or lung function tests three to six months after discharge. Resumen: Objetivo: Identificar secuelas pulmonares de COVID-19 através de evaluación radiológica y de función pulmonar.Diseño: Estudio prospectivo, longitudinal, de cohortes de marzo de 2020 a marzo de 2021. Ámbito: Unidades de Cuidados Intensivos (UCI) en un hospital terciario en Portugal. Pacientes: Se incluyeron un total de 254 pacientes con COVID-19 confirmada por ensayo de reacción en cadena de la polimerasa con transcriptasa inversa en tiempo real de hisopos nasales/faríngeos. Intervenciones: Se realizaron una tomografía axial computarizada (TAC) de tórax y pruebas de función pulmonar (PFP) a los 3 a 6 meses. Principales variables de interés: TAC; PFP; Disminución de capacidad de difusión de monóxido de carbono (DLCO). Resultados: Todas TAC revelaron una mejora en el seguimiento, con el 72 % de los pacientes que aún mostraban anomalías, el 58 % con opacidades en vidrio esmerilado y el 62 % con evidencia de fibrosis. La PFP presentó anomalías en 94 pacientes (46 %): trece pacientes tenían un patrón obstructivo, 35 un patrón restrictivo y 58 tenían una DLCO disminuida. La regresión logística multivariada mostró más anomalías en la función pulmonar con hospitalización en la UCI más prolongada, enfermedad pulmonar obstructiva crónica (EPOC), enfermedad renal crónica, ventilación mecánica invasiva y ventilación con presión de meseta más alta, y más anomalías en la tomografía computarizada con mayor edad, estancia más prolongada en la UCI, y ventilación con mayor Titulación de Pression Positiva Expiratória (PEEP). Conclusiones: La mayoría de los pacientes con COVID-19 grave aún presentan anomalías en las tomografías computarizadas o en las pruebas de función pulmonar de tres a seis meses después del alta.

Endometriosis-associated ovarian cancer represents the most common form of malignancy associated with this benign disease. It has a better prognosis than most types of ovarian cancer, with endometrioid adenocarcinoma and clear cell carcinoma as the main histological types. Clinical presentation is usually nonspecific and tumor biomarkers can be misleading, since they can also be elevated in the presence of benign ovarian endometriosis. We report a case of a 52-year-old woman with known ovarian and deep pelvic endometriosis, who developed ovarian clear cell carcinoma within a large endometrioma. The imaging findings highlight the key role of magnetic resonance imaging in detecting suspicious features such as loss of the “T2 shading” sign, loss of high T1 signal of an endometrioma, or the presence of mural nodules. Early detection of these malignancies is fundamental for adequate surgical treatment and overall outcome.

Intermediate- to high-grade non-muscle invasive bladder cancer is preferably treated with transurethral resection followed by adjuvant intravesical immunotherapy with Bacillus Calmette-Guérin (BCG). BCG acts as an immune stimulator, inducing a complex inflammatory response that selectively targets tumoral cells. Mild side effects of BCG instillation, such as fever, malaise, and bladder irritation are frequent, while severe treatment-associated complications of the genito-urinary tract are rare. "Distant" complications are even rarer and, since BCG is able to disseminate hematogenously, virtually all organs and systems can be involved, with the lungs, liver and musculoskeletal system being most commonly affected. Vascular complications of BCG immunotherapy are exceedingly rare and difficult to diagnose, because they can mimic other vascular infections and may occur several years after treatment. Knowledge of previous BCG immunotherapy and awareness about treatment-related complications is essential to avoid misdiagnosis, and to guide appropriate treatment.

Advancements in the development of computer-aided decision (CAD) systems for clinical routines provide unquestionable benefits in connecting human medical expertise with machine intelligence, to achieve better quality healthcare. Considering the large number of incidences and mortality numbers associated with lung cancer, there is a need for the most accurate clinical procedures; thus, the possibility of using artificial intelligence (AI) tools for decision support is becoming a closer reality. At any stage of the lung cancer clinical pathway, specific obstacles are identified and "motivate" the application of innovative AI solutions. This work provides a comprehensive review of the most recent research dedicated toward the development of CAD tools using computed tomography images for lung cancer-related tasks. We discuss the major challenges and provide critical perspectives on future directions. Although we focus on lung cancer in this review, we also provide a more clear definition of the path used to integrate AI in healthcare, emphasizing fundamental research points that are crucial for overcoming current barriers.

Lung diseases affect the lives of billions of people worldwide, and 4 million people, each year, die prematurely due to this condition. These pathologies are characterized by specific imagiological findings in CT scans. The traditional Computer-Aided Diagnosis (CAD) approaches have been showing promising results to help clinicians; however, CADs normally consider a small part of the medical image for analysis, excluding possible relevant information for clinical evaluation. Multiple Instance Learning (MIL) approach takes into consideration different small pieces that are relevant for the final classification and creates a comprehensive analysis of pathophysiological changes. This study uses MIL-based approaches to identify the presence of lung pathophysiological findings in CT scans for the characterization of lung disease development. This work was focus on the detection of the following: Fibrosis, Emphysema, Satellite Nodules in Primary Lesion Lobe, Nodules in Contralateral Lung and Ground Glass, being Fibrosis and Emphysema the ones with more outstanding results, reaching an Area Under the Curve (AUC) of 0.89 and 0.72, respectively. Additionally, the MIL-based approach was used for EGFR mutation status prediction - the most relevant oncogene on lung cancer, with an AUC of 0.69. The results showed that this comprehensive approach can be a useful tool for lung pathophysiological characterization.

Abstract Background Ventricular arrhythmias (VA) include a spectrum that ranges from premature ventricular beats (VPBs) to ventricular fibrillation (VF) and account for approximately 50% of all cardiovascular deaths. Echocardiography is commonly used to identify structural heart disease (SHD), the most frequent substrate of VA. Cardiovascular magnetic resonance (CMR) is recommended to complement echocardiography when image quality is suboptimal. Purpose This study sought to determine whether CMR may identify SHD in patients (pts) with VA, who had normal baseline ECGs and whose echocardiogram with fair technical conditions, ruled out pathological findings. Methods We included consecutive pts followed in arrythmia outpatient clinic of one clinical center from June 2014 to June 2021 for significant VA; this was categorized as >1,000 but <10,000 VPBs/24 h; ≥10,000 VPBs/24 h; nonsustained ventricular tachycardia (NSVT), sustained VT, or a history of resuscitated cardiac arrest, and no pathological findings at echocardiography, requiring a clinically indicated CMR. Primary endpoint was CMR detection of SHD. Data were collected at the end of the study. Results A total of 75 pts were included (no SHD: N=59; 45±15 years old; SHD: N=16, 53±15 years). All pts performed CMR, and Table 1 shows pts' baseline characteristics, VA diagnosis and CMR measurements. Definite SHD was diagnosed in 8 patients (11%): ischemic cardiopathy (three pts), myocarditis (1 pt), hypertrophic cardiomyopathy (1 pt), right ventricle arrhythmogenic disease (1 pt), non-compaction cardiomyopathy (1 pt); 1 patient presented higher myocardial T2 signal and was later diagnosed with sarcoidosis. Furthermore, abnormal findings not specific for a definite SHD diagnosis were found in other 8 pts (10%) who showed unspecific intra-myocardium enhancement. Discussion and conclusion CMR imaging identified SHD in around 20% of patients with normal ECG and echocardiogram. Among patients with identified SHD, ischemic cardiopathy was the most common finding, differently from the largest study that showed myocarditis as the main diagnosis. This may be associated to higher age in the SHD group. In conclusion, CMR allowed diagnosis of clinically relevant SHD even when echocardiography excluded it. Funding Acknowledgement Type of funding sources: None.

Herlyn-Werner-Wunderlich syndrome is a rare complex congenital disorder, with combined Müllerian and mesonephric duct anomalies, presenting with uterus didelphys, unilateral blind hemivagina and ipsilateral renal agenesis. Hemivaginal obstruction usually leads to impairment of normal menstrual flow, resulting in symptoms after menarche, namely dysmenorrhea, pelvic pain or infertility. Age of presentation depends on the anatomical features of this anomaly. We report a case of a 21-year-old female presenting with few symptoms and incidental findings on transvaginal ultrasound, with typical findings of this disorder on magnetic resonance imaging, which remains the gold standard imaging technique for thorough assessment of Herlyn-Werner-Wunderlich syndrome, allowing for a correct diagnosis and adequate surgical management. Our case also highlights some unusual features, such as the presence of a blind ectopic ureter, with hematic content, and an incomplete septum within the obstructed hemivagina.

The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.