Diagnostics, Volume 14, Issue 4 (February-2 2024) – 107 articles

In recent years, there has been growing interest in the use of computer-assisted technology for early detection of skin cancer through the analysis of dermatoscopic images. However, the accuracy illustrated behind the state-of-the-art approaches depends on several factors, such as the quality of the images and the interpretation of the results by medical experts. This systematic review aims to critically assess the efficacy and challenges of this research field in order to explain the usability and limitations and highlight potential future lines of work for the scientific and clinical community. In this study, the analysis was carried out over 45 contemporary studies extracted from databases such as Web of Science and Scopus. Several computer vision techniques related to image and video processing for early skin cancer diagnosis were identified. In this context, the focus behind the process included the algorithms employed, result accuracy, and validation metrics. Thus, the results yielded significant advancements in cancer detection using deep learning and machine learning algorithms. Lastly, this review establishes a foundation for future research, highlighting potential contributions and opportunities to improve the effectiveness of skin cancer detection through machine learning. Full article

(1) Background: Prenatal care providers face a continuous challenge in screening for intrauterine growth restriction (IUGR) and preeclampsia (PE). In this study, we aimed to assess and compare the predictive accuracy of four machine learning algorithms in predicting the occurrence of PE, IUGR, and their associations in a group of singleton pregnancies; (2) Methods: This observational prospective study included 210 singleton pregnancies that underwent first trimester screenings at our institution. We computed the predictive performance of four machine learning-based methods, namely decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF), by incorporating clinical and paraclinical data; (3) Results: The RF algorithm showed superior performance for the prediction of PE (accuracy: 96.3%), IUGR (accuracy: 95.9%), and its subtypes (early onset IUGR, accuracy: 96.2%, and late-onset IUGR, accuracy: 95.2%), as well as their association (accuracy: 95.1%). Both SVM and NB similarly predicted IUGR (accuracy: 95.3%), while SVM outperformed NB (accuracy: 95.8 vs. 94.7%) in predicting PE; (4) Conclusions: The integration of machine learning-based algorithms in the first-trimester screening of PE and IUGR could improve the overall detection rate of these disorders, but this hypothesis should be confirmed in larger cohorts of pregnant patients from various geographical areas. Full article

Long-term Glucocorticoid (GC) use results in compromised bone strength and fractures, and several treatment recommendations have been developed to prevent fractures, but none have been validated in a real-world setting. This study aims to create a treatment decision tool and compares this tool to the treatment suggestions from the American College of Rheumatology (ACR), International Osteoporosis Foundation and European Calcified Tissue Society (IOF-ECTS), and GC-adjusted Fracture Risk Assessment Tool (GC-FRAX), above the intervention threshold. We utilized registry data gathered at Chang Gung Memorial Hospital at Kaohsiung, Taiwan, between September 2014 and April 2021. This research is a single-center, observational, and case-controlled study. We recruited participants using prednisone for at least 2.5 mg/day or the equivalent dose for over 3 months, excluding those younger than 40, those with malignancies, or those currently undergoing anti-osteoporosis therapy. The primary endpoint was new fragility fractures within 3 years, including morphometric vertebral fractures detected at baseline and with a follow-up thoracic–lumbar spine X-ray. Participants were randomly allocated into derivation and validation sets. We developed the Steroid-Associated Fracture Evaluation (SAFE) tool in the derivation cohort by assessing the weights of exploratory variables via logistic regression. Prediction performance was compared in the validation set by the receiver operating characteristic (ROC) curve, the area under the curve (AUC), and sensitivity and specificity. A total of 424 treatment-naïve subjects were enrolled, and 83 (19.6%) experienced new fractures within 3 years. The final formula of the SAFE tool includes osteoporosis (1 point), an accumulated GC dose ≥ 750 mg within 6 months (or equivalent prednisolone of ≥4.5 mg/day for 6 months) (1 point), a BMI ≥ 23.5 (1 point), previous fractures (1 point), and elderliness of ≥70 years (2 points). In the validation set, a treatment decision based on the SAFE ≥ 2 points demonstrated an AUC of 0.65, with a sensitivity/specificity/accuracy of 75.9/54.0/58.9, with an ACR of 0.56 (100.0/11.0/31.0), IOF-ECTS 0.61 (75.9/46.0/52.7), and GC-FRAX 0.62 (82.8/42.0/51.2). Among current GIOP recommendations, the SAFE score serves as an appropriate treatment decision tool with increased accuracy and specificity. Full article

Cervical cancer, primarily caused by high-risk human papillomavirus (HR-HPV) types 16 and 18, is a major global health concern. Persistent HR-HPV infection can progress from reversible precancerous lesions to invasive cervical cancer, which is driven by the oncogenic activity of human papillomavirus (HPV) genes, particularly E6 and E7. Traditional screening methods, including cytology and HPV testing, have limited sensitivity and specificity. This review explores the application of p16/Ki-67 dual-staining cytology for cervical cancer screening. This advanced immunocytochemical method allows for simultaneously detecting p16 and Ki-67 proteins within cervical epithelial cells, offering a more specific approach for triaging HPV-positive women. Dual staining and traditional methods are compared, demonstrating their high sensitivity and negative predictive value but low specificity. The increased sensitivity of dual staining results in higher detection rates of CIN2+ lesions, which is crucial for preventing cervical cancer progression. However, its low specificity may lead to increased false-positive results and unnecessary biopsies. The implications of integrating dual staining into contemporary screening strategies, particularly considering the evolving landscape of HPV vaccination and changes in HPV genotype prevalence, are also discussed. New guidelines and further research are necessary to elucidate the long-term effects of integrating dual staining into screening protocols. Full article

Inflammation plays a crucial role in diabetes and obesity through macrophage activation. Macrophage chemoattractant protein-1 (MCP-1), activin-A, and clusterin are chemokines with known roles in diabetes and obesity. The aim of this study is to investigate their possible diagnostic and/or early prognostic values in children and adolescents with obesity and type-1 diabetes mellitus (T1DM). Methods: We obtained serum samples from children and adolescents with a history of T1DM or obesity, in order to measure and compare MCP-1, activin-A, and clusterin concentrations. Results: Forty-three subjects were included in each of the three groups (controls, T1DM, and obesity). MCP-1 values were positively correlated to BMI z-score. Activin-A was increased in children with obesity compared to the control group. A trend for higher values was detected in children with T1DM. MCP-1 and activin-A levels were positively correlated. Clusterin levels showed a trend towards lower values in children with T1DM or obesity compared to the control group and were negatively correlated to renal function. Conclusions: The inflammation markers MCP-1, activin-A, and clusterin are not altered in children with T1DM. Conversely, obesity in children is positively correlated to serum MCP-1 values and characterized by higher activin-A levels, which may reflect an already established systematic inflammation with obesity since childhood. Full article

Introduction: Tumor necrosis factor (TNF), a pro-inflammatory cytokine, can be produced by cardiomyocytes, leading to metabolic disorders in the myocardium. The objective of this study was to assess the relationship between plasma levels of the TNF cytokine and the presence of known biochemical and clinical risk factors for cardiovascular disease, along with the parameters of cardiac morphology in patients diagnosed with coronary artery disease (CAD) at a young age. Materials and Methods: The study group included 75 men aged up to 50 years and 25 women aged up to 55 years. The plasma TNF concentration was measured by use of the ELISA assay. Echocardiography and electrocardiographic examinations were performed in all patients. Results: We observed positive correlations for TNF with the BMI ratio, weight, waist and hip circumference. We also found negative correlations for TNF with HDL levels and ApoA concentrations, and positive correlations with the ApoB/ApoA1 ratio, Apo B, IL6, LDL and TG concentrations. These results suggest an association between higher plasma TNF concentrations and components of metabolic syndrome, including dyslipidemia. TNF may be a potential risk factor for impaired diastolic function. Conclusions: While TNF may be useful for diagnosing certain risks in CAD patients, the TNF measurement cannot be used as a surrogate test for echocardiography. Full article

Introduction: Recent evidence reported mental health issues in university students such as anxiety and depressive symptoms and poor sleep quality. Decreased plasma brain-derived neurotrophic factor (BDNF) levels have been proposed as a biomarker of depressive symptoms, whereas cortisol levels are an index of energy mobilization and stress and have been linked to sleep quality. Given that salivary biomarkers represent an interesting new field of research, the aim of this cross-sectional study was to evaluate salivary BDNF and cortisol levels in university students to assess whether they have associations with psychological disturbances such as anxiety and depressive symptoms, sleep quality, and stress level. Methods: Salivary BDNF and cortisol levels were measured by specific immunoassays in 70 students whose mental health was also evaluated on the same day through the evaluation of anxiety and depression symptoms (Goldberg scale), sleep quality (Pittsburg Sleep Quality Index and Athens Insomnia Scale), and stress (self-perceived stress scale) and healthy lifestyle habits (alcohol consumption, smoking, regular exercise, and body mass index) were also measured. Multivariate regression analyses were performed in order to identify the strengths of associations between psychological alterations and the concentrations of BDNF, cortisol, and other variables. Results: Salivary BDNF levels were significantly higher in students with more depressive symptoms, whereas no significant differences were found for cortisol levels. When performing the binary logistic regression model, BDNF levels are included as a predictor variable for a high-depressive-symptoms burden (p < 0.05). Students with worse sleep quality on the Pittsburg Scale had higher cortisol levels (p < 0.05). The subdomains of sleep latency and sleep medication were those significantly associated with salivary cortisol levels in logistic regression analyses (OR = 15.150, p = 0.028). Sleep medication only appeared to be related to cortisol levels (OR = 185.142, p = 0.019). Perceived stress levels and anxiety symptoms were not associated with BDNF or cortisol levels. Conclusions: BDNF could play a key role in the pathophysiology of mood-related disorders, and elevation of its peripheral levels could contribute to protecting neurons from the development of mental illness. Higher salivary cortisol levels measured in the morning are accompanied by poorer sleep quality. More research is needed, focusing on salivary biomarkers of disorders related to depressive symptoms and poor sleep quality as a potential tool for the diagnosis and prevention of mental illness. Full article

Objective: To comprehensively capture intra-tumor heterogeneity in head and neck cancer (HNC) and maximize the use of valid information collected in the clinical field, we propose a novel multi-modal image–text fusion strategy aimed at improving prognosis. Method: We have developed a tailored diagnostic algorithm for HNC, leveraging a deep learning-based model that integrates both image and clinical text information. For the image fusion part, we used the cross-attention mechanism to fuse the image information between PET and CT, and for the fusion of text and image, we used the Q-former architecture to fuse the text and image information. We also improved the traditional prognostic model by introducing time as a variable in the construction of the model, and finally obtained the corresponding prognostic results. Result: We assessed the efficacy of our methodology through the compilation of a multicenter dataset, achieving commendable outcomes in multicenter validations. Notably, our results for metastasis-free survival (MFS), recurrence-free survival (RFS), overall survival (OS), and progression-free survival (PFS) were as follows: 0.796, 0.626, 0.641, and 0.691. Our results demonstrate a notable superiority over the utilization of CT and PET independently, and exceed the result derived without the clinical textual information. Conclusions: Our model not only validates the effectiveness of multi-modal fusion in aiding diagnosis, but also provides insights for optimizing survival analysis. The study underscores the potential of our approach in enhancing prognosis and contributing to the advancement of personalized medicine in HNC. Full article

Parietal thinning was detected in a 72-year-old with recurrent headaches. Quantification of bone loss was performed applying two- and three-dimensional methods using computerized tomographies. Two-dimensional methods provided accurate measurements using single-line analyses of bone thicknesses (2.13 to 1.65 and 1.86 mm on the left and 4.44 to 3.08 and 4.20 mm on the right side), single-point analyses of bone intensities (693 to 375 and 403 on the left and 513 to 393 and 411 Houndsfield Units on the right side) and particle-size analyses of low density areas (16 to 22 and 12 on the left and 18 to 23 and 14 on the right side). Deteriorations between days 0 and 220 followed by bone stability on day 275 were paralleled using the changed volumes of bone defects to 1200 and finally 1133 mm³ on the left side and to 331 and finally 331 mm³ on the right side. Interfolding as measurement of the bones’ shape provided changes to −1.23 and −1.72 mm on the left and to −1.42 and −1.30 mm on the right side. These techniques suggest a stabilizing effect of corticosteroids between days 220 and 275. Reconstruction of computerized tomographies appears justified to allow for quantification of bone loss during long-term follow-up. Full article

The aim of the study was to build a machine learning-based predictive model to discriminate between hospitalized patients at low risk and high risk of bloodstream infection (BSI). A Data Mart including all patients hospitalized between January 2016 and December 2019 with suspected BSI was built. Multivariate logistic regression was applied to develop a clinically interpretable machine learning predictive model. The model was trained on 2016–2018 data and tested on 2019 data. A feature selection based on a univariate logistic regression first selected candidate predictors of BSI. A multivariate logistic regression with stepwise feature selection in five-fold cross-validation was applied to express the risk of BSI. A total of 5660 hospitalizations (4026 and 1634 in the training and the validation subsets, respectively) were included. Eleven predictors of BSI were identified. The performance of the model in terms of AUROC was 0.74. Based on the interquartile predicted risk score, 508 (31.1%) patients were defined as being at low risk, 776 (47.5%) at medium risk, and 350 (21.4%) at high risk of BSI. Of them, 14.2% (72/508), 30.8% (239/776), and 64% (224/350) had a BSI, respectively. The performance of the predictive model of BSI is promising. Computational infrastructure and machine learning models can help clinicians identify people at low risk for BSI, ultimately supporting an antibiotic stewardship approach. Full article

A 36-year-old woman, gravida 3, para 1 (previous cesarean section), with one medical abortion, and no history of systemic diseases presented an unremarkable medical history during prenatal visits. The final prenatal ultrasound at 38 weeks of gestation showed a vertex presentation, a weight of 2600 g, a normal amniotic fluid level, and the placenta located on the posterior wall of the uterus. Fetal cardiotocography conducted before delivery reported a reactive heart rate without decelerations. The Doppler wave analysis of the fetal umbilical artery was normal (the ratio of peak-systolic flow velocity to the end-diastolic flow velocity was 2.5) without the absence or reversal of end-diastolic velocity. The total score of the fetal biophysical profile by ultrasound was 8. The night before the scheduled cesarean section, she experienced heightened anxiety and was unable to sleep, noting “crazy” fetal movements throughout the night. During the cesarean section, it was discovered that the umbilical cord was wrapped around the newborn’s legs, resembling ankle shackles. The fetal weight was 2740 g, and Apgar scores were 9 at the first minute and 10 at the fifth minute. The motility of the neonatal legs was normal without cyanosis or neurological adverse outcomes. Full article

This study attempts to identify and briefly describe the current directions in applied and theoretical clinical prediction research. Context-rich chronic heart failure syndrome (CHFS) telemedicine provides the medical foundation for this effort. In the chronic stage of heart failure, there are sudden exacerbations of syndromes with subsequent hospitalizations, which are called acute decompensation of heart failure (ADHF). These decompensations are the subject of diagnostic and prognostic predictions. The primary purpose of ADHF predictions is to clarify the current and future health status of patients and subsequently optimize therapeutic responses. We proposed a simplified discrete-state disease model as an attempt at a typical summarization of a medical subject before starting predictive modeling. The study tries also to structure the essential common characteristics of quantitative models in order to understand the issue in an application context. The last part provides an overview of prediction works in the field of CHFS. These three parts provide the reader with a comprehensive view of quantitative clinical predictive modeling in heart failure telemedicine with an emphasis on several key general aspects. The target community is medical researchers seeking to align their clinical studies with prognostic or diagnostic predictive modeling, as well as other predictive researchers. The study was written by a non-medical expert. Full article

Magnetic resonance imaging (MRI) has been proven to be an indispensable imaging method in bladder cancer, and it can accurately identify muscular invasion of bladder cancer. Multiparameter MRI is a promising tool widely used for preoperative staging evaluation of bladder cancer. Vesical Imaging-Reporting and Data System (VI-RADS) scoring has proven to be a reliable tool for local staging of bladder cancer with high accuracy in preoperative staging, but VI-RADS still faces challenges and needs further improvement. Artificial intelligence (AI) holds great promise in improving the accuracy of diagnosis and predicting the prognosis of bladder cancer. Automated machine learning techniques based on radiomics features derived from MRI have been utilized in bladder cancer diagnosis and have demonstrated promising potential for practical implementation. Future work should focus on conducting more prospective, multicenter studies to validate the additional value of quantitative studies and optimize prediction models by combining other biomarkers, such as urine and serum biomarkers. This review assesses the value of multiparameter MRI in the accurate evaluation of muscular invasion of bladder cancer, as well as the current status and progress of its application in the evaluation of efficacy and prognosis. Full article

Background: This study is a systematic review with meta-analysis comparing radioactive seed localization (RSL) versus radio-guided occult lesion localization (ROLL) and wire-guided localization (WGL) for patients with impalpable breast cancer undergoing breast-conserving surgery and evaluating efficacy, safety, and logistical outcomes. The protocol is registered in PROSPERO with the number CRD42022299726. Methods: A search was conducted in the Embase, Lilacs, Pubmed, Scielo, Web of Science, and clinicaltrials.gov databases, in addition to a manual search in the reference list of relevant articles, for randomized clinical trials and cohort studies. Studies selected were submitted to their own data extraction forms and risk of bias analysis according to the ROB 2 and ROBINS 1 tools. A meta-analysis was performed, considering the random effect model, calculating the relative risk or the mean difference for dichotomous or continuous data, respectively. The quality of the evidence generated was analyzed by outcome according to the GRADE tool. Overall, 46 articles met the inclusion criteria and were included in this systematic review; of these, 4 studies compared RSL and ROLL with a population of 1550 women, and 43 compared RSL and WGL with a population of 19,820 women. Results: The results showed that RSL is a superior method to WGL in terms of surgical efficiency in the impalpable breast lesions’ intraoperative localization, and it is at least equivalent to ROLL. Regarding security, RSL obtained results equivalent to the already established technique, the WGL. In addition to presenting promising results, RSL has been proven to be superior to WGL and ROLL technologies. Full article

The COVID-19 pandemic, caused by SARS-CoV-2, has manifested distinct impacts on infants and children. This study delves into the intricate connection between lung ultrasound (LUS) findings and serum biomarkers in neonates and infants with COVID-19. Exploring factors contributing to the mild symptoms in this demographic, including immune responses and pre-existing immunity, the study spans 3 years and 9 months, involving 42 patients. Respiratory and gastrointestinal symptoms predominate, and LUS emerges as a vital, non-irradiating tool for evaluating pulmonary abnormalities. Serum biomarkers like CRP, procalcitonin, and cytokines provide key insights into the pathophysiology. Correlations reveal nuanced links between LUS score and clinical parameters, unveiling associations with hospitalization duration (rho = 0.49), oxygen saturation (rho = −0.88), and inflammatory markers, like ferritin (rho = 0.62), LDH (rho = 0.73), and D-dimer (rho = 0.73) with significance level (p < 0.05). The absence of large consolidations in LUS suggests unique pulmonary characteristics. The novelty of these findings lies in the comprehensive integration of LUS with serum biomarkers to assess and monitor the severity of lung involvement in neonates and infants affected by SARS-CoV-2. This approach offers valuable insights into disease severity, biomarker levels, the duration of hospitalization, and oxygen saturation, providing a multifaceted understanding of COVID-19’s impact on this vulnerable population. Full article

Esophageal cancer can be treated effectively with esophagectomy; however, the postoperative complication rate is high. In this paper, we study to what extent machine learning methods can predict anastomotic leakage and pneumonia up to two days in advance. We use a dataset with 417 patients who underwent esophagectomy between 2011 and 2021. The dataset contains multimodal temporal information, specifically, laboratory results, vital signs, thorax images, and preoperative patient characteristics. The best models scored mean test set AUROCs of 0.87 and 0.82 for leakage 1 and 2 days ahead, respectively. For pneumonia, this was 0.74 and 0.61 for 1 and 2 days ahead, respectively. We conclude that machine learning models can effectively predict anastomotic leakage and pneumonia after esophagectomy. Full article

Pancreatic ductal adenocarcinoma (PDAC) stands out as the predominant malignant neoplasm affecting the pancreas, characterized by a poor prognosis, in most cases patients being diagnosed in a nonresectable stage. Image-based artificial intelligence (AI) models implemented in tumor detection, segmentation, and classification could improve diagnosis with better treatment options and increased survival. This review included papers published in the last five years and describes the current trends in AI algorithms used in PDAC. We analyzed the applications of AI in the detection of PDAC, segmentation of the lesion, and classification algorithms used in differential diagnosis, prognosis, and histopathological and genomic prediction. The results show a lack of multi-institutional collaboration and stresses the need for bigger datasets in order for AI models to be implemented in a clinically relevant manner. Full article

Background and objectives: oral alterations in Systemic Sclerosis (SSc) patients are widespread and include microstomia, periodontitis, telangiectasias, mandibular resorption, bone lesions, and xerostomia. This cross-sectional study aims to evaluate the differences between SSc patients (cases) and healthy subjects (controls) regarding oral manifestations, quality of life (QoL), and microcirculation alterations. Methods: plaque index (PCR), periodontal index (PSR), DMFT, salivary flow rate, and buccal opening were measured by expert clinicians. S-HAQ test, the Self-Rating Anxiety State (SAS), the Self-Rating Depression Scale (SDS), and the WHOQOL-BREF test were administered to patients to evaluate their QoL. Microvascular alterations were assessed by oral videocapillaroscopy, performed on gingival and labial mucosa. A statistical analysis was conducted to find significant differences between healthy people and SSc patients. Results: 59 patients were enrolled in this study. Standard salivary flow is significantly more frequent in controls, while xerostomia, reduced flow, microstomia, lip retraction, and periodontitis are significantly more frequent in the cases. Gingival capillaroscopy showed differences concerning loop visibility, thickening of the gum, tortuosity of gingival loops, and reduced gingival density. Labial capillaroscopy demonstrates that visibility of the labial loops, the labial ectasias, and the tortuosity of the loops are significantly associated with the presence of scleroderma. Hand and facial deformities, hypomobility of the tongue, cheeks, lips, microstomia, and xerostomia significantly compromised the quality of life of SSc patients, which was significantly worse among them. Moreover, oral videocapillaroscopy could be a proper diagnostic method to detect oral microcirculation alterations. SSc patients often present ectasias, rarefaction of the reticulum, microhemorrhages, and megacapillaries, which negatively impact their oral health. Conclusions: periodontitis, reduced salivary flow, and microstomia could be considered SSc oral manifestations. Joint deformities, facial appearance, and comorbidities significantly reduce the QoL of SSc patients compared to healthy subjects. Oral videocapillaroscopy could be an innovative and reliable technique to detect oral microcirculation anomalies. Full article

The ambulatory glucose profile (AGP) lacks sufficient statistical metrics and insightful graphs; indeed, it is missing important information on the temporal patterns of glucose variations. The AGP graph is difficult to interpret due to the overlapping metrics and fluctuations in glucose levels over 14 days. The objective of this proposed work is to overcome these challenges, specifically the lack of insightful information and difficulty in interpreting AGP graphs, to create a platform for decision assistance. The present work proposes 20 findings built from decision rules that were developed from a combination of AGP metrics and additional statistical metrics, which have the potential to identify patterns and insightful information on hyperglycemia and hypoglycemia. The “CGM Trace” webpage was developed, in which insightful metrics and graphical representations can be used to make inferences regarding the glucose data of any user. However, doctors (endocrinologists) can access the “Findings” tab for a summarized presentation of their patients’ glycemic control. The findings were implemented for 67 patients’ data, in which the data of 15 patients were collected from a clinical study and the data of 52 patients were gathered from a public dataset. The findings were validated by means of MANOVA (multivariate analysis of variance), wherein a p value of < 0.05 was obtained, depicting a strong significant correlation between the findings and the metrics. The proposed work from “CGM Trace” offers a deeper understanding of the CGM data, enhancing AGP reports for doctors to make treatment adjustments based on insightful information and hidden patterns for better diabetic management. Full article

Sagittal craniosynostosis, a rare but fascinating craniofacial anomaly, presents a unique challenge for both diagnosis and treatment. This condition involves premature fusion of the sagittal suture, which alters the normal growth pattern of the skull and can affect neurological development. Sagittal craniosynostosis is characterised by a pronounced head shape, often referred to as scaphocephaly. Asymmetry of the face and head, protrusion of the fontanel, and increased intracranial pressure are common clinical manifestations. Early recognition of these features is crucial for early intervention, and understanding the aetiology is, therefore, essential. Although the exact cause remains unclear, genetic factors are thought to play an important role. Mutations in genes such as FGFR2 and FGFR3, which disrupt the normal development of the skull, are suspected. Environmental factors and various insults during pregnancy can also contribute to the occurrence of the disease. An accurate diagnosis is crucial for treatment. Imaging studies such as ultrasound, computed tomography, magnetic resonance imaging, and three-dimensional reconstructions play a crucial role in visualising the prematurely fused sagittal suture. Clinicians also rely on a physical examination and medical history to confirm the diagnosis. Early detection allows for quick intervention and better treatment outcomes. The treatment of sagittal craniosynostosis requires a multidisciplinary approach that includes neurosurgery, craniofacial surgery, and paediatric care. Traditional treatment consists of an open reconstruction of the cranial vault, where the fused suture is surgically released to allow normal growth of the skull. However, advances in minimally invasive techniques, such as endoscopic strip craniectomy, are becoming increasingly popular due to their lower morbidity and shorter recovery times. This review aims to provide a comprehensive overview of sagittal craniosynostosis, highlighting the aetiology, clinical presentation, diagnostic methods, and current treatment options. Full article

Point-of-Care Ultrasound (POCUS) is a rapid and valuable diagnostic tool available in emergency and intensive care units. In the context of cardiac arrest, POCUS application can help assess cardiac activity, identify causes of arrest that could be reversible (such as pericardial effusion or pneumothorax), guide interventions like central line placement or pericardiocentesis, and provide real-time feedback on the effectiveness of resuscitation efforts, among other critical applications. Its use, in addition to cardiovascular life support maneuvers, is advocated by all resuscitation guidelines. The purpose of this narrative review is to summarize the key applications of POCUS in cardiac arrest, highlighting, among others, its prognostic, diagnostic, and forensic potential. We conducted an extensive literature review utilizing PubMed by employing key search terms regarding ultrasound and its use in cardiac arrest. Apart from its numerous advantages, its limitations and challenges such as the potential for interruption of chest compressions during image acquisition and operator proficiency should be considered as well and are discussed herein. Full article

The binocular Esterman visual field test (EVFT) of 120 points was the first method to quantify the defects in the binocular visual field. It is used in many parts of the world as a standard test to determine whether an individual has the visual capabilities to drive safely. In Japan, it is required for the grading and issuance of visual disability certificates. The purpose of this study was to determine the reliability of the EVFT results. We studied 104 patients who had undergone the binocular EVFT at Mie University Hospital. Their mean age was 68.0 ± 11.4 years, and the best-corrected visual acuity of the better eye was 0.18 ± 0.38 logMAR units. The EVFT was performed twice on the same day, and the results of the first and second tests were compared. The mean Esterman scores for the first and second test were 89.3 ± 30.5 and 89.1 ± 30.2, respectively, and the test times were 338.9 ± 86.8 and 336.7 ± 76.4 s, respectively. The differences were not significant (p = 0.69 and p = 0.33). In the Bland–Altman analyses (second–first test) of the Esterman scores, the mean difference was 0.38 without significant fixed errors (p = 0.20) or proportional errors (p = 0.27). The limits of agreement within the 1.96 standard deviation were −8.96 to +9.45 points. The agreement rate for the most peripheral 24 test points was significantly lower than the agreement rate for the other 96 test points (p < 0.01). The agreement rate of the upper visual field was significantly lower than that of the lower field (p < 0.01). The overall reliability rate of the EVFT is acceptable, but the peripheral and upper test points have relatively low reliability rates. These findings are important for interpretations of the EVFT results. Full article

The presence of lymphovascular invasion (LVI) in urothelial carcinoma (UC) is a poor prognostic finding. This is difficult to identify on routine hematoxylin–eosin (H&E)-stained slides, but considering the costs and time required for examination, immunohistochemical stains for the endothelium are not the recommended diagnostic protocol. We developed an AI-based automated method for LVI identification on H&E-stained slides. We selected two separate groups of UC patients with transurethral resection specimens. Group A had 105 patients (100 with UC; 5 with cystitis); group B had 55 patients (all with high-grade UC; D2-40 and CD34 immunohistochemical stains performed on each block). All the group A slides and 52 H&E cases from group B showing LVI using immunohistochemistry were scanned using an Aperio GT450 automatic scanner. We performed a pixel-per-pixel semantic segmentation of selected areas, and we trained InternImage to identify several classes. The DiceCoefficient and Intersection-over-Union scores for LVI detection using our method were 0.77 and 0.52, respectively. The pathologists’ H&E-based evaluation in group B revealed 89.65% specificity, 42.30% sensitivity, 67.27% accuracy, and an F1 score of 0.55, which is much lower than the algorithm’s DCC of 0.77. Our model outlines LVI on H&E-stained-slides more effectively than human examiners; thus, it proves a valuable tool for pathologists. Full article

The purpose of this study was to investigate the possibility of implementing an artificial intelligence (AI) approach for the analysis of fluorescence lifetime imaging ophthalmoscopy (FLIO) data even with small data. FLIO data, including the fluorescence intensity and mean fluorescence lifetime (τm) of two spectral channels, as well as OCT-A data from 26 non-smokers and 28 smokers without systemic and ocular diseases were used. The analysis was performed with support vector machines (SVMs), a well-known AI method for small datasets, and compared with the results of convolutional neural networks (CNNs) and autoencoder networks. The SVM was the only tested AI method, which was able to distinguish τ_m between non-smokers and heavy smokers. The accuracy was about 80%. OCT-A data did not show significant differences. The feasibility and usefulness of the AI in analyzing FLIO and OCT-A data without any apparent retinal diseases were demonstrated. Although further studies with larger datasets are necessary to validate the results, the results greatly suggest that AI could be useful in analyzing FLIO-data even from healthy subjects without retinal disease and even with small datasets. AI-assisted FLIO is expected to greatly advance early retinal diagnosis. Full article

Background. Corpus callosal abnormalities (CCA) are midline developmental brain malformations and are usually associated with a wide spectrum of other neurological and non-neurological abnormalities. The study aims to highlight the diagnostic role of fetal MRI to characterize heterogeneous corpus callosal abnormalities using the latest classification system. It also helps to identify associated anomalies, which have prognostic implications for the postnatal outcome. Methods. In this study, retrospective data from antenatal women who underwent fetal MRI between January 2014 and July 2023 at Rush University Medical Center were evaluated for CCA and classified based on structural morphology. Patients were further assessed for associated neurological and non-neurological anomalies. Results. The most frequent class of CCA was complete agenesis (79.1%), followed by hypoplasia (12.5%), dysplasia (4.2%), and hypoplasia with dysplasia (4.2%). Among them, 17% had isolated CCA, while the majority (83%) had complex forms of CCA associated with other CNS and non-CNS anomalies. Out of the complex CCA cases, 58% were associated with other CNS anomalies, while 8% were associated with non-CNS anomalies. 17% of cases had both. Conclusion. The use of fetal MRI is valuable in the classification of abnormalities of the corpus callosum after the confirmation of a suspected diagnosis on prenatal ultrasound. This technique is an invaluable method for distinguishing between isolated and complex forms of CCA, especially in cases of apparent isolated CCA. The use of diffusion-weighted imaging or diffusion tensor imaging in fetal neuroimaging is expected to provide further insights into white matter abnormalities in fetuses diagnosed with CCA in the future. Full article

COVID-19-associated rhino-orbital mucormycosis has become a new clinical entity. This study’s aim was to evaluate the histopathological and ultramicroscopic morphological aspects of this fungal infection. This was an observational retrospective study on eight patients from three tertiary centers in Romania. The tissue samples collected during functional endoscopic sinus surgery were studied through histopathological examination, scanning electron microscopy, and transmission electron microscopy. In the histopathological examination, the morphological aspects characteristic of mucormycosis in all cases were identified: wide aseptate hyphae with right-angle ramifications, which invade blood vessels. One case presented perineural invasion into the perineural lymphatics. And in another case, mucormycosis–aspergillosis fungal coinfection was identified. Through scanning electron microscopy, long hyphae on the surface of the mucosa surrounded by cells belonging to the local immune system were identified in all samples, and bacterial biofilms were identified in half of the samples. Through transmission electron microscopy, aseptate hyphae and bacterial elements were identified in the majority of the samples. Rhino-orbital-cerebral mucormycosis associated with COVID-19 produces nasal sinus dysbiosis, which favors the appearance of bacterial biofilms. The way in which the infection develops depends on the interaction of the fungi with cells of the immune system. Full article

Objectives: The purpose of this study was to investigate the imaging characteristics of medication-related osteonecrosis of the jaw (MRONJ) using [18F]fluoride positron emission tomography/computed tomography (PET/CT) and [18F]fluorodeoxyglucose (FDG) PET/magnetic resonance imaging (MRI) for preoperative assessment and to correlate them with microarchitectural and histomorphometric data with respect to clinical findings. Methods: Twelve patients (five female; mean age 75 ± 7.6 yr) with symptomatic MRONJ underwent both scans on the same day, and imaging findings were used to plan surgical interventions for seven patients. Bone tracer uptake was classified as high, medium, or low, and surgical samples were evaluated using Micro-CT and histomorphometric analysis. Results: CT showed medullary sclerosis in all patients, and MRI revealed gadolinium enhancement in four patients. PET imaging revealed remarkably elevated [18F]fluoride uptake and moderately increased [18F]FDG uptake in MRONJ compared to healthy jawbones, with both differences being statistically significant. [18F]fluoride uptake was associated with necrosis, bacteria, and inflammatory tissue. Micro-CT data did not show significant differences, but histomorphometric analysis revealed higher osteocyte and lacunae densities in the high [18F]fluoride uptake group, and more necrotic bone in the medium [18F]fluoride uptake group. Bacteria were observed in all areas. Conclusions: In summary, [18F]fluoride PET accurately identified MRONJ extent, revealing functional changes in jawbone remodeling not visible on CT. [18F]FDG PET showed differences in bone and soft tissue, though less pronounced. This method aids in evaluating disease activity and guiding treatment planning, requiring further research for optimal surgical approaches based on tracer uptake. Full article

A small tumor size may impact the diagnostic performance of endoscopic ultrasound-guided tissue acquisition (EUS-TA) for diagnosing solid pancreatic lesions (SPLs). We aimed to compare the diagnostic yield of EUS-guided fine-needle aspiration (FNA) and biopsy (FNB) in SPLs with a diameter ≤ 15 mm. Consecutive patients who underwent EUS-TA for SPLs ≤ 15 mm between January 2015 and December 2022 in a tertiary referral center were retrospectively evaluated. The primary endpoint was diagnostic accuracy. The final diagnosis was based on surgical pathology or disease evolution after a minimum follow-up of 6 months. Inadequate samples were all considered false negatives for the study. Secondary outcomes included sample adequacy, factors impacting accuracy, and safety. We included 368 patients (52.4% male; mean age: 60.2 years) who underwent FNA in 72 cases and FNB in 296. The mean size of SPLs was 11.9 ± 2.6 mm. More than three passes were performed in 5.7% and 61.5% of patients in the FNB and FNA groups, respectively (p < 0.0001). FNB outperformed FNA in terms of diagnostic accuracy (89.8% vs. 79.1%, p = 0.013) and sample adequacy (95.9% vs. 86.1%, p < 0.001). On multivariate analysis, using FNA (OR: 2.10, 95% CI: 1.07–4.48) and a final diagnosis (OR: 3.56, 95% CI: 1.82–6.94) of benign conditions negatively impacted accuracy. Overall, the adverse event rate was 0.8%, including one pancreatitis in the FNA group and one pancreatitis and one bleeding in the FNB group, all mild and conservatively managed. EUS-TA for SPLs ≤ 15 mm has a high diagnostic yield and safety. This study suggests the superiority of FNB over FNA, with better performance even with fewer passes performed. Full article

Depression is a prevalent and debilitating mental health condition that poses significant challenges for healthcare providers, researchers, and policymakers. The diagnostic coding specificity of depression is crucial for improving patient care, resource allocation, and health outcomes. We propose a novel approach to assess risk-adjusted coding specificity for individuals diagnosed with depression using a vast cohort of over one million inpatient hospitalizations in the United States. Considering various clinical, demographic, and socioeconomic characteristics, we develop a risk-adjusted model that assesses diagnostic coding specificity. Results demonstrate that risk-adjustment is necessary and useful to explain variability in the coding specificity of principal (AUC = 0.76) and secondary (AUC = 0.69) diagnoses. Our approach combines a multivariate logistic regression at the patient hospitalization level to extract risk-adjusted probabilities of specificity with a Poisson Binomial approach at the facility level. This method can be used to identify healthcare facilities that over- and under-specify diagnostic coding when compared to peer-defined standards of practice. Full article

Adequacy of anesthesia concept (AoA) in the guidance of general anesthesia (GA) is based on entropy, and it also reflects the actual depth of anesthesia and the surgical pleth index (SPI). Therefore, this study aimed to analyze the potential existence of relationships between SPI values at certain stages of the AoA-guided GA for vitreoretinal surgeries (VRS) and the incidence of intolerable postoperative pain perception (IPPP). A total of 175 patients were each assigned to one of five groups. In the first, the VRS procedure was performed under GA without premedication; in the second group, patients received metamizole before GA; in the third, patients received acetaminophen before GA; in the fourth group, patients received Alcaine before GA; and, in the peribulbar block group, the patients received a peribulbar block with a mix of the solutions of lignocaine and bupivacaine. Between the patients declaring mild and statistically significant differences in the IPPP in terms of SPI values before induction (52.3 ± 18.8 vs. 63.9 ± 18.1, p < 0.05) and after emergence from GA (51.1 ± 13 vs. 68.1 ± 8.8; p < 0.001), it was observed that the patients postoperatively correlated with heart rate variations despite the group allocation. The current study proves the feasibility that preoperative SPI values help with predicting IPPP immediately after VRS under AoA guidance and discrimination (between mild diagnoses and IPPP when based on postoperative SPI values) as they correlate with heart rate variations. Specifically, this applies when the countermeasures of IPPP and hemodynamic fluctuations are understood to be of importance in reducing unwelcome adverse events. Full article