Diagnostics

Background: The Paris System for Reporting Urinary Cytology (TPS) is considered the gold standard when it comes to diagnostic classifications of urine specimens. Its second edition brought some important changes, including the abolition of the diagnostic category of “low-grade urothelial neoplasm (LGUN)”, acknowledging the inability of cytology to reliably discern low-grade urothelial lesions. Methods: In this retrospective study, we assessed the validity of this change, studying the cytological diagnoses of histologically diagnosed low-grade urothelial carcinomas during a three-year period. Moreover, we correlated the sum of the urinary cytology diagnoses of this period with the histological diagnoses, whenever available. Results: Although all the cytological diagnoses of LGUN were concordant with the histological diagnoses, most low-grade urothelial carcinomas were misdiagnosed cytologically. Subsequently, the positive predictive value (PPV) of urinary cytology for the diagnosis of LGUN was 100%, while the sensitivity was only 21.7%. Following the cyto-histopathological correlation of the sum of the urinary cytology cases, the sensitivity of urinary cytology for the diagnosis of high-grade urothelial carcinoma (HGUC) was demonstrated to be 90.1%, the specificity 70.8%, the positive predictive value (PPV) 60.3%, the negative predictive value (NPV) 93.6% and the overall accuracy 77.2%, while for LGUN, the values were 21.7%, 97.2%, 87.5%, 58.6% and 61.9%, respectively. Risk of high-grade malignancy was 0% for the non-diagnostic (ND), 4.8% for the non-high-grade urothelial carcinoma (NHGUC), 33.3% for the atypical urothelial cells (AUCs), 65% for the suspicious for high-grade urothelial carcinoma (SHGUC), 100% for the HGUC and 12.5% for the LGUN diagnostic categories. Conclusions: This study validates the incorporation of the LGUN in the NHGUC diagnostic category in the second edition of TPS. Moreover, it proves the ability of urinary cytology to safely diagnose HGUC and stresses the pivotal role of its diagnosis. Full article

EEG-based emotion recognition has numerous real-world applications in fields such as affective computing, human-computer interaction, and mental health monitoring. This offers the potential for developing IOT-based, emotion-aware systems and personalized interventions using real-time EEG data. This study focused on unique EEG channel selection and feature selection methods to remove unnecessary data from high-quality features. This helped improve the overall efficiency of a deep learning model in terms of memory, time, and accuracy. Moreover, this work utilized a lightweight deep learning method, specifically one-dimensional convolutional neural networks (1D-CNN), to analyze EEG signals and classify emotional states. By capturing intricate patterns and relationships within the data, the 1D-CNN model accurately distinguished between emotional states (HV/LV and HA/LA). Moreover, an efficient method for data augmentation was used to increase the sample size and observe the performance deep learning model using additional data. The study conducted EEG-based emotion recognition tests on SEED, DEAP, and MAHNOB-HCI datasets. Consequently, this approach achieved mean accuracies of 97.6, 95.3, and 89.0 on MAHNOB-HCI, SEED, and DEAP datasets, respectively. The results have demonstrated significant potential for the implementation of a cost-effective IoT device to collect EEG signals, thereby enhancing the feasibility and applicability of the data. Full article

The spleen, often referred to as the “forgotten organ”, plays numerous important roles in various diseases. Recently, there has been an increased interest in the application of radiomics in different areas of medical imaging. This systematic review aims to assess the current state of the art and evaluate the methodological quality of radiomics applications in spleen imaging. A systematic search was conducted on PubMed, Scopus, and Web of Science. All the studies were analyzed, and several characteristics, such as year of publication, research objectives, and number of patients, were collected. The methodological quality was evaluated using the radiomics quality score (RQS). Fourteen articles were ultimately included in this review. The majority of these articles were published in non-radiological journals (78%), utilized computed tomography (CT) for extracting radiomic features (71%), and involved not only the spleen but also other organs for feature extraction (71%). Overall, the included papers achieved an average RQS total score of 9.71 ± 6.37, corresponding to an RQS percentage of 27.77 ± 16.04. In conclusion, radiomics applications in spleen imaging demonstrate promising results in various clinical scenarios. However, despite all the included papers reporting positive outcomes, there is a lack of consistency in the methodological approaches employed. Full article

Medulloblastoma (MB) is the most common malignant central nervous system tumor of childhood, which includes multiple molecular subgroups (4) and subtypes (8 to 12), each with different outcomes and potential therapy options. Long-term survival remains poor for many of the subtypes, with high late mortality risks and poor health-related quality of life. Initial treatment strategies integrate molecular subgroup information with more standard clinical and phenotypic factors to risk stratify newly diagnosed patients. Clinical trials treating relapsed disease, often incurable, now include multiple new approaches in an attempt to improve progression-free and overall survival. Full article

Low baseline levels of parathyroid hormone (PTH) are associated with a higher rate of multiglandular disease, lower localization rates of preoperative imaging modalities, and a higher rate of unsuccessful minimally invasive parathyroidectomies. The objective of this study is to assess the diagnostic value of four-dimensional dynamic computed tomography (4D-CT) in localizing primary hyperparathyroidism (pHPT) in patients with low baseline PTH levels, compared to patients with high baseline PTH levels. Patients with pHPT who received a 4D-CT scan as part of their standard diagnostic evaluation were divided into two groups based on the following criteria: (1) preoperative PTH levels less than 100 pg/mL and (2) patients with preoperative PTH levels greater than 100 pg/mL. All patients underwent parathyroidectomy based on 4D-CT findings, with intraoperative parathyroid hormone monitoring. The lesion-based sensitivity of 4D-CT was 88% in patients with low baseline PTH levels and 94.7% in patients with high baseline PTH levels (p = 0.33). However, the success rate of image-guided resection based on 4D-CT findings was 71.4% in the low baseline PTH group compared to 90.6% in the high baseline PTH group (p = 0.06). Our study demonstrated that 4D-CT has a high lesion-based sensitivity in patients with pHPT and low baseline PTH levels but led to a relatively low rate of successful image-guided resection in patients with low baseline PTH levels. Therefore, it is important to exercise increased caution during 4D-CT-guided surgical exploration of patients with low baseline PTH levels to ensure successful surgical resection of all parathyroid lesions. Full article

Prognosis in recurrent/metastatic head and neck squamous-cell carcinoma (HNSCC) refractory to platinum-based chemotherapy is poor, making therapy optimization a priority. Anti-programmed cell death protein 1 (anti-PD-1) monoclonal antibody Nivolumab was approved in such cases. We present the early experience with Nivolumab immunotherapy at three cancer clinics from south and northeast Romania, aiming to describe the main characteristics and outcomes relative to literature reports, and to suggest patient selection criteria. Diagnostic, clinical, biological, therapeutic, and outcomes-related data from January 2020 until March 2023 were analyzed retrospectively. Eighteen patients with platinum refractory HNSCC (85.7% men, median age 58.9) were administered Nivolumab for 1–14 months (median 5.6 months) in addition to other treatments (surgery, radiotherapy, chemotherapy), and monitored for up to 25 months. Median neutrophil-to-lymphocyte ratio (NLR) ranged from 2.72 initially to 6.01 during treatment. Overall survival (OS) was 16 months, and patients who died early had the sharpest NLR increases (13.07/month). There were no severe immune-related adverse events. Lower NLR values and combined intensive chemotherapy, radiotherapy, and immunotherapy were related to better outcomes. To our knowledge, we also report the first two cases of second primary malignancy (SPM) in the head and neck region treated with Nivolumab in Romania (for which the sequential administration of radiotherapy and immunotherapy seems better). The work of other Romanian authors on the role of HPV status in HNC is also discussed. Multi-center trials are needed in order to investigate and confirm these observations. Full article

Background: The hemodynamic definition of PH has recently been revised with unchanged threshold of peak tricuspid regurgitation velocity (TRV). The aim of this study was to evaluate the predictive accuracy of peak TRV for PH based on the new (>20 mmHg) and the old (>25 mmHg) cut-off value for mean pulmonary artery pressure (mPAP) and to compare it with the mean right ventricular–right atrial (RV–RA) pressure gradient. Methods: Patients with advanced heart failure were screened from 2016 to 2021. The exclusion criteria were absent right heart catheterization (RHC) results, chronic obstructive pulmonary disease, any septal defect, inadequate acoustic window or undetectable TR. The mean RV–RA gradient was calculated from the velocity–time integral of TR. Results: The study included 41 patients; 34 (82.9%) had mPAP > 20 mmHg and 24 (58.5%) had mPAP > 25 mmHg. The AUC for the prediction of PH with mPAP > 20 mmHg was 0.855 for peak TRV and mean RV–RA gradient was 0.811. AUC for the prediction of PH defined as mPAP > 25 mmHg for peak TRV was 0.860 and for mean RV–RA gradient was 0.830. A cutoff value of 2.4 m/s for peak TRV had 65% sensitivity and 100% positive predictive value for predicting PH according to the new definition. Conclusions: Peak TRV performed better than mean RV–RA pressure gradient in predicting PH irrespective of hemodynamic definitions. Peak TRV performed similarly with the two definitions of PH, but a lower cutoff value had higher sensitivity and equal positive predictive value for PH. Full article

Performance measures are an important tool for assessing and comparing different medical image segmentation algorithms. Unfortunately, the current measures have their weaknesses when it comes to assessing certain edge cases. These limitations arise when images with a very small region of interest or without a region of interest at all are assessed. As a solution to these limitations, we propose a new medical image segmentation metric: MISm. This metric is a composition of the Dice similarity coefficient and the weighted specificity. MISm was investigated for definition gaps, an appropriate scoring gradient, and different weighting coefficients used to propose a constant value. Furthermore, an evaluation was performed by comparing the popular metrics in the medical image segmentation and MISm using images of magnet resonance tomography from several fictitious prediction scenarios. Our analysis shows that MISm can be applied in a general way and thus also covers the mentioned edge cases, which are not covered by other metrics, in a reasonable way. In order to allow easy access to MISm and therefore widespread application in the community, as well as reproducibility of experimental results, we included MISm in the publicly available evaluation framework MISeval. Full article

One of the most common and deadly diseases in the world is lung cancer. Only early identification of lung cancer can increase a patient’s probability of survival. A frequently used modality for the screening and diagnosis of lung cancer is computed tomography (CT) imaging, which provides a detailed scan of the lung. In line with the advancement of computer-assisted systems, deep learning techniques have been extensively explored to help in interpreting the CT images for lung cancer identification. Hence, the goal of this review is to provide a detailed review of the deep learning techniques that were developed for screening and diagnosing lung cancer. This review covers an overview of deep learning (DL) techniques, the suggested DL techniques for lung cancer applications, and the novelties of the reviewed methods. This review focuses on two main methodologies of deep learning in screening and diagnosing lung cancer, which are classification and segmentation methodologies. The advantages and shortcomings of current deep learning models will also be discussed. The resultant analysis demonstrates that there is a significant potential for deep learning methods to provide precise and effective computer-assisted lung cancer screening and diagnosis using CT scans. At the end of this review, a list of potential future works regarding improving the application of deep learning is provided to spearhead the advancement of computer-assisted lung cancer diagnosis systems. Full article

Spondylolysis is underdiagnosed and often missed in non-musculoskeletal abdominal CT imaging. Our aim was to assess the inter-reader agreement and diagnostic performance of a novel “Darth Vader sign” for the detection of spondylolysis in routine axial images. We performed a retrospective search in the institutional report archives through keyword strings for lumbar spondylolysis and spondylolisthesis. Abdominal CTs from 53 spondylolysis cases (41% female) and from controls (n = 6) without spine abnormalities were identified. A total of 139 single axial slices covering the lumbar spine (86 normal images, 40 with spondylolysis, 13 with degenerative spondylolisthesis without spondylolysis) were exported. Two radiology residents rated all images for the presence or absence of the “Darth Vader sign”. The diagnostic accuracy for both readers, as well as the inter-reader agreement, was calculated. The “Darth Vader sign” showed an inter-reader agreement of 0.77. Using the “Darth Vader sign”, spondylolysis was detected with a sensitivity and specificity of 65.0–88.2% and 96.2–99.0%, respectively. The “Darth Vader sign” shows excellent diagnostic performance at a substantial inter-reader agreement for the detection of spondylolysis. Using the “Darth Vader sign” in the CT reading routine may be an easy yet effective tool to improve the detection rate of spondylolysis in non-musculoskeletal cases and hence improve patient care. Full article

Background: Distal tibiofibular injuries are common in patients with malleolar fractures. Malreduction is frequently reported in the literature and is mainly caused by insufficient intraoperative radiological evaluation. In this direction, we performed a prospective observational study to validate the efficacy of the anatomical landmarks of the anterior incisura corner. Methods: Patients with malleolar fractures and syndesmotic instability were reduced according to specific anatomic landmarks and had a postoperative bilateral ankle CT. The quality of the reduction was compared to the healthy ankles. Results: None of the controlled parameters differed significantly between the operated and healthy ankles. Minor deviations were correlated to the normal incisura morphology rather than the reduction technique. Conclusions: The anterior incisura anatomical landmarks can be an efficient way of reducing the distal tibiofibular joint without the need for intraoperative radiological evaluation. Full article

The carotid artery is a major blood vessel that supplies blood to the brain. Plaque buildup in the arteries can lead to cardiovascular diseases such as atherosclerosis, stroke, ruptured arteries, and even death. Both invasive and non-invasive methods are used to detect plaque buildup in the arteries, with ultrasound imaging being the first line of diagnosis. This paper presents a comprehensive review of the existing literature on ultrasound image analysis methods for detecting and characterizing plaque buildup in the carotid artery. The review includes an in-depth analysis of datasets; image segmentation techniques for the carotid artery plaque area, lumen area, and intima–media thickness (IMT); and plaque measurement, characterization, classification, and stenosis grading using deep learning and machine learning. Additionally, the paper provides an overview of the performance of these methods, including challenges in analysis, and future directions for research. Full article

The aim of this systematic review is to provide a comprehensive overview of the role of fluoro-5α-dihydrotestosterone ([¹⁸F]-FDHT) for the in vivo imaging of androgen receptors (AR) through positron emission tomography (PET) in metastatic breast (mBC) and metastatic castration-resistant prostate cancer (mCRPC). Relevant studies published from 2013 up to May 2023 were selected by searching Scopus, PubMed and Web of Science. The selected imaging studies were analyzed using a modified version of the critical Appraisal Skills Programme (CASP). Eleven studies encompassing 321 patients were selected. Seven of the eleven selected papers included 266 subjects (82.2%) affected by mCRPC, while four encompassed 55 (17.2%) patients affected by mBC. [¹⁸F]-FDHT PET showed a satisfying test/retest reproducibility, and when compared to a histochemical analysis, it provided encouraging results for in vivo AR quantification both in mCRPC and mBC. [¹⁸F]-FDHT PET had a prognostic relevance in mCRPC patients submitted to AR-targeted therapy, while a clear association between [¹⁸F]-FDHT uptake and the bicalutamide response was not observed in women affected by AR-positive mBC. Further studies are needed to better define the role of [¹⁸F]-FDHT PET, alone or in combination with other tracers (i.e., [¹⁸F]-FDG/[¹⁸F]-FES), for patients’ selection and monitoring during AR-targeted therapy, especially in the case of mBC. Full article

Assessing coronary physiology after stent implantation facilitates the optimisation of percutaneous coronary intervention (PCI). Coronary artery disease (CAD) patterns can be characterised by the pullback pressure gradient (PPG) index. The impact of focal vs. diffuse disease on physiology-guided incremental optimisation strategy (PIOS) is unknown. This is a sub-study of the TARGET-FFR randomized clinical trial (NCT03259815). The study protocol directed that optimisation be attempted for patients in the PIOS arm when post-PCI FFR was <0.90. Overall, 114 patients (n = 61 PIOS and 53 controls) with both pre-PCI fractional flow reserve (FFR) pullbacks and post-PCI FFR were included. A PPG ≥ 0.74 defined focal CAD. The PPG correlated significantly with post-PCI FFR (r = 0.43; 95% CI 0.26 to 0.57; p-value < 0.001) and normalised delta FFR (r = 0.49; 95% CI 0.34 to 0.62; p-value < 0.001). PIOS was more frequently applied to vessels with diffuse CAD (6% focal vs. 42% diffuse; p-value = 0.006). In patients randomized to PIOS, those with focal disease achieved higher post-PCI FFR than patients with diffuse CAD (0.93 ± 0.05 vs. 0.83 ± 0.07, p < 0.001). There was a significant interaction between CAD patterns and the randomisation arm for post-PCI FFR (p-value for interaction = 0.004). Physiology-guided stent optimisation was applied more frequently to vessels with diffuse disease; however, patients with focal CAD at baseline achieved higher post-PCI FFR. Full article

Awareness of gender differences in cardiovascular disease (CVD) has increased: both the different impact of traditional cardiovascular risk factors on women and the existence of sex-specific risk factors have been demonstrated. Therefore, it is essential to recognize typical aspects of ischemic heart disease (IHD) in women, who usually show a lower prevalence of obstructive coronary artery disease (CAD) as a cause of acute coronary syndrome (ACS). It is also important to know how to recognize pathologies that can cause acute chest pain with a higher incidence in women, such as spontaneous coronary artery dissection (SCAD) and myocardial infarction with non-obstructive coronary arteries (MINOCA). Coronary computed tomography angiography (CCTA) and cardiac magnetic resonance imaging (CMR) gained a pivotal role in the context of cardiac emergencies. Thus, the aim of our review is to investigate the most frequent scenarios in women with acute chest pain and how advanced cardiac imaging can help in the management and diagnosis of ACS. Full article

Because it is associated with most multifactorial inherited diseases like heart disease, hypertension, diabetes, and other serious medical conditions, obesity is a major global health concern. Obesity is caused by hereditary, physiological, and environmental factors, as well as poor nutrition and a lack of exercise. Weight loss can be difficult for various reasons, and it is diagnosed via BMI, which is used to estimate body fat for most people. Muscular athletes, for example, may have a BMI in the obesity range even when they are not obese. Researchers from a variety of backgrounds and institutions devised different hypotheses and models for the prediction and classification of obesity using different approaches and various machine learning techniques. In this study, a majority voting-based hybrid modeling approach using a gradient boosting classifier, extreme gradient boosting, and a multilayer perceptron was developed. Seven distinct machine learning algorithms were used on open datasets from the UCI machine learning repository, and their respective accuracy levels were compared before the combined approaches were chosen. The proposed majority voting-based hybrid model for prediction and classification of obesity that was achieved has an accuracy of 97.16%, which is greater than both the individual models and the other hybrid models that have been developed. Full article

Hip pain is indubitably a frequent clinical problem deriving from copious etiologies. Hip impingement syndromes are one of the most prevalent causes of persistent groin pain, especially in young and active patients. Diligent imaging of the hip region is indispensable to discern femoroacetabular impingement, as the differential diagnosis of hip pain can be exceedingly arduous. Despite hip radiography being plain and broadly attainable, it offers narrow information concerning soft tissue pathologies around the hip joint (extra-articular hip impingement syndromes). Magnetic resonance imaging and arthrography remain the gold standard examination for detecting intra-articular pathologies; however, they are widely considered expensive, time-consuming and characterized by confined. Consequently, ultrasonography has emerged as an alternative valuable diagnostic tool for distinguishing the underlying abnormalities that trigger femoroacetabular impingement. Proper hip ultrasound examination provides dynamic assessment, while also beneficial for guided intervention around the hip joint. Ultrasound hip examination is exacting due to its complex regional anatomy and deep location. It is capable of providing detailed information about various hip quadrants. An adept operator can identify both intra-articular and extra-articular pathologies. In addition, with ultrasonography, hip injections have been rendered relatively undemanding, aiding in therapeutic and diagnostic purposes. This paper aims to provide a succinct and compendious review of the existing literature, accentuating the crucial role of ultrasonography in diagnosing hip impingement syndromes and determining whether an additional examination is required regarding distinguishing between intra-articular and extra-articular syndromes. Full article

A prostate-targeted biopsy (TB) core is usually collected from a site where magnetic resonance imaging (MRI) indicates possible cancer. However, the extent of the lesion is difficult to accurately predict using MRI or TB alone. Therefore, we performed several biopsies around the TB site (perilesional [p] TB) and analyzed the association between the positive cores obtained using TB and pTB and the Prostate Imaging Reporting and Data System (PI-RADS) scores. This retrospective study included patients who underwent prostate biopsies. The extent of pTB was defined as the area within 10 mm of a TB site. A total of 162 eligible patients were enrolled. Prostate cancer (PCa) was diagnosed in 75.2% of patients undergoing TB, with a positivity rate of 50.7% for a PI-RADS score of 3, 95.8% for a PI-RADS score of 4, and 100% for a PI-RADS score of 5. Patients diagnosed with PCa according to both TB and pTB had significantly higher positivity rates for PI-RADS scores of 4 and 5 than for a PI-RADS score of 3 (p < 0.0001 and p = 0.0009, respectively). Additional pTB may be performed in patients with PI-RADS ≥ 4 regions of interest for assessing PCa malignancy. Full article

This cross-sectional study aimed to compare optical coherence tomography angiography (OCT-A) findings in patients with primary Raynaud’s phenomenon (PRP; n = 22), very early disease of systemic sclerosis (VEDOSS; n = 19), and systemic sclerosis (SSc; 25 patients with limited cutaneous SSc (lcSSc) and 13 patients with diffuse cutaneous SSc (dcSSc)). Whole, parafoveal, and perifoveal superficial capillary plexus (SCP) vessel densities (VDs), deep capillary plexus VDs, and whole, inside, and peripapillary VDs were significantly higher in the PRP group (p < 0.001). In the lcSSc group, the FAZ perimeter was significantly higher than that in the VEDOSS group (p = 0.017). Retinal nerve fiber layer VDs were significantly lower in the lcSSc group than in the PRP and VEDOSS groups (p < 0.001). The whole and peripapillary optic disc VDs of the VEDOSS group were significantly higher than in the lcSSc group (p < 0.001). Whole SCP VDs (94.74% sensitivity, 100.00% specificity) and parafoveal SCP VDs (89.47% sensitivity, 100.00% specificity) showed the best performance in distinguishing patients with SSc from those with PRP. OCT-A seems to have potential diagnostic value in differentiating patients with PRP from patients with SSc and VEDOSS, and there is potential value in assessing prognostic roles, since findings from OCT-A images could be early indicators of retinal vascular injury long before overt SSc symptoms develop. Full article