Search Results (117)

Background/Objectives: Discrepancies in diabetic retinopathy (DR) grading are well-documented, with retinal non-perfusion (RNP) quantification posing greater challenges. This study assessed intergrader agreement in DR evaluation, focusing on qualitative severity grading and quantitative RNP measurement. We aimed to improve agreement through structured consensus meetings. Methods: A retrospective analysis of 100 comparisons from 50 eyes (36 patients) was conducted. Two paired medical retina fellows graded ultra-widefield color fundus photographs (CFP) and fundus fluorescein angiography (FFA) images. CFP assessments included DR severity using the International Clinical Diabetic Retinopathy (ICDR) grading system, DR Severity Scale (DRSS), and predominantly peripheral lesions (PPL). FFA-based RNP was defined as capillary loss with grayscale matching the foveal avascular zone. Weekly adjudication by a senior specialist resolved discrepancies. Intergrader agreement was evaluated using Cohen’s kappa (qualitative DRSS) and intraclass correlation coefficients (ICC) (quantitative RNP). Bland–Altman analysis assessed bias and variability. Results: After eight consensus meetings, CFP grading agreement improved to excellent: kappa = 91% (ICDR DR severity), 89% (DRSS), and 89% (PPL). FFA-based PPL agreement reached 100%. For RNP, the non-perfusion index (NPI) showed moderate overall ICC (0.49), with regional ICCs ranging from 0.40 to 0.57 (highest in the nasal region, ICC = 0.57). Bland–Altman analysis revealed a mean NPI difference of 0.12 (limits: −0.11 to 0.35), indicating acceptable variability despite outliers. Conclusions: Structured consensus training achieved excellent intergrader agreement for DR severity and PPL grading, supporting the clinical reliability of ultra-widefield imaging. However, RNP measurement variability underscores the need for standardized protocols and automated tools to enhance reproducibility. This process is critical for developing robust AI-based screening systems. Full article

Background: Despite advances in artificial intelligence (AI) for Diabetic Retinopathy (DR) classification, traditional severity-based approaches often lack interpretability and fail to capture specific lesion-centered characteristics. To address these limitations, we constructed the National Medical Center (NMC) dataset, independently annotated by medical professionals with detailed labels of major DR lesions, including retinal hemorrhages, microaneurysms, and exudates. Methods: This study explores four critical research questions. First, we assess the analytical advantages of lesion-centered labeling compared to traditional severity-based labeling. Second, we investigate the potential complementarity between these labeling approaches through integration experiments. Third, we analyze how various model architectures and classification strategies perform under different labeling schemes. Finally, we evaluate decision-making differences between labeling methods using visualization techniques. We benchmarked the lesion-centered NMC dataset against the severity-based public Asia Pacific Tele-Ophthalmology Society (APTOS) dataset, conducting experiments with EfficientNet—a convolutional neural network architecture—and diverse classification strategies. Results: Our results demonstrate that binary classification effectively identifies severe non-proliferative Diabetic Retinopathy (Severe NPDR) exhibiting complex lesion patterns, while relationship-based learning enhances performance for underrepresented classes. Transfer learning from NMC to APTOS notably improved severity classification, achieving performance gains of 15.2% in mild cases and 66.3% in severe cases through feature fusion using Bidirectional Feature Pyramid Network (BiFPN) and Feature Pyramid Network (FPN). Visualization results confirmed that lesion-centered models focus more precisely on pathological features. Conclusions: Our findings highlight the benefits of integrating lesion-centered and severity-based information to enhance both accuracy and interpretability in DR classification. Future research directions include spatial lesion mapping and the development of clinically grounded learning methodologies. Full article

Diabetic retinopathy (DR) is a leading cause of vision impairment worldwide, requiring early detection for effective treatment. Deep learning models have been widely used for automated DR classification, with Convolutional Neural Networks (CNNs) being the most established approach. Recently, Vision Transformers (ViTs) have shown promise, but a direct comparison of their performance and interpretability remains limited. Additionally, hybrid models that combine CNN and transformer-based architectures have not been extensively studied. This work systematically evaluates CNNs (ResNet-50), ViTs (Vision Transformer and SwinV2-Tiny), and hybrid models (Convolutional Vision Transformer, LeViT-256, and CvT-13) on DR classification using publicly available retinal image datasets. The models are assessed based on classification accuracy and interpretability, applying Grad-CAM and Attention-Rollout to analyze decision-making patterns. Results indicate that hybrid models outperform both standalone CNNs and ViTs, achieving a better balance between local feature extraction and global context awareness. The best-performing model (CvT-13) achieved a Quadratic Weighted Kappa (QWK) score of 0.84 and an AUC of 0.93 on the test set. Interpretability analysis shows that CNNs focus on fine-grained lesion details, while ViTs exhibit broader but less localized attention. These findings provide valuable insights for optimizing deep learning models in medical imaging, supporting the development of clinically viable AI-driven DR screening systems. Full article

The main purpose was to evaluate the in vitro adhesion strength of direct and semi-direct composite resin restorations in dentin, when the same adhesive system is applied, using microtensile testing (μTBS) and to observe the most recurrent types of failure in the different groups. For this study, 16 intact human mandibular molars without microscopic evidence of lesions were randomly divided into two test groups, according to the restoration strategy: direct restoration (DR) and semi-direct restoration (SR). For both restorative strategies, the same adhesive system (Clearfil SE Bond 2, Kuraray, Tokyo, Japan) was applied to the dentin surface using a two-step self-etching approach with no prior conditioning of the dentin, and the same composite resin (Ceram. x Sepctra ST HV, Dentsply Sirona, Charlotte, NC, USA) was used as a restorative material. The indirect restoration was cemented using resin cement (Variolink Esthetic LC, Ivoclar Vivadent, Schaan, Liechtenstein) within the interior side of the restoration. Each specimen was sliced into sections measuring approximately 1 mm². The rods were then subjected to a microtensile bond strength test and the statistical analysis on the differences in μTBS between the groups were determined with the Mann–Whitney test. The surfaces were examined to determine the failure mode. The Chi-Square test was used to determine the association between the type of restoration and the failure mode. The DR group presented with a mean μTBS of 38.15 ± 10.75 MPa and a predominance of cohesive failures in the composite resin (69.5%). The SR group showed a mean μTBS of 25.45 ± 10.19 MPa and a predominance of adhesive failures (92.3%). There was not only a statistically significant difference in the adhesive strength of the DR and SR groups (p < 0.001), but also a statistically significant association between the type of restorative strategy and failure mode (p < 0.001). Even though Clearfil SE Bond 2 provided acceptable adhesion to the dentin, using the same two-step self-etch adhesive system, lower adhesive strength and more adhesive failures are expected in semi-direct restorations when compared to direct restorations. Full article

Biochemical recurrence (BCR) occurs in 20–50% of patients with localized prostate cancer (PC) after radical prostatectomy (RP). Conventional imaging often fails to detect early local or systemic recurrences at low PSA levels. Positron emission tomography/computed tomography (PET/CT) with 18F-DCFPyL PSMA offers improved sensitivity and specificity for detecting recurrent disease. This study evaluates the diagnostic capability of 18F-DCFPyL PET/CT in early BCR of PC following RP and its impact on therapeutic decision-making and clinical management. Methods: In a prospective study, 85 patients with BCR (PSA 0.2–2.0 ng/mL) and negative conventional imaging underwent 18F-DCFPyL PET/CT. Detection rates (DRs) were analyzed against clinical variables, including PSA levels and PSA doubling time (DT-PSA). Lesions were classified into local recurrence, lymph node involvement, bone, and visceral disease. Therapeutic decisions were adjusted based on PET/CT findings. Results: 18F-DCFPyL PET/CT identified lesions in 53% of patients, with DRs of 31.3%, 60%, and 77.8% for PSA levels <0.5, 0.5–1, and >1 ng/mL, respectively. DRs were significantly associated with shorter DT-PSAs (<6 months: 61.5%). The lesions detected included 22.2% local recurrences, 51.1% lymph node disease, 20% bone, and 6.7% visceral involvement. ROC analysis determined optimal PSA and DT-PSA cutoffs of 0.55 ng/mL and 9.2 months, respectively. Therapeutic strategies were modified in 84.4% of PET-positive cases. Conclusions: 18F-DCFPyL PET/CT demonstrates high sensitivity for detecting recurrent PC at low PSA levels, significantly impacting therapeutic decisions and optimizing clinical management. These findings support its integration into guidelines for managing early BCR of PC. Full article

The trigeminal nerve is the primary gateway through which the rabies virus enters the brain. Viral infection-related trigeminal neuritis is associated with certain clinical signs. This study investigated trigeminal ganglion histopathology in 92 rabid dogs. Trigeminal ganglionitis was classified into three pathological grades: mild, moderate, and severe. Immunostaining of selected sections was performed using antibodies against lymphocytes (CD3, CD20), stellate cells (glial fibrillary acidic protein, GFAP), macrophages (Iba-1, HLA-DR), ganglion cells (neurofilament, NF), and Schwann cells (S-100) to identify lesion cell types. In moderate and severe cases, double-immunofluorescence staining was performed to determine neuronophagia and Nageotte nodule cell types. Mild (13.0%) cases had minimal morphological changes in ganglion cells; moderate (56.5%) and severe (30.4%) cases showed infected ganglion cells and axons with degenerative necrosis, which were replaced by inflammatory cells. Immunohistochemically, viral antigens were detected in most ganglion cells in mild cases and were significantly reduced in severe cases. The number of CD3-, CD20-, GFAP-, and Iba-1-positive cells increased as the severity progressed, and neuronophagia and Nageotte nodules primarily comprised HLA-DR-positive cells. These findings suggest that the rabies virus reaches the trigeminal ganglion via ascending or descending routes and induces trigeminal neuropathological changes, contributing to neurological symptoms in rabid dogs. Full article

Accurate citrus disease identification is essential for targeted orchard pesticide application. Current models struggle with accuracy and efficiency due to diverse leaf lesion patterns and complex orchard environments. This study presents YOLOv8n-DE, an improved lightweight YOLOv8-based model for enhanced citrus disease detection. It introduces the DR module structure for effective feature enhancement and the Detect_Shared architecture for parameter efficiency. Evaluated on public and orchard-collected datasets, YOLOv8n-DE achieves 97.6% classification accuracy, 91.8% recall, and 97.3% mAP, with a 90.4% mAP for challenging diseases. Compared to the original YOLOv8, it reduces parameters by 48.17%, computational load by 59.26%, and model size by 41.94%, while significantly decreasing classification and regression errors, and false positives/negatives. YOLOv8n-DE offers outstanding performance and lightweight advantages for citrus disease detection, supporting precision agriculture development in orchards. Full article

Background/Objectives: Histopathological indicators, including desmoplastic reaction (DR) and tumour budding (TB), are significant prognostic indicators for metastatic liver lesions in patients with colorectal cancer (CRC). However, the relationship of DR and TB in primary CRC and metastatic lung lesions and their prognostic significance has not yet been examined. This study aimed to elucidate the association of DR and TB in primary CRC and metastatic lung lesions. Methods: Patients with pT3 or pT4 CRC with lung metastasis who underwent surgical resection of the primary CRC and synchronous or metachronous metastatic lung lesions were enrolled. DR was classified into immature (IM) and non-IM types, and TB was classified into TB1 (<4 buds), TB2 (5–9 buds) and TB3 (≥10 buds) in both the primary CRC and metastatic lung lesions. Results: Overall, 40 patients with CRC (males, 21; females, 19; median age, 70 years; right-side colon, 6; left-side colon, 9; rectum, 25; pT3, 31; pT4, 9) were evaluated. Six and thirty-four patients were classified as having IM and non-IM DR in the metastatic lung lesions, respectively. Thirty-one, seven, and two patients were classified as having TB1, TB2, and TB3, respectively. There was no significant correlation between primary and lung metastatic lesions for DR (κ = 0.08, p = 0.086), whereas TB demonstrated a moderate correlation (κ = 0.47, p = 0.015). The presence of IM DR and TB2/3 in metastatic lung lesions significantly correlated with poor overall survival (p = 0.0020 and 0.044, respectively). Conclusions: histological indicators of metastatic lung lesions in CRC may provide important prognostic information for better patient care. Full article

Background: Diabetic retinopathy (DR) is the leading cause of blindness among working-age adults. Early detection is crucial to reducing DR-related vision loss risk but is fraught with challenges. Manual detection is labor-intensive and often misses tiny DR lesions, necessitating automated detection. Objective: We aimed to develop and validate an annotation-free deep learning strategy for the automatic detection of exudates and bleeding spots on color fundus photography (CFP) images and ultrawide field (UWF) retinal images. Materials and Methods: Three cohorts were created: two CFP cohorts (Kaggle-CFP and E-Ophtha) and one UWF cohort. Kaggle-CFP was used for algorithm development, while E-Ophtha, with manually annotated DR-related lesions, served as the independent test set. For additional independent testing, 50 DR-positive cases from both the Kaggle-CFP and UWF cohorts were manually outlined for bleeding and exudate spots. The remaining cases were used for algorithm training. A multiscale contrast-based shape descriptor transformed DR-verified retinal images into contrast fields. High-contrast regions were identified, and local image patches from abnormal and normal areas were extracted to train a U-Net model. Model performance was evaluated using sensitivity and false positive rates based on manual annotations in the independent test sets. Results: Our trained model on the independent CFP cohort achieved high sensitivities for detecting and segmenting DR lesions: microaneurysms (91.5%, 9.04 false positives per image), hemorrhages (92.6%, 2.26 false positives per image), hard exudates (92.3%, 7.72 false positives per image), and soft exudates (90.7%, 0.18 false positives per image). For UWF images, the model’s performance varied by lesion size. Bleeding detection sensitivity increased with lesion size, from 41.9% (6.48 false positives per image) for the smallest spots to 93.4% (5.80 false positives per image) for the largest. Exudate detection showed high sensitivity across all sizes, ranging from 86.9% (24.94 false positives per image) to 96.2% (6.40 false positives per image), though false positive rates were higher for smaller lesions. Conclusions: Our experiments demonstrate the feasibility of training a deep learning neural network for detecting and segmenting DR-related lesions without relying on their manual annotations. Full article

Classical radiation biology as we understand it clearly identifies genomic DNA as the primary target of ionizing radiation. The evidence appears rock-solid: ionizing radiation typically induces DSBs with a yield of ~30 per cell per Gy, and unrepaired DSBs are a very cytotoxic lesion. We know very well the kinetics of induction and repair of different types of DNA damage in different organisms and cell lines. And yet, higher organisms differ in their radiation sensitivity—humans can be unpredictably radiosensitive during radiotherapy; this can be due to genetic defects (e.g., ataxia telangiectasia (AT), Fanconi anemia, Nijmegen breakage syndrome (NBS), and the xeroderma pigmentosum spectrum, among others) but most often is unexplained. Among other mammals, goats (Capra hircus) appear to be very radiosensitive (LD₅₀ = 2.4 Gy), while Mongolian gerbils (Meriones unguiculatus) are radioresistant and withstand quadruple that dose (LD₅₀ = 10 Gy). Primary radiation lethality in mammals is due most often to hematopoietic insufficiency, which is, in the words of Dr. Theodor Fliedner, one of the pioneers of radiation hematology, “a disturbance in cellular kinetics”. And yet, what makes one cell type, or one particular organism, more sensitive to ionizing radiation? The origins of radiosensitivity go above and beyond the empirical evidence and models of DNA damage and repair—as scientists, we must consider other phenomena: the radiation-induced bystander effect (RIBE), abscopal effects, and, of course, genomic instability and immunomodulation. It seems that radiosensitivity is not entirely determined by the mathematics of DNA damage and repair, and it is conceivable that radiation biology may benefit from an informed enquiry into physiology and organism-level signaling affecting radiation responses. The current article is a review of several key aspects of radiosensitivity beyond DNA damage induction and repair; it presents evidence supporting new potential venues of research for radiation biologists. Full article

Tuberculosis (TB), caused by Mycobacterium tuberculosis, remains a leading cause of global mortality. While TB detection can be performed through chest X-ray (CXR) analysis, numerous studies have leveraged AI to automate and enhance the diagnostic process. However, existing approaches often focus on partial or incomplete lesion detection, lacking comprehensive multi-class and multi-label solutions for the full range of TB-related anomalies. To address this, we present a hybrid AI model combining vision transformer (ViT) and convolutional neural network (CNN) architectures for efficient multi-class and multi-label classification of 14 TB-related anomalies. Using 133 CXR images from Dr. Cipto Mangunkusumo National Central General Hospital and 214 images from the NIH datasets, we tackled data imbalance with augmentation, class weighting, and focal loss. The model achieved an accuracy of 0.911, a loss of 0.285, and an AUC of 0.510. Given the complexity of handling not only multi-class but also multi-label data with imbalanced and limited samples, the AUC score reflects the challenging nature of the task rather than any shortcoming of the model itself. By classifying the most distinct TB-related labels in a single AI study, this research highlights the potential of AI to enhance both the accuracy and efficiency of detecting TB-related anomalies, offering valuable advancements in combating this global health burden. Full article

Bats are mammals with high biodiversity and wide geographical range. In Brazil, three haematophagous bat species are found. Desmodus rotundus is the most documented due to its role as a primary host of rabies virus in Latin America. Bats are known to harbor various emerging viruses causing severe human diseases. Beyond zoonotic viruses, these animals also harbor a diversity of non-zoonotic viruses. Papillomaviruses are circular double-stranded deoxyribonucleic acid (dsDNA) viruses that infect the epithelial and mucosal cells of many vertebrates, occasionally causing malignant lesions. High-throughput sequencing has enabled papillomaviruses discovery in different bat species. Here, 22 D. rotundus samples were collected through the rabies eradication program in Rio Grande do Sul. The DNA extracted from pooled intestines was amplified by the rolling-circle amplification (RCA) method and sequenced using the Illumina^® MiSeq platform (San Diego, CA, USA).Analysis revealed three contigs corresponding to the Papillomaviridae family, representing three novel viruses named DrPV-1, DrPV-2, and DrPV-3. Phylogenetic analysis suggests DrPV-1 may constitute a new species within the Dyophipapillomavirus genus, while DrPV-2 and DrPV-3 may represent different types within the same species from a novel genus. This is the first description of a papillomavirus in the D. rotundus species, contributing to the characterization of PVs in the Chiropteran order. Full article

Objective: To quantify microvascular lesions in a large real-world data (RWD) set, based on single central retinal fundus images of diabetic eyes from different origins, with the aim of validating its use as a precision tool for classifying diabetic retinopathy (DR) severity. Design: Retrospective meta-analysis across multiple fundus image datasets. Sample size: The study analyzed 2445 retinal fundus images from diabetic patients across four diverse RWD international datasets, including populations from Spain, India, China and the US. Intervention: The quantification of specific microvascular lesions: microaneurysms (MAs), hemorrhages (Hmas) and hard exudates (HEs) using advanced automated image analysis techniques on central retinal images to validate reliable metrics for DR severity assessment. The images were pre-classified in the DR severity levels as defined by the International Clinical Diabetic Retinopathy (ICDR) scale. Main Outcome Measures: The primary variables measured were the number of MAs, Hmas, red lesions (RLs) and HEs. These counts were related with DR severity levels using statistical methods to validate the relationship between lesion counts and disease severity. Results: The analysis revealed a robust and statistically significant increase (p < 0.001) in the number of microvascular lesions and the DR severity across all datasets. Tight data distributions were reported for MAs, Hmas and RLs, supporting the reliability of lesion quantification for accurately assessing DR severity. HEs also followed a similar pattern, but with a broader dispersion of data. Data used in this study are consistent with the definition of the DR severity levels established by the ICDR guidelines. Conclusions: The statistically significant increase in the number of microvascular lesions across DR severity validate the use of lesion quantification in a single central retinal field as a key biomarker for disease classification and assessment. This quantification method demonstrates an improvement over traditional assessment scales, providing a quantitative microvascular metric that enhances the precision of disease classification and patient monitoring. The inclusion of a numerical component allows for the detection of subtle variations within the same severity level, offering a deeper understanding of disease progression. The consistency of results across diverse datasets not only confirms the method’s reliability but also its applicability in a global healthcare setting. Full article

Pigmented skin lesions have increased considerably worldwide in the last years, with melanoma being responsible for 75% of deaths and low survival rates. The development and refining of more efficient non-invasive optical techniques such as diffuse reflectance spectroscopy (DRS) is crucial for the diagnosis of melanoma skin cancer. The development of novel diagnostic approaches requires a sufficient number of test samples. Hence, the similarities between banana brown spots (BBSs) and human skin pigmented lesions (HSPLs) could be exploited by employing the former as an optical phantom for validating these techniques. This work analyses the potential similarity of BBSs to HSPLs of volunteers with different skin phototypes by means of several characteristics, such as symmetry, color RGB tonality, and principal component analysis (PCA) of spectra. The findings demonstrate a notable resemblance between the attributes concerning spectrum, area, and color of HSPLs and BBSs at specific ripening stages. Furthermore, the spectral similarity is increased when a fiber-optic probe with a shorter distance (240 µm) between the source fiber and the detector fiber is utilized, in comparison to a probe with a greater distance (2500 µm) for this parameter. A Monte Carlo simulation of sampling volume was used to clarify spectral similarities. Full article

Background: Multiple sclerosis (MS) is characterized by white matter demyelinating plaques, which can be classified as active, chronic active, or chronic inactive based on the extent of demyelination, cellularity, and inflammation. Microglia and macrophages play a central role in these processes. This study aimed to investigate the morphological characteristics of HLA-DR-immunopositive cells in these plaques to improve our understanding of the roles of these cells in MS plaques. Methods: This study is a retrospective post-mortem histopathological study. We analyzed 90 plaques from 6 MS cases. Of the plaques studied, 77 were grouped into three categories: 28 active, 34 chronic active, and 15 chronic inactive. Additionally, five vacuolated white matter lesions, two axonal degeneration lesions, and six lesions with mixed histological features were included. Six control cases were also examined to assess HLA-DR-immunopositive cell expression across various age groups. The cells were classified based on their morphology into two types: round cells without processes (macrophages) and cells with varying processes and shapes (ramified microglia). Results: Both macrophages and ramified microglia were present in all lesion types, with a focus on identifying the predominant cell type. Of the 28 active plaques, macrophages were the primary cell type in 25 plaques, while ramified microglia predominated in 3. In the center of 49 chronic plaques, scattered ramified microglia were observed in 46, with three plaques showing a predominance of macrophages. Among the 34 chronic active lesions, ramified microglia were the main cell type in the periphery of 32 plaques, with the remaining two predominantly exhibiting macrophages. Conclusions: The predominance of macrophages in active lesions and the presence of scattered ramified microglia in the center of chronic plaques are consistent with the phagocytic role of macrophages. Meanwhile, the prevalence of ramified microglia at the periphery of chronic active lesions suggests a potential protective function in maintaining lesion stability. Full article