Search Results (2,694)

Background/Objectives: Parotid incidentalomas are increasingly detected during brain MRI and PET-CT, particularly in patients with serious diseases such as cancer. This study aimed to evaluate the clinical significance of incidentally identified parotid lesions. Methods: We retrospectively reviewed the records of 44,952 patients (≥19 years) who underwent brain MRI and 10,957 who underwent PET-CT between January 2014 and December 2023. The incidence, imaging findings, and pathological results of parotid incidentalomas were analyzed. Results: Among 44,952 brain MRIs, 100 incidental parotid lesions (0.22%) were detected, compared with 92 lesions (0.84%) among 10,957 PET-CT scans. The mean patient age was slightly higher in the PET-CT group. Of the MRI-detected lesions, 35 patients underwent further evaluation and 14 underwent surgery, with final pathology confirming only benign tumors, including pleomorphic adenomas, Warthin tumors, and basal cell adenomas. In contrast, among 23 PET-CT patients who underwent additional evaluation, 7 had surgery, and final pathology revealed both benign and malignant tumors. Malignant cases included mucoepidermoid carcinoma, metastatic Merkel cell carcinoma, metastatic sebaceous carcinoma, and adenoid cystic carcinoma. Notably, two patients with initially benign cytology and negative PET-CT findings were later confirmed to have malignancies after surgery, Primary sites of metastatic disease included the thyroid, cervix, head and neck, and skin. Conclusions: Most parotid incidentalomas detected on brain MRI are benign and may be managed conservatively. However, incidentalomas identified on PET-CT require thorough evaluation, as they may indicate metastatic disease or a second primary malignancy, particularly in patients with head and neck or skin cancers. Full article

Background/Objectives: Ground-glass opacity (GGO) refers to areas of increased lung opacity on computed tomography (CT) scans. Distinguishing malignant from benign lesions using CT scans remains significantly challenging. This study aims to compare the performances of a linear multivariate statistical regression and an AI deep learning method in their abilities to predict GGO malignancy, given a set of pixel features extracted from CT scans. Methods: This retrospective study investigated patients from the Carmel Medical Center with findings of GGO nodules in their lung CT scans. Forty-seven consecutive patients were found to have either pure or part-solid GGO lesions, as defined by two independent radiologists. After manually segmenting the GGOs in the CT scans, pixel features were extracted using the MaZda software package, which analyzes six different image texture features. These textural variables were then compiled as input for the multivariate statistical regression. Additionally, an AI deep learning method, developed by our group and hosted on the cloud, was applied to the CT images containing the GGOs. Results: Among the 47 patients, 32 were diagnosed by pathology with malignant lesions and 15 with benign findings. Using the multivariate statistical regression, we identified 19 variables with statistically significant or near-significant differences through univariate analysis. In subsequent multivariate analyses, two independent variables that could distinguish between benign and malignant GGO lesions were identified: S(4,4)AngScMom (p = 0.012) and WavEnLH_s-2 (p = 0.008). The regression formula based on these two variables yielded a sensitivity of 91% and a specificity of 67% AUC: 0.8 (95% CI: [0.65, 0.94]). The AI deep learning model demonstrated a sensitivity of 100% and a specificity of 80% AUC: 0.96 (95% CI: [0.86, 1.00]). Conclusions: This proof-of-concept study demonstrates the superior performance of the AI deep learning model compared to the multivariate statistical regression, particularly in terms of sensitivity and specificity. However, given the small sample size, these results could potentially change with larger patient cohorts. Full article

Background and Objectives: Stratifying thyroid nodules according to malignancy risk is a crucial step in early diagnosis and patient care. Recently, deep learning techniques have emerged as powerful tools for medical diagnostics, particularly with convolutional neural networks (CNNs) applied to medical image classification. This study aimed to develop a new hybrid CNN model for classifying thyroid nodules using the TN5000 ultrasound image dataset. Materials and Methods: The TN5000 dataset includes 5000 ultrasound images, with 3572 malignant and 1428 benign nodules. To address the issue of class imbalance, the researchers applied an R-based anomaly data augmentation method and a GAN-based technique (G-RAN) to generate synthetic benign images, resulting in a balanced dataset for training. The model architecture was built on a pre-trained EfficientNet-B3 backbone, further enhanced with squeeze-and-excitation (SE) blocks and residual refinement modules to improve feature extraction. The task was to classify malignant nodules (labeled 1) and benign nodules (labeled 0). Results: The proposed hybrid CNN achieved strong performance, with an accuracy of 89.73%, sensitivity of 90.01%, precision of 88.23%, and an F1-score of 88.85%. The total training time was 42 min. Conclusions: The findings demonstrate that the proposed hybrid CNN model is a promising tool for thyroid nodule classification on ultrasound images. Its high diagnostic accuracy suggests that it could serve as a reliable decision-support system for clinicians, improving consistency in diagnosis and reducing human error. Future work will focus on clinical validation, explainability of the model’s decision-making process, and strategies for integration into routine hospital workflows. Full article

Radiomics entails a data-driven approach to imaging with a wide array of potential uses in characterizing soft tissue sarcomas, enabling extraction of quantitative features from routine clinical CT and MRI examinations. These features—encompassing descriptors of size, shape, and internal heterogeneity—can improve diagnostic accuracy, tumor grading, and treatment response assessment. Radiomics has shown promise in distinguishing benign from malignant lesions, subtyping sarcomas, and predicting metastatic potential. In particular, models integrating radiomic data with clinical variables have demonstrated performance comparable to expert radiologists in challenging diagnostic scenarios. Machine learning enhances radiomics by automating feature selection and improving predictive modeling. Despite its potential, challenges remain in standardizing imaging protocols, ensuring reproducibility, and integrating radiomics into clinical workflows. Multi-institutional collaboration is essential for broader model validation and clinical integration. By leveraging specific radiomics features as novel quantitative imaging biomarkers, radiomics can drive precision oncology in sarcoma, supporting tailored therapies and improving prognostic accuracy. Full article

Background and Objective: Gastric cancer (GC) is a serious public health problem in southeastern Mexico. Some cases go undiagnosed or are diagnosed at advanced stages of the tumors. Borrmann classification is the method used by endoscopists to classify gastric lesions and identify tumor stage. This study aimed to characterize GC patients treated at a specialized hospital in the Yucatan Peninsula, Mexico, according to the Borrmann endoscopic classification, with a focus on clinicopathological characteristics and survival differences. Materials and Methods: A retrospective cohort study was conducted among patients aged 18 years or older who underwent an endoscopic procedure at the hospital to confirm a diagnosis of GC between January 2019 and December 2024. Clinical data were collected, including medical history, blood type, non-communicable diseases, tumor type, tumor location (primary or metastatic), and details of medical and/or surgical treatment. Survival curves were generated for all patients and stratified by the Borrmann classification. Results: A total of 209 cases of GC were included, with 115 men with a mean age of 59.3 years and 94 women with a mean age of 52.2 years. Acid peptic disease (70.3%), followed by wasting syndrome (66.9%), was the most common medical condition in patients with GC. Blood type O with a positive Rh factor was the most frequent (66.5%). According to the Borrmann classification, localized tumors (p = 0.001) were observed at lower Borrmann levels, whereas Helicobacter pylori (p = 0.040) was more frequent at higher levels. The overall survival time was 18 months for all patients; specifically, 18 months at higher Borrmann levels and 20 months at lower levels. Conclusions: GC is a highly prevalent malignancy in southeastern Mexico. The Borrmann classification remains a valuable and practical tool for evaluating GC. The association between Borrmann endoscopic classification and the clinicopathological and survival characteristics may contribute to accurate diagnosis assessment and improved prognostic stratification in future GC cases. Full article

Background: Persistent infection with high-risk human papillomavirus (HR-HPV) is the primary cause of cervical intraepithelial neoplasia (CIN) and cervical cancer. While HPV testing has become central to screening programs and the frequency of detecting multiple HPV genotypes has subsequently risen, the clinical relevance of multiple-type (MT) HPV infections remains uncertain. This study aimed to investigate the correlation between HPV infection type and the severity of cervical cytological and histological abnormalities. Methods: This retrospective study analyzed 340 women with dysplasia and 82 with histologically confirmed cervical cancer treated at the University Hospital Cologne between 2016 and 2019. HPV genotyping was performed using a DNA microarray detecting 41 HPV genotypes. Associations between infection patterns and cytological and histological findings were evaluated. Results: Multiple infections accounted for 42% of HPV-positive cases (119 among 284), showing a bimodal age distribution with peaks in patients ≤19 and ≥60 years. HPV16 and HPV18 were most frequently detected in worse than CIN3 lesions (CIN3+), mainly as single-type (ST) infections. Women with ST infections had a significantly higher risk of CIN3+ compared to those with MT infections (p = 0.004). HPV16 ST was significantly associated with CIN3+ compared to other HR-HPV ST (p = 0.046), whereas MT including HPV16 did not increase CIN3+ risk (p = 0.124). Co-infections involving alpha-9 clade types were associated with higher CIN3+ risk, while alpha-7 co-infections did not show an additive effect. Furthermore, coinfections involving two different alpha-9 or -7 were observed infrequently. Conclusions: Single HR-HPV infections are more strongly associated with high-grade cervical lesions than multiple infections, especially when HPV 16 is involved. These findings underscore the dominant oncogenic potential of HPV16 and suggest that intergenotypic interactions in MT infections may mitigate malignant progression. Full article

Sessile serrated lesions (SSLs) are well-known precursors of colorectal cancer in the general population, but their role in inflammatory bowel disease (IBD) is less clear. This narrative review summarizes what is known about the prevalence, molecular features, endoscopic detection, malignant potential, and management of SSLs in patients with IBD, highlighting where evidence supports action nowadays and where prospective studies are urgently needed. IBD-associated colorectal cancer has long been considered a consequence of the inflammation–dysplasia–carcinoma sequence, distinct from the conventional adenoma–carcinoma pathway. Increasing evidence, however, suggests that the serrated pathway, typically characterized by SSLs and traditional serrated adenomas (TSAs), may also contribute to IBD-related oncogenesis. This review synthesizes histopathological, molecular, endoscopic, and clinical data on SSLs in patients with IBD, with contextual reference to TSAs, sessile serrated lesions with dysplasia, and serrated epithelial change only when relevant to their interpretation or risk stratification. SSLs are now more frequently identified in IBD surveillance, especially in ulcerative colitis and the proximal colon, although prevalence estimates remain heterogeneous due to evolving definitions and significant interobserver variability. Molecular studies indicate that IBD-associated serrated lesions often harbor BRAF mutations but display a lower CpG island methylator phenotype than their sporadic counterparts, suggesting an inflammation-modified biology. While most hyperplastic polyps and non-dysplastic SSLs appear to pose limited neoplastic risk, dysplastic serrated lesions carry a markedly higher likelihood of synchronous or metachronous advanced neoplasia. Advances in high-definition endoscopy and chromoendoscopy improve the detection of these subtle, mucus-capped, flat lesions, while endoscopic resection is nowadays feasible in expert hands. Future priorities should include prospective multicenter cohorts integrating molecular profiling to refine surveillance strategies. Full article

Background/Objectives: Cervical cancer is one of the most frequent malignancies among women in Kazakhstan, where human papillomavirus (HPV) vaccination was initiated in 2024. Despite the implementation of vaccination and cytology-based screening programs, diagnostic limitations remain, and local evidence linking HPV infection to clinical outcomes is scarce. This study aimed to evaluate the correlation between HPV status, cervical cytology results, colposcopic impression, and biopsy results in a non-vaccinated female population. Methods: A cross-sectional study was conducted at the University Medical Center, Astana, between November 2024 and March 2025. A total of 396 women of reproductive age were enrolled. Cervical samples underwent liquid-based cytology and high-risk HPV testing with the RealBest assay. Colposcopy was performed following abnormal cervical cytology results, and colposcopy-guided biopsies were obtained where indicated. Sociodemographic characteristics were assessed, and associations between HPV genotype and clinical outcomes were analyzed using descriptive and inferential statistics. Results: HPV infection was detected in 140 women (35.4%). HPV-16 was the most common genotype (11.4%), followed by HPV-52 (6.6%) and HPV-33 (5.3%). Among 198 women evaluated by colposcopy, abnormal findings were observed in 72.2%, with HPV-16 showing a significant association with higher-grade abnormalities (p < 0.001). Biopsies were available for 40 participants: 12 had CIN I, 12 had CIN II, 10 had CIN III, and 4 had carcinoma in situ. HPV-16 was the only genotype significantly linked to CIN II/III lesions. Conclusions: HPV-16 was strongly associated with abnormal colposcopic findings and high-grade histology, underscoring its oncogenic importance. The prevalence of HPV-52 and HPV-33 further supports the need for HPV nonavalent vaccination. These findings highlight the importance of HPV-based screening, genotype-specific triage, and expanded vaccination to reduce cervical cancer incidence in Kazakhstan. Full article

Background: Artificial intelligence (AI) has shown significant promise in augmenting diagnostic capabilities across medical specialties. Recent advancements in generative AI allow for synthesis and interpretation of complex clinical data including imaging and patient history to assess disease risk. Objective: To evaluate the diagnostic performance of a dermatology-trained multimodal large language model (DermFlow, Delaware, USA) in assessing malignancy risk of pigmented skin lesions. Methods: This retrospective study utilized data from 59 patients with 68 biopsy-proven pigmented skin lesions seen at Indiana University clinics from February 2023 to May 2025. De-identified patient histories and clinical images were input into DermFlow, and clinical images only were input into Claude Sonnet 4 (Claude) to generate differential diagnoses. Clinician pre-operative diagnoses were extracted from the clinical note. Assessments were compared to histopathologic diagnoses (gold standard). Results: Among 68 clinically concerning pigmented lesions, DermFlow achieved 47.1% top diagnosis accuracy and 92.6% any-diagnosis accuracy, with F1 = 0.948, sensitivity 93.9%, and specificity 89.5% (balanced accuracy 91.7%). Claude had 8.8% top diagnosis and 73.5% any-diagnosis accuracy, F1 = 0.816, sensitivity 81.6%, specificity 52.6% (balanced accuracy 67.1%). Clinicians achieved 38.2% top diagnosis and 72.1% any-diagnosis accuracy, F1 = 0.776, sensitivity 67.3%, specificity 84.2% (balanced accuracy 75.8%). DermFlow recommended biopsy in 95.6% of cases vs. 82.4% for Claude, with multiple pairwise differences favoring DermFlow (p < 0.05). Conclusions: DermFlow demonstrated comparable or superior diagnostic performance to clinicians and superior performance to Claude in evaluating pigmented skin lesions. Although additional data must be gathered to further validate the model in real clinical settings, these initial findings suggest potential utility for dermatology-trained AI models in clinical practice, particularly in settings with limited dermatologist availability. Full article

Background: Oral lichen planus (OLP) is a chronic mucosal disease associated with a risk of malignant transformation. Although topical corticosteroids are the standard therapy, prolonged administration may result in local and systemic complications. Photodynamic therapy (PDT) with 5-aminolevulinic acid (ALA) has been proposed as a less invasive and safer alternative. Methods: In this prospective study, 44 patients with histologically verified OLP underwent a protocol consisting of ten consecutive weekly PDT sessions, each comprising a single irradiation. A 5% ALA formulation was topically applied, followed by illumination with a 630 nm red light device. Clinical outcomes were evaluated at baseline, immediately after therapy, and at 12- and 48-month follow-ups. Changes in lesion surface, REU index, and pain intensity on a visual analog scale (VAS) were analyzed. Results: Significant improvements were noted, with progressive and sustained decreases in lesion extent, REU scores, and VAS values throughout the 4-year observation period. The therapeutic response was consistent across different mucosal sites (keratinized and non-keratinized). No treatment-related adverse reactions were recorded. Conclusions: Long-term follow-up indicates that ALA-mediated PDT is a safe and effective management option for both reticular and erosive variants of OLP. Its durable clinical benefits and favorable safety profile support its role as an alternative to corticosteroid therapy. Full article

Brown tumors (BTs) are rare osteolytic lesions that typically occur in association with primary or secondary hyperparathyroidism (PHP and SHP). Excessive secretion of parathyroid hormone induces increased bone resorption, resulting in lesions characterized by fibrosis, vascularization, and hemosiderin deposition. The most common sites include the jaws, ribs, pelvis, and long bones. Clinical manifestations may involve pain, swelling, or pathological fractures. We present the case of a mandibular BT in a 48-year-old female with chronic renal failure and secondary hyperparathyroidism. The patient exhibited progressive mandibular swelling with radiological features resembling an aggressive odontogenic or malignant lesion. Laboratory analysis confirmed markedly elevated parathyroid hormone levels, while scintigraphy demonstrated increased focal uptake in the mandible and ribs. Histopathological evaluation revealed multinucleated giant cells within a fibrous stroma, consistent with BT. Despite initiation of systemic endocrine therapy, the lesion continued to enlarge, necessitating complete surgical excision of the mandibular mass. This case underscores the diagnostic dilemmas of mandibular BT, which may closely mimic aggressive jaw pathologies. Importantly, while many BTs regress after systemic management of hyperparathyroidism, this case illustrates that surgical excision may be unavoidable in patients with unstable systemic status or progressive local disease. Comprehensive clinical, radiological, laboratory, and histopathological evaluation remains essential to ensure timely diagnosis and appropriate treatment. Full article

Oral cancer represents a life-threatening malignancy with profound implications for patient survival and quality of life. Oral squamous cell carcinoma (OSCC), the predominant histological variant of oral cancer, constitutes a substantial healthcare challenge wherein early detection remains critical for therapeutic efficacy and enhanced survival outcomes. Recent advances in deep learning methodologies have demonstrated superior performance in medical imaging applications. However, existing investigations have predominantly employed unimodal image data for oral lesion classification, thereby neglecting the potential advantages of multimodal data integration. To address this limitation, we propose a comprehensive multimodal pipeline for the classification of OSCC versus leukoplakia through the integration of histopathological imagery with tabular data encompassing anatomical characteristics and behavioral risk factors. Our methodology achieved a precision of 0.97, F1-score of 0.97, recall of 0.98, and accuracy of 0.97. These findings demonstrate the enhanced diagnostic precision and efficacy afforded by multimodal approaches in oral cancer classification, suggesting a promising avenue for improved diagnostic accuracy and treatment planning optimization. Full article

Cardiovascular diseases in dogs have diverse causes and may progress rapidly to life-threatening complications. This review outlines the relevant pathological conditions involving the cardiovascular system in dogs, especially the myocardium, including myocarditis caused by canine parvovirus (CPV-2), heartworm disease (Dirofilaria immitis), hemangiosarcoma, and polyarteritis nodosa (PAN). CPV-2 affects the myocardium of puppies during the early weeks of life, leading to necrosis, fibrosis, and congestive heart failure. Heartworm disease is caused by adult D. immitis residing mainly in the pulmonary arteries, inducing pulmonary hypertension, right ventricular overload, and vascular damage, with the severity being related to the worm burden and duration of infestation. Hemangiosarcoma is a malignant vascular tumor, most frequently originating in the spleen or right atrium, often diagnosed at an advanced stage, with widespread metastases. Polyarteritis nodosa in dogs is a necrotizing, systemic vasculitis of medium-sized arteries that may affect the coronary arteries of the heart. Its pathogenesis is still unclear, though an immune-mediated mechanism is suspected. By presenting these lesions, the review underscores the many factors that can trigger cardiovascular diseases in dogs, as well as the clinical significance and the need for further research into their pathogenesis and treatment. Full article

Background/Objectives: Autofluorescence (AF) is a widely used adjunctive tool in the detection of oral potentially malignant disorders (OPMDs) and malignant lesions, but its performance can be influenced by clinicians’ experiences. This study aimed to examine how AF influences diagnostic decision-making and performances of a novice clinician compared with those of an experienced examiner. Methods: A total of 80 patients with oral lesions participated in this cross-sectional study. Each underwent a standard oral examination (OE) followed by an assessment with the VELscope^® System Vx (LED Medical Diagnostics Inc., Burnaby, BC, Canada), independently conducted by an expert clinician (E) and a postgraduate dentist (PD), both blinded to each other’s results. Biopsy and histopathological analysis provided the reference diagnosis. After every examination, lesions were categorized as either “Risk of Malignancy” (RM) or “No Risk of Malignancy” (NRM). Results: Based on OE, PD identified 39 RM lesions, while E 29. AF with VELscope^® identified an additional 12 RM lesions for the PD and 7 for the E that were not suspected on OE alone. Combining OE with VELscope^® improved sensitivity (PD: 90.9%; E: 95.4%) and negative predictive value (PD: 91.7%; E: 97.6%), while decreasing specificity (PD: 37.9%; E: 70.7%) and positive predictive value (PD: 35.7%; E: 55.3%) compared with OE alone. Conclusions: AF increases diagnostic sensitivity, particularly for less experienced clinicians, while offering moderate advantages for experts. Nevertheless, the corresponding decline in specificity emphasizes the need for cautious interpretation. AF should be incorporated as a complementary tool within structured diagnostic pathways, accompanied by adequate training, and cannot replace histopathological confirmation or clinical expertise. Full article

Background: Desmoid tumors (DTs) are rare, locally aggressive soft-tissue neoplasms that often affect women of reproductive age. Pregnancy and prior abdominal surgery or trauma have been associated with tumor development and growth, while imaging frequently overlaps with abdominal-wall endometriosis. We present the case of a 39-year-old woman with an abdominal-wall DT and provide a narrative review of the literature focused on pregnancy/postpartum patterns, differential diagnosis, and management. Methods: A narrative review of PubMed/MEDLINE and Web of Science (January 1982–December 2024) was conducted. We included English-language case reports/series, narrative/descriptive reviews, and consensus statements relevant to DTs in pregnancy or reproductive-age women, emphasizing abdominal-wall disease. Results: The patient’s right abdominal-wall mass enlarged during pregnancy and further post-partum imaging repeatedly suggested endometriosis. En bloc resection revealed desmoid-type fibromatosis composed of bland spindle cells in a collagenous stroma, with nuclear β-catenin and lymphoid enhancer–binding factor 1 (LEF1) positivity on immunohistochemistry. Magnetic resonance imaging (MRI) at 12 months showed no recurrence. Across included studies, pregnancy and post-partum enlargement is common, abdominal-wall DTs frequently mimic scar endometriosis, and pre-operative ultrasound has limited specificity. Current practice supports watch-and-wait for stable, asymptomatic lesions and function-preserving surgery for symptomatic progression, while systemic options (anti-estrogens, low-dose chemotherapy, and tyrosine kinase inhibitors) are reserved for progressive or unresectable disease. Recurrence risk relates to age, size, site, and β-catenin status; future pregnancy is not contraindicated. Conclusions: Abdominal-wall DTs, although rare, should be considered in the differential diagnosis of reproductive-age women presenting with abdominal-wall masses, particularly during or after pregnancy. Full article