Svetlana Valjarevic

Fractal analysis has become a frequently used technique in sensory physiology for the evaluation of signal complexity, with potential applications ranging from the analysis of retinal vascular architecture to the quantification of changes in electroencephalographic recordings. Features such as fractal dimension and lacunarity may be able to detect discrete changes in both one-dimensional and two-dimensional signals associated with numerous physiological processes and disease development. However, their interpretation and translational potential are constrained by various limitations. In this concise review, we critically explore current applications of fractal analysis across major sensory domains and focus on the challenges that limit reproducibility and biological interpretation. We particularly focus on the biological ambiguity of fractal dimension and related measures, the non-equivalence of commonly used fractal metrics, acquisition-related variability, small datasets, and insufficient technical validation. Finally, we discuss issues related to the integration of fractal metrics into contemporary machine learning models, including challenges related to generalizability, overfitting, and poor explainability.

Background: Draining veins of the arteriovenous malformations (AVMs) can be the cause of hemorrhages, and the subject of a specific treatment. However, there are very scarce reports about their radiologic anatomy. Methods: Fifty-seven patients with cerebral AVMs were enrolled, almost with equal number of males and females. All of them underwent a neurologic examination, and then digital subtraction angiography, and computerized tomographic angiography. The obtained data were statistically analyzed. Results: The 57 patients had AVMs most often located in the frontal region (17.6%), and in the temporal and parietotemporal area (15.8% each). Supratentorial location existed in 88.4%, and infratentorial in 12.6%. Their draining veins ranged 1–17 in number (mean, 2.19). Singular veins were present in 22.8%, and double in 59.7%. Most of draining veins entered the superior sagittal sinus and other superficial vessels (63.2%), some terminated into deep veins or sinuses (12.3%), whilst both sites were present in 24.5%. Dilated draining veins existed in 88.9%, and venous aneurysms in 8.8%. An AVM hemorrhage was the initial sign in 49.2%. As for the AVMs treatment, endovascular embolization was performed (15.8%), surgical intervention (12.3%), and gamma knife irradiation (21.1%), whilst the remaining patients were treated conservatively, with a total mortality rate of 7.2%. Conclusion: Draining veins, which averaged 2.19 in number, terminated in various venous vessels. Most of them were dilated and tortuous, with rare aneurysms. A hemorrhage appeared in a half of the patients. Most of AVMs were treated by endovascular, neurosurgical, or radio-surgical interventions.

Background: Hyperacusis is a common, but often underrecognized comorbidity in patients with chronic subjective tinnitus. Reduced sound tolerance is associated with a greater tinnitus-related burden, impaired communication, reduced social participation, and poorer daily functioning. However, published data regarding its prevalence and clinical impact remain limited and inconsistent. Objectives: To determine the prevalence of hyperacusis in patients with chronic subjective tinnitus and to assess its association with tinnitus-related handicap, uncomfortable loudness levels, and degree of hearing loss and daily functioning. Methods: This cross-sectional study included 194 patients aged 21–85 years with chronic subjective tinnitus. Hyperacusis was assessed using a structured clinical interview that included questions on decreased sound tolerance and sound-induced ear pain and uncomfortable loudness level measurements (ULLs). Patients were categorized into two groups: tinnitus with hyperacusis (T + H; n = 32) and tinnitus without hyperacusis (T; n = 162). The impact of tinnitus on daily functioning was evaluated using a standardized and clinically validated questionnaire—the Tinnitus Handicap Inventory (THI). Data were analyzed using appropriate parametric and nonparametric statistical tests. Results: Hyperacusis was identified in 32 of 194 patients with chronic tinnitus (16.5%). Patients with tinnitus and hyperacusis (T + H) had significantly higher THI scores than those with isolated tinnitus, indicating greater tinnitus-related handicap (76.3 vs. 41.9; p < 0.001). Patients with hyperacusis also demonstrated significantly lower ULL values than those without hyperacusis (p < 0.001). Conclusions: Although the reported prevalence of hyperacusis among patients with tinnitus varies across the literature, our findings indicate that hyperacusis is a common comorbidity associated with significantly greater tinnitus-related handicap. Routine assessment of hyperacusis, including ULL measurements, should be incorporated into the clinical evaluation of patients with tinnitus to facilitate comprehensive diagnosis and optimize management. These findings highlight the importance of systematic assessment of hyperacusis in patients with tinnitus in routine audiological practice.

Auditory evoked potentials (AEPs) are electroencephalographic (EEG) responses to auditory stimuli and are frequently used to evaluate auditory processing and cognitive integrity. Interpretation of AEPs today predominantly relies on standard linear techniques such as time-domain averaging and frequency-domain spectral decomposition. These approaches may not always capture nonlinear, nonstationary, and scale-free characteristics of EEG signals; therefore, in contemporary neurophysiology research, there may be a need for the utilization of additional nonlinear frameworks. Fractal analysis may be a powerful tool for the quantification of subtle changes in EEG and AEP complexity, irregularity, and variability. This approach is often overlooked due to methodological and conceptual limitations but nevertheless holds significant potential in revealing alterations in geometrical and spatial complexity of AEPs under various physiological conditions. Here, we discuss potential applications and shortcomings of fractal AEP analysis, as well as its possible integration with supervised machine learning algorithms. We also focus on novel artificial intelligence-based concepts that could, in theory, utilize the power of fractal AEP and EEG analysis to improve the classification and prediction of neurophysiological processes and phenomena.

We present the case of a 70-year-old female patient who sought consultation with an otolaryngologist due to a mass protruding from the left nasal cavity. The patient reported that she had noticed the mass for the past two months, although she had experienced nasal breathing difficulties for over ten years. Upon examination, a large pink mass was observed protruding from the left nostril. Anterior rhinoscopy revealed complete obstruction of both the left and right nasal cavities by the tumor mass. Computed tomography showed that the mass entirely filled both nasal cavities and all paranasal sinuses. Surgical treatment was performed, involving endoscopic sinus surgery, which resulted in the complete removal of the mass. Histopathological analysis confirmed that the mass was a case of massive sinonasal polyposis. At the six-month follow-up, no signs of recurrence were observed. Although sinonasal polyposis is a relatively common condition in rhinologic surgery, such pronounced polyposis with prolapse of polyps through the nostril is a rare presentation that can initially mimic benign or malignant tumors of the nasal cavities.

This case report describes a 61-year-old female patient who presented to the emergency room of our hospital with severe dyspnea. The patient reported experiencing breathing difficulties for the past 2 weeks, with daily worsening, as well as swallowing problems persisting for about a year. She denied any comorbidities or history of neck-related injuries or surgeries. Physical examination revealed significant swelling on both sides of her neck. Computed tomography was performed to further investigate her condition. The neck CT showed a massive tumor that completely replaces both lobes of the thyroid gland and extends into the mediastinum. Urgent endotracheal intubation was carried out, followed by angiography to assess the tumor mass's vascularization. The patient was then tracheotomized, and a biopsy of the tumor mass was performed. Histopathological examination revealed insular carcinoma of the thyroid gland. The hospital stay was complicated by respiratory failure and paratracheal tumor bleeding, leading to a fatal outcome.

Introduction/Aim: We aimed to propose a novel and innovative concept of a support vector machine learning algorithm that employs fractal and run-length matrix indicators of nuclear structure to identify malignant squamous epithelial cells in laryngeal cancer. Material and Methods: Regions of interest in micrographs of laryngeal cancer and chronic laryngitis were analyzed using the box-counting fractal and run-length matrix textural techniques. For each nucleus, we quantified fractal dimension values, lacunarity, long-run emphasis, and short-run emphasis. These features were used as input data for training and testing the support vector machine model in the "Scikit-learn" library for Python. Results: The support vector machine model produced relatively good performance indicators. The classification accuracy of the model was 0.83, indicating its adequate ability to distinguish cancer cells from non-cancer cells in our sample. The F1 score (the harmonic mean of precision and recall) was 0.83, suggesting a relatively good balance between these two metrics. The value of the Matthews Correlation Coefficient for this model was 0.65, which indicated moderate agreement between the predicted and actual labels and balanced performance across the two classes. Conclusion: The proposed model provides a solid foundation for further developing artificial intelligence systems for signal analysis in cancer research. If the limitations of this concept are addressed, future research can focus on developing a more comprehensive machine-learning model for identifying laryngeal epithelial cancer cells.

Introduction. While mucosal melanoma of the head and neck remains an uncommon condition, its incidence has been on the rise in recent decades. Within the larynx, the supraglottis represents the most frequently affected subsite, followed by the glottis, with hoarseness being the predominant symptom. Given the tumor?s aggressive behavior and its challenging location, it is often overlooked until it progresses to an advanced stage, which significantly worsens the prognosis. Case report. A 45-year-old male patient with stridorous breathing presented to the emergency room. An indirect laryngoscopy revealed a transglottic mass occupying the left piriform recess and the entire laryngeal inlet, leading to an exceptionally narrowed airway. Urgent tracheostomy was performed. Contrast-enhanced computed tomography of the neck identified an ulceroproliferative mass in the larynx, spanning the supraglottic, glottic, and subglottic regions, causing airway narrowing and extending into the left pyriform sinus. Laryngoscopy was performed, and biopsy of the laryngeal lesion confirmed a diagnosis of malignant melanoma. Unfortunately, the patient refused further surgical and oncological treatment, as well as additional diagnostic procedures. Four months after the initial diagnosis, the patient was lost to follow-up. Conclusion. Laryngeal melanoma is an uncommon condition that can necessitate an emergency tracheostomy. Since melanoma can be mistaken for other laryngeal malignancies, immunohistochemical analysis plays a crucial role in making an accurate diagnosis. Early detection of the disease is vital.

Osteomyelitis is a bone inflammation caused by an infectious microorganism, which may lead to complete structure decay. Over time, along with the discovery and usage of powerful antibiotics, it became a rare occurrence in modern practice. In this paper, we will present a case of a patient with craniofacial osteomyelitis, which occurred as a complication of previous trauma and incomplete surgical treatment, due to lack of compliance. Chronic diseases in the non-cooperative patient led to the development of a severe clinical state. We believe that the existence of communication between defects on the anterior wall of the frontal sinus and corresponding subcutaneous and cutaneous tissue may have prevented further complications, in particular endocranial. Despite of a severe local finding, there was no dramatic increase in inflammatory parameters in laboratory analysis, as expected in such cases. A careful diagnostic procedure, identification of causative agent, adequately applied antibiotic therapy followed by surgical treatment debridement, improved the general condition of the patient as well as local finding. A severe form of osteomyelitis of the facial bones can be a complication after facial bone osteosynthesis. The absence of endocranial complications can be explained by drainage of purulent content through defects in the skin of the face. Quick and precise diagnostics, followed by treatment that includes a combination of surgery and conservative treatment, give the best results in such complex conditions.

Introduction: All cardiac conditions that cause the left or right hemilarynx palsy can be defined as Ortner's syndrome. Case Presentation: A 57-year-old man was urgently admitted to the Cardiology Department for laboured breathing and a clinical suspicion of heart failure. An emergency consultation by an otorhinolaryngologist was sought because he was complaining of a choking sensation in addition to hoarseness. Fiberoptic nasopharyngolaryngoscopy revealed restricted mobility of his left hemilarynx. His ECG tracing showed signs of chronic heart failure. Computed tomography of the neck and chest with intravenous contrast confirmed cardiomegaly with mediastinal structure displacement. Betablockers, diuretics, angiotensin receptor blockers, and allopurinol were prescribed, resulting in improved breathing. Conclusion: Hoarseness can be an initial sign of a potentially lethal illness. Early recognition and treatment of the underlying cardiovascular condition are crucial for the patient's recovery. It is essential to emphasize that a dyspneic patient requires a thorough cardiac assessment as well as an examination by an otorhinolaryngologist.