Application of fractal and textural analysis in medical physiology, pathophysiology and pathology

Pantić, Igor; Paunovic, Jovana; Radojević-Škodrić, Sanja

doi:10.5937/medi55-40351

Cited by 3 publications

(2 citation statements)

References 47 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ovo je potencijalno od posebnog značaja u onkologiji, gde postoji moguća primena ove metode u razlikovanju malignih i benignih promena, što može biti od velike pomoći profesionalnom patologu i drugim lekarima prilikom donošenja definitivne dijagnoze. Studije su već ukazale da su GLCM parametri tkiva, ćelija i ćelijskih jedara potencijalno značajni indikatori programirane ćelijske smrti, starenja i drugih fizioloških i patoloških promena (37). Analiza parametara tkiva GLCM metodom dokazala je statistički značajnu razliku između GLCM parametara zdravog tkiva i tkiva planocelularnih karcinoma glave i vrata.…”

Section: Dijagnostika Planocelularnog Karcinoma Larinksaunclassified

See 1 more Smart Citation

Application of contemporary computer methods in laryngeal cancer diagnosis and treatment

Valjarević,

Jovanović,

Pantić

2023

Medicinski podmladak

Self Cite

View full text Add to dashboard Cite

Early detection of disease and accurate assessment of its extent are of paramount importance for the course of treatment and prognosis of larynx cancer. Machine learning and artificial intelligence tools have the potential to accelerate and improve diagnostic procedures in medicine, as well as to predict disease outcomes and response to specific therapies. Computer algorithms can analyze two-dimensional images obtained during procedures such as laryngeal spectroscopy and endoscopy. Radiological images can be evaluated using appropriate algorithms to determine whether the laryngeal tissue is benign or malignantly altered. In recent years, machine learning tools have been developed to determine the precise radiation doses, predict tumor radiosensitivity, as well as the possibility and severity of complications based on radiological image analysis. In the field of pathology, significant progress has been made by creating digital records of histopathological preparations, which can be further analyzed. This allows changes in intercellular interaction and tissue architecture that cannot be detected by conventional microscopic methods to be identified. With innovative computer techniques, it is possible to quantify tissue and cell structure parameters, which are calculated based on mathematical formulas and used to measure structural homogeneity and uniformity in both normal and pathologically altered tissue. Future multidisciplinary research aimed at developing new and innovative biosensors for the detection of discrete morphological changes characteristic of squamous cell carcinoma of the larynx will make a significant contribution to the advancement of diagnosis and treatment in the field of otolaryngology. In the future, the use of artificial intelligence and machine learning could enable the fusion of algorithms that combine data obtained from radiological, endoscopic, and histopathological findings, which could significantly increase the accuracy and precision of diagnosis, facilitate the process of deciding on therapeutic options, and improve the success rate of larynx cancer treatment.

show abstract

Section: Dijagnostika Planocelularnog Karcinoma Larinksaunclassified

“…MedPodml 2023, 74(5):14-20 (39). Važno je napomenuti i da koncept mašinskog učenja podrazumeva unose izuzetno velikog broja podataka radi treniranja algoritma, što studije čini teško izvodljivim (37).…”

Section: Dijagnostika Planocelularnog Karcinoma Larinksaunclassified

Application of contemporary computer methods in laryngeal cancer diagnosis and treatment

Valjarević,

Jovanović,

Pantić

2023

Medicinski podmladak

Self Cite

View full text Add to dashboard Cite

show abstract

The effects of 20-hydroxyecdysone on nuclear shape, heterochromatin quantity and gray-level co-occurrence matrix texture analysis of adrenal zona fasciculata cells in an obese gerbil (Gerbillus tarabuli) model for metabolic syndrome: a correlational study

Bellahreche,

Sihali-Beloui,

Semiane

et al. 2023

Histochem Cell Biol

View full text Add to dashboard Cite

Multifractal characterization of grayscale histopathological images: Unveiling patterns linked to metastases in breast cancer

Nedeljković,

Milošević,

Radulović

et al. 2024

Medicinska istraživanja

View full text Add to dashboard Cite

Introduction: Breast cancer, a pervasive global malignancy, demands precise prognostication of the risk of metastases for personalized therapeutic strategies and enhanced survival rates. In pursuit of refined diagnostic methodologies, this study employs multifractal analysis on grayscale histopathological images, revealing distinctive patterns associated with the occurrence of metastases. Aim: Analyzing the multifractal spectra of grayscale images for groups with and without metastases to assess the utility of this analytical approach in enhancing the diagnostic process. Materials and methods: The study included 102 female patients treated at the Institute for Oncology and Radiology of Serbia in the same year (1993). Histopathological samples were immunostained with a pan-cytokeratin antibody and digitized with a high-resolution scanner, from which a specialist chose representative parts, thus leading to a total number of 519 images (418 in no-metastases group and 101 in metastases group). Images were subjected to multifractal analysis, assessing the generalized dimension, Hölder exponent, and singularity spectra. Results: Statistical comparisons between groups with and without metastases unveil significant differences in the negative domains of both generalized dimension and Hölder exponent spectra, highlighting the influence of fine structures in tissue morphology that are linked to metastatic risk. Conclusion: Multifractal analysis applied to images of histopathological samples from breast tumors demonstrates the ability to differentiate between groups of patients with and without metastases. While caution is warranted regarding image resolution limitations and immunostaining sensitivity, this method is a non-training-dependent approach with potential diagnostic significance and possible synergies with advanced neural network approaches.

show abstract

Application of fractal and textural analysis in medical physiology, pathophysiology and pathology

Cited by 3 publications

References 47 publications

Application of contemporary computer methods in laryngeal cancer diagnosis and treatment

Application of contemporary computer methods in laryngeal cancer diagnosis and treatment

The effects of 20-hydroxyecdysone on nuclear shape, heterochromatin quantity and gray-level co-occurrence matrix texture analysis of adrenal zona fasciculata cells in an obese gerbil (Gerbillus tarabuli) model for metabolic syndrome: a correlational study

Multifractal characterization of grayscale histopathological images: Unveiling patterns linked to metastases in breast cancer

Contact Info

Product

Resources

About