Revolutionizing Ovarian Cancer Diagnosis: The Role of Advanced Imaging Techniques
Fuente:
Zenodo
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Recurso digital |
| Lenguaje: | inglés |
| Publicado: |
Zenodo
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866901847434854400 |
|---|---|
| author | A.A.Rajabbaev B.A.Choriyev |
| author_facet | A.A.Rajabbaev B.A.Choriyev |
| contents | <p><span>Ovarian cancer remains one of the most lethal gynecological malignancies, posing a significant public health challenge due to its high mortality rates and frequent recurrence. Despite advancements in screening and diagnostic technologies, the disease is often diagnosed at advanced stages, leading to poor prognoses. This study aims to revolutionize the differentiation of ovarian masses by integrating advanced ultrasound imaging techniques with machine learning algorithms. Data from 121 patients with histologically confirmed ovarian tumors were analyzed using transvaginal and transabdominal ultrasound methods. A combination of logistic regression models and machine learning algorithms was employed to process multidimensional ultrasound data, significantly improving the accuracy of distinguishing between benign and malignant tumors. The implementation of a comprehensive scoring system, alongside logistic regression modeling, demonstrated a remarkable increase in diagnostic accuracy. The predictive model, based on morphological characteristics such as size, shape, echogenicity, and vascularization, achieved a sensitivity of 93%, specificity of 92%, and overall accuracy of 92.5%, as confirmed by ROC curve analysis. This study underscores the transformative potential of machine learning in ultrasound imaging for ovarian tumors, suggesting that advanced assessment and predictive modeling could lead to earlier and more precise diagnoses, ultimately improving patient outcomes.</span></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_14779896 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Revolutionizing Ovarian Cancer Diagnosis: The Role of Advanced Imaging Techniques A.A.Rajabbaev B.A.Choriyev Ovarian cancer, ultrasound imaging, machine learning, predictive modeling, tumor differentiation, benign tumors, malignant tumors, pathology, scoring system, histological features, borderline tumors, ovarian tumors, serous tumors, mucinous tumors, clear cell adenocarcinoma, tumor morphology, diagnostic accuracy, ROC curve, public health, healthcare standards, early detection, treatment sensitivity, survival rate, reproductive health, gynecological oncology, healthcare innovation, patient management, clinical outcomes. <p><span>Ovarian cancer remains one of the most lethal gynecological malignancies, posing a significant public health challenge due to its high mortality rates and frequent recurrence. Despite advancements in screening and diagnostic technologies, the disease is often diagnosed at advanced stages, leading to poor prognoses. This study aims to revolutionize the differentiation of ovarian masses by integrating advanced ultrasound imaging techniques with machine learning algorithms. Data from 121 patients with histologically confirmed ovarian tumors were analyzed using transvaginal and transabdominal ultrasound methods. A combination of logistic regression models and machine learning algorithms was employed to process multidimensional ultrasound data, significantly improving the accuracy of distinguishing between benign and malignant tumors. The implementation of a comprehensive scoring system, alongside logistic regression modeling, demonstrated a remarkable increase in diagnostic accuracy. The predictive model, based on morphological characteristics such as size, shape, echogenicity, and vascularization, achieved a sensitivity of 93%, specificity of 92%, and overall accuracy of 92.5%, as confirmed by ROC curve analysis. This study underscores the transformative potential of machine learning in ultrasound imaging for ovarian tumors, suggesting that advanced assessment and predictive modeling could lead to earlier and more precise diagnoses, ultimately improving patient outcomes.</span></p> |
| title | Revolutionizing Ovarian Cancer Diagnosis: The Role of Advanced Imaging Techniques |
| topic | Ovarian cancer, ultrasound imaging, machine learning, predictive modeling, tumor differentiation, benign tumors, malignant tumors, pathology, scoring system, histological features, borderline tumors, ovarian tumors, serous tumors, mucinous tumors, clear cell adenocarcinoma, tumor morphology, diagnostic accuracy, ROC curve, public health, healthcare standards, early detection, treatment sensitivity, survival rate, reproductive health, gynecological oncology, healthcare innovation, patient management, clinical outcomes. |
| url | https://doi.org/10.5281/zenodo.14779896 |