Impact Factor

7.883 Call For Paper

Share on

Author(s):

V Gokulakrishnan | Prathiba CS | Harshinidevi G | Mariya Vianney A | Naveena V
Keywords:

Brain Tumor Detection, Convolutional Neural Networks, Deep Learning, Fetal Ultrasound, Prenatal Diagnosis
Abstract:
The Early Identification Of Brain Tumors In Fetus Is Critical For Timely Medical Intervention And Improved Neonatal Outcomes. This Study Presents A Deep Learning-based Approach To Automatically Detect And Classify Brain Tumors In Fetal Ultrasound Images, Aiming To Support Clinicians In Diagnostic Processes. Leveraging The Power Of Convolutional Neural Networks (CNNs), The Proposed Model Analyzes Subtle Patterns And Structural Abnormalities That Are Often Challenging To Discern Through Manual Observation. A Curated Dataset Of Fetal Brain Ultrasound Scans Was Utilized To Train And Validate The Model, Ensuring Robustness And Generalizability. Image Preprocessing Techniques, Including Noise Reduction And Contrast Enhancement, Were Applied To Optimize Feature Extraction. Performance Metrics Such As Accuracy, Sensitivity, And Precision Were Employed To Evaluate The Model's Effectiveness. Results Demonstrate The Model's Potential In Assisting Radiologists By Offering High Detection Accuracy With Minimal False Positives. This Research Underscores The Value Of Deep Learning In Prenatal Care And Highlights Its Application In Enhancing Diagnostic Accuracy For Fetal Neurological Conditions Through Non-invasive Imaging Techniques.

Download Article