I am a dedicated researcher and educator with a strong passion for Biomedical Image Analysis, focusing on the early detection of ovarian tumors and PCOD, conditions that significantly impact young adults. With advancements in technology, I am committed to leveraging cutting-edge image processing and AI-driven diagnostic tools to enable early detection and intervention. My ultimate goal is to reduce suffering and improve the quality of life for those affected by these conditions.

Beyond research, teaching is my true calling. As a faculty member, I strive to create an engaging learning environment where students can discover their potential, develop critical thinking skills, and prepare to become the future leaders of our nation. I believe that every student has unique capabilities, and my mission is to help them unlock their strengths, gain confidence, and excel in their respective fields.

Through my work in both research and education, I aim to bridge the gap between academia and real-world applications, ensuring that technological advancements translate into meaningful healthcare solutions. My journey is driven by the vision of a healthier society, where early diagnosis prevents long-term suffering, and where students are empowered to contribute to scientific progress.

"Education is the most powerful weapon which you can use to change the world." - Nelson Mandela ·

• Polycystic Ovarian Disease (PCOD) and Ovarian Cancer are significant health concerns affecting women worldwide.
• Early and accurate detection is critical for effective treatment and improved prognosis.
• Current diagnostic methods rely on manual interpretation of ultrasound, CT, and histopathology images, which can be subjective and time-consuming.
• AI-based computational models can enhance diagnostic accuracy and assist healthcare professionals in early-stage detection.
• Develop a robust AI-based framework for the automated detection and classification of PCOD and ovarian cancer.
• Integrate multi-modal imaging (Ultrasound, CT, and Histopathology) to improve diagnostic accuracy.
• Utilize deep learning techniques for feature extraction, lesion segmentation, and classification.
• Enhance interpretability and explainability of AI models for clinical adoption.
• A high-accuracy AI-based diagnostic framework for PCOD and ovarian cancer detection.
• Improved early detection rates, reducing misdiagnosis and treatment delays.
• Potential integration into clinical workflows for real-time decision support.
• AI-based computational frameworks can revolutionize ovarian disease diagnosis by enhancing precision, efficiency, and accessibility.
• Future work includes expanding datasets, refining model interpretability, and clinical validation through collaborations with healthcare institutions.
• Research Interests
  
• Biomedical Image Analysis
• Machine Learning
• Deep Learning
• Generative AI
• XAI models