At Leading India, I developed BrainScan AI, an explainable deep learning system for detecting and classifying brain tumors from MRI scans. I combined MobileNetV2, EfficientNetB0, and a custom CNN, achieving 97–98% validation accuracy, and integrated Grad-CAM to show which regions influenced predictions.
I also developed and deployed the application using Python, TensorFlow, Keras, OpenCV, Flask, and React.js. BrainScan AI received runner-up recognition at the National Level Project Competition (SYNERGY-26) and TechQuest 2026.
On LogicPilot, I developed an AI-assisted coding platform for guided problem-solving, with Socratic debugging, logic-gap detection, and interactive code visualization. I also developed an AI interview preparation platform with resume-aware questions, Whisper-based transcription, and automated feedback.
