Mohsin Furkh Dar
Bridging the gap between AI research and practical applications through innovative web solutions. I specialize in building intelligent web applications that leverage cutting-edge AI/ML technologies to solve real-world problems in healthcare, education, and beyond.
Research Focus
About Me
Bridging AI Innovation with Clinical Impact
I am a PhD graduate in Computer Science from the University of Hyderabad, specializing in Deep Learning for Medical Image Analysis. Currently serving as Assistant Professor at UPES School of Computer Science, my research has produced breakthrough innovations including EfficientU-Net, UMA-Net with adaptive loss functions, and Saliency-Guided AttentionNet. With NET JRF qualification (AIR under 50), my work spans novel architectures, genetic algorithm-based feature selection, and attention mechanisms validated across multiple medical imaging modalities.
As Founder of ShifaAI, I'm translating academic research into real-world healthcare solutions through AI-powered diagnostic platforms that provide automated medical image analysis and intelligent clinical decision support. My mission is democratizing access to expert-level medical interpretation, particularly in underserved regions where specialized healthcare is limited. I am open to collaborations in medical AI research and clinical partnerships to further advance the field of healthcare AI.
Deep Learning
Advanced neural architectures for medical image analysis
Medical Imaging
Multi-modal imaging: CT, MRI, X-ray, ultrasound
Clinical Collaboration
Translating research into real-world medical applications
Research Leadership
Mentoring students and leading interdisciplinary projects
Featured Research
PhD Thesis: Advances in Deep Learning for Medical Imaging
Developed novel deep learning architectures for medical image segmentation and classification, achieving state-of-the-art performance in breast cancer detection from ultrasound images and other medical image modalities.
ShifaAI: AI-Powered Healthcare Platform
ShifaAI is revolutionizing healthcare with AI-powered diagnostics, automated report analysis, and personalized treatment suggestions for patients and healthcare providers.
Built using Next.js, TensorFlow, and modern web technologies, it reduces diagnostic errors and accelerates care delivery through intelligent automation.
Currently in active development with new features rolling out regularly
MPhil Thesis: Performance Comparison of Face Detection and Recognition Algorithms
A comprehensive evaluation of face detection and recognition algorithms, analyzing performance metrics and computational efficiency across various benchmarks including WIDER FACE and MegaFace.
- SSH achieved highest precision-recall in detection but with slower processing
- Dlib-R and ArcFace showed superior recognition accuracy
- Detailed analysis of speed-accuracy tradeoffs in real-world applications
Let's Collaborate
Interested in my research or exploring collaboration opportunities? I'd love to hear from you.