Hasan Shaikh — Researcher in AI for Cancer Imaging

“The real purpose of research is not just discovery — but translation. That’s where science becomes service.”

Welcome! I’m Hasan Shaikh, a passionate AI researcher working at the Quantitative Imaging Research and Artificial Intelligence Lab (QIRAIL), Christian Medical College (CMC) Vellore, India. My work lies at the intersection of cancer imaging, radiomics, and deep learning, with a vision to bring real-world clinical impact through data-driven solutions.

👨‍💻 About Me

• 🔬 Currently involved in prospective clinical studies to predict locoregional recurrence in head and neck cancer using CT imaging and radiomics.
• 🧠 Special focus on explainable machine learning, automated segmentation, and integrating AI into clinical workflows.
• 🛠️ Skilled in Python, PyRadiomics, scikit-learn, nnUNet, MedSAM, and full-stack development tools like React and FastAPI.
• 🤝 Collaborating across departments, including Radiation Oncology, Computer Science, and AI research labs.
• 🧪 Past projects include multimodal survival prediction, deep learning pipelines, and feature optimization using metaheuristic algorithms (PSO, WOA, GWO).

I’m committed to combining domain knowledge, technical skill, and clinical understanding to develop systems that can genuinely assist doctors and improve patient care.

🔍 Current Research Focus

• Radiomics-Based Recurrence Prediction
  Developing robust ML pipelines for analyzing texture, shape, and intensity features from CT images to stratify recurrence risk.

• AI-Driven Tumor Segmentation
  Applying state-of-the-art models like nnUNet and MedSAM for accurate and reproducible tumor volume segmentation in clinical datasets.

• Clinical Dashboard Integration
  Building end-to-end dashboards with backend (FastAPI) + frontend (React) to bring predictions and risk assessments into the hands of clinicians.

• Model Explainability & Generalization
  Exploring feature attribution, cohort variation, and domain shifts across datasets to ensure models remain reliable and understandable.

💡 Why This Website?

This portfolio exists not only to archive my work but to share ideas, progress, and collaborations. It reflects my journey from solving small classification tasks to designing clinically relevant AI pipelines. Here, you’ll find:

• A showcase of ongoing and past projects
• A list of talks, posters, and presentations
• Published abstracts and book chapters
• My academic CV and roadmap for future exploration

If you’re a fellow researcher, professor, or prospective collaborator interested in cancer imaging, medical AI, or clinical implementation — I’d love to connect.

📬 Let’s Connect

Feel free to reach out through LinkedIn, GitHub, or email me.

Let’s use AI not just to interpret medical images — but to empower clinical decisions, one model at a time.