Winter School Internship Program in Cancer Tumor Detection Using Medical Imaging & Machine Learning Techniques

Duration: 5 Weeks (15 Feb – 24 Mar, 2026)
Mode: Live Online | Hands-On | Mentor-Guided

Program Overview

The Winter School Internship Program in Cancer Tumor Detection is a 5-week live, hands-on training program designed to introduce participants to medical imaging and AI-based tumor detection workflows used in modern cancer research and healthcare.

Through interactive live sessions and guided practical exercises, participants gain real-world experience in medical image preprocessing, deep learning-based tumor classification and segmentation, explainable AI, and end-to-end imaging pipelines. The program is beginner-friendly and focuses on practical implementation using real datasets and industry-relevant tools.

What You Will Learn

By the end of this program, you will be able to:

• Understand the medical imaging ecosystem and clinical use-cases

• Work with CT, MRI, microscopy, and histopathology data

• Handle medical image formats such as DICOM, NIFTI, and OME-TIFF

• Preprocess imaging datasets for deep learning applications

• Build CNN-based models for tumor classification

• Perform tumor segmentation using architectures like U-Net

• Apply explainable AI techniques (e.g., Grad-CAM) to interpret results

• Design and present end-to-end imaging AI workflows

Learning Experience

• Live mentor-guided sessions with real-time interaction

• Weekly hands-on coding tasks and guided discussions

• Access to session recordings and curated learning materials

• Continuous technical and bioinformatics support

• Real-world datasets and research-oriented workflows

Tools & Technologies

Participants will gain hands-on experience with:

Python, NumPy, Pandas, OpenCV, SimpleITK, pydicom, NiBabel, MONAI, PyTorch, PyTorch Lightning, MLflow, Docker, GitHub, Jupyter Notebook, OHIF Viewer, Google Colab

Program Structure (Week-Wise)

Week 1: Foundations of medical imaging and Python basics
Week 2: Image preprocessing and deep learning fundamentals
Week 3: Tumor segmentation and model explainability
Week 4: Advanced imaging AI and multimodal learning
Week 5: End-to-end imaging pipelines, MLOps, and project completion

Capstone Project & Certification

• Real-world tumor detection project

• Project documentation and GitHub submission

• Personalized feedback and project review

• Course & Internship Completion Certificate

Who Should Enroll?

This program is ideal for students, early-career researchers, and life science professionals who want to gain hands-on experience in medical imaging, deep learning, and AI-driven cancer research. No prior machine learning experience is required.