MICCAI 2026 Tutorial

Learning to Self-Organize: Neural Cellular Automata for Medical Imaging

Organizers: John Kalkhof, Caroline Essert, Marco Lorenzi, Carsten Marr, Anirban Mukhopadhyay, Camila González, Marawan Elbatel, Daniel Lang, Ario Sadafi, Maximilian Buser, Michael Deutges, Jonas Mehtali, Henry Krumb, Mirko Konstantin, Nick Lemke

  • Duration~4h (incl breaks)
  • FormatLecture ↔ Hands-on (~50/50)
  • DeliveryGoogle Colab
  • RequirementsLaptop

Abstract

Medical image analysis increasingly relies on large neural networks. While powerful, these models often lack robustness across diverse data, are difficult to interpret, and are inefficient for large-scale or edge computing applications. Neural Cellular Automata (NCA) are an emerging architectural paradigm: they learn local update rules that are iteratively applied so that complex anatomical or morphological patterns emerge through self-organization. This formulation enables models to reach performance comparable to much larger architectures while using two to three orders of magnitude fewer parameters and providing insight into the intermediate updates. This tutorial introduces the foundations of NCAs, their training and emergent behavior, and reviews recent medical-imaging applications including segmentation, temporally consistent synthesis, robust classification, and fast surrogate modeling for therapy planning. Prepared Colab-based hands-on sessions will guide participants to train models, visualize local updates, and apply NCAs to example tasks.

View Agenda Access Materials

Why This Tutorial

Medical image analysis increasingly relies on large neural networks, which raises challenges around computational efficiency, robustness across heterogeneous data, and interpretability in clinical practice. NCA approaches these problems through local iterative updates that produce global structure via self-organization.

The tutorial is designed for participants familiar with deep learning but new to NCAs, and aims to provide both conceptual understanding and practical experience. By the end, participants should be able to train NCAs for medical imaging tasks, visualize their iterative dynamics, and evaluate trade-offs between performance, robustness, and efficiency.

Agenda

10 min0:00-0:10Welcome
20 min0:10-0:30Foundations
30 min0:30-1:00Hands-on 1
10 min1:00-1:10Break
20 min1:10-1:30Applications
40 min1:30-2:10Hands-on 2
10 min2:10-2:20Break
20 min2:20-2:40Simulation
10 min2:40-2:50Tips
30 min2:50-3:20Hands-on 3
15 min3:20-3:35Outlook
15 min3:35-3:50Q&A
Duration Time Session Topic
10 min 0:00-0:10 Lecture

Welcome and setup (Wi-Fi check, Colab access, goals)
20 min 0:10-0:30 Lecture

Foundations of NCA (CA → NCA, local updates, emergence, architecture)
30 min 0:30-1:00 Hands-on

Train a minimal NCA in Colab and visualize iterative updates
10 min 1:00-1:10 Break

Break
20 min 1:10-1:30 Lecture

Applications in medical imaging (segmentation, registration, detection)
40 min 1:30-2:10 Hands-on

Train classification and segmentation models; evaluate robustness
10 min 2:10-2:20 Break

Break
20 min 2:20-2:40 Lecture

Applications in medical imaging (simulation)
10 min 2:40-2:50 Lecture

Tips for training and technical details
30 min 2:50-3:20 Hands-on

Extend to detection/simulation
15 min 3:20-3:35 Lecture

Interpretability and outlook (limits, future directions)
15 min 3:35-3:50 Discussion

Final Q&A

Materials

Tutorial materials will follow.