Publications

A PDF of any paper below is available on request – please get in touch.

2025

C-NCA: Chained Neural Cellular Automata for Fast and Accurate Thermal Ablation Estimation

Jonas Mehtali, Juan Verde, Caroline Essert

Medical Image Computing and Computer Assisted Interventions (MICCAI 2025), Seoul, Korea, September 28 – October 2, 2025

Conference Paper E-Poster

Abstract. We introduce an approach to estimate heat-induced tissue death in percutaneous thermal ablation based on a chained Neural Cellular Automata (NCA) architecture. The model accurately estimates cell death induced by thermal damage with low root mean square error and high speed. With only 12,210 learned parameters, it can compute 25 minutes of treatment at up to 476 fps, making it suitable for interactive simulations and optimization loops.

Paper · E-Poster · DOI

BibTeX

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
@inproceedings{mehtali2025cnca,
  author    = {Mehtali, Jonas and Verde, Juan and Essert, Caroline},
  title     = {C-NCA: Chained Neural Cellular Automata for Fast and Accurate
               Thermal Ablation Estimation},
  booktitle = {Medical Image Computing and Computer Assisted Interventions (MICCAI 2025)},
  year      = {2025},
  address   = {Seoul, Korea},
  pages     = {156--165},
  doi       = {10.1007/978-3-032-04965-0\\_7}
}

Heat: High-Efficiency Simulation for Thermal Ablation Therapy

Jonas Mehtali, Juan Verde, Caroline Essert

International Journal of Computer Assisted Radiology and Surgery (IJCARS), 2025, 20(6), pp. 1135–1143

Journal Article

Abstract. Percutaneous thermal ablation is increasingly popular but still suffers from complex preoperative planning, especially regarding the prediction of the ablation zone. We propose HEAT (High-Efficiency simulation for thermal Ablation Therapy), a novel GPU-accelerated simulation framework for thermal ablation that enables real-time planning.

Paper · DOI

BibTeX

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
@article{mehtali2025heat,
  author  = {Mehtali, Jonas and Verde, Juan and Essert, Caroline},
  title   = {Heat: High-Efficiency Simulation for Thermal Ablation Therapy},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year    = {2025},
  volume  = {20},
  number  = {6},
  pages   = {1135--1143},
  doi     = {10.1007/s11548-025-03350-z}
}

2024

Henry J. Krumb, Jonas Mehtali, Juan Verde, Anirban Mukhopadhyay, Caroline Essert

Medical Image Computing and Computer Assisted Interventions (MICCAI 2024), Marrakesh, Morocco, October 6–10, 2024 Volume 15006, pp. 99–108

Conference Paper

Abstract. Cryoablation is a minimally invasive technique that uses extreme cold to destroy cancerous tumors. However, it remains challenging to plan and navigate during the procedure. We present Cryotrack, a novel planning and navigation system for computer-assisted cryoablation.

Paper · DOI

BibTeX

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
@inproceedings{krumb2024cryotrack,
  author    = {Krumb, Henry J. and Mehtali, Jonas and Verde, Juan and
               Mukhopadhyay, Anirban and Essert, Caroline},
  title     = {Cryotrack: Planning and Navigation for Computer Assisted Cryoablation},
  booktitle = {Medical Image Computing and Computer Assisted Interventions (MICCAI 2024)},
  year      = {2024},
  address   = {Marrakesh, Morocco},
  pages     = {99--108},
  doi       = {10.1007/978-3-031-72089-5\\_10}
}

Research Interests

Thermal ablation therapy planning
Cryoablation simulation and navigation
Medical image computing
Computer-assisted interventions
GPU-accelerated simulation
Image-guided surgery

Last updated: April 2026