KonfAI: A Modular and Fully Configurable Framework for Deep Learning in Medical Imaging

TL;DR

KonfAI is a flexible, modular deep learning framework tailored for medical imaging, enabling customizable workflows and advanced training strategies to improve reproducibility and performance.

Contribution

It introduces a fully configurable, declarative framework that simplifies complex medical imaging deep learning workflows and supports advanced techniques like patch-based learning and multi-model training.

Findings

Applied to segmentation, registration, and synthesis tasks

Achieved top results in international challenges

Supports extensive customization and advanced strategies

Abstract

KonfAI is a modular, extensible, and fully configurable deep learning framework specifically designed for medical imaging tasks. It enables users to define complete training, inference, and evaluation workflows through structured YAML configuration files, without modifying the underlying code. This declarative approach enhances reproducibility, transparency, and experimental traceability while reducing development time. Beyond the capabilities of standard pipelines, KonfAI provides native abstractions for advanced strategies including patch-based learning, test-time augmentation, model ensembling, and direct access to intermediate feature representations for deep supervision. It also supports complex multi-model training setups such as generative adversarial architectures. Thanks to its modular and extensible architecture, KonfAI can easily accommodate custom models, loss functions, and data processing components. The framework has been successfully applied to segmentation, registration, and image synthesis tasks, and has contributed to top-ranking results in several international medical imaging challenges. KonfAI is open source and available at https://github.com/vboussot/KonfAI.