PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction
2026-04-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial IntelligenceMachine Learning
AI summaryⓘ
The authors created PR3DICTR, a computer tool that helps researchers build and test models for classifying 3D medical images using deep learning. It is built with popular programming tools and is designed to be easy to use, flexible, and standardized. The platform offers ready-made features for designing models and training them but also allows users to add their own components. PR3DICTR works for tasks where the goal is to classify 3D data into two categories or based on specific events, and it can be used with very little coding.
3D medical imagingdeep learningclassificationPyTorchMONAImodel architecturehyper-parameter tuningbinary classificationcomputer-aided diagnosis
Authors
Daniel C. MacRae, Luuk van der Hoek, Robert van der Wal, Suzanne P. M. de Vette, Hendrike Neh, Baoqiang Ma, Peter M. A. van Ooijen, Lisanne V. van Dijk
Abstract
Three-dimensional medical image data and computer-aided decision making, particularly using deep learning, are becoming increasingly important in the medical field. To aid in these developments we introduce PR3DICTR: Platform for Research in 3D Image Classification and sTandardised tRaining. Built using community-standard distributions (PyTorch and MONAI), PR3DICTR provides an open-access, flexible and convenient framework for prediction model development, with an explicit focus on classification using three-dimensional medical image data. By combining modular design principles and standardization, it aims to alleviate developmental burden whilst retaining adjustability. It provides users with a wealth of pre-established functionality, for instance in model architecture design options, hyper-parameter solutions and training methodologies, but still gives users the opportunity and freedom to ``plug in'' their own solutions or modules. PR3DICTR can be applied to any binary or event-based three-dimensional classification task and can work with as little as two lines of code.