Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction

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.

PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction

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.

Paper Structure

This paper contains 13 sections, 6 figures.

Table of Contents

  1. Introduction
  2. Methods
  3. Prerequisite: Data curation
  4. Modularity
  5. Framework & user interaction
  6. The PR3DICTR architecture
  7. Dataset, loaders and augmentation
  8. Training, hyperparameter optimization and experiments
  9. Model training evaluation
  10. Model evaluation on the test set
  11. Example use case
  12. Discussion
  13. Conclusion

Figures (6)

  • Figure 1: Example of a binary classification deep learning model workflow using 3D medical imaging.
  • Figure 2: Overall PR3DICTR workflow. An example notebook for steps 1--3 can be found in the repository, and another notebook demonstrates steps 4--6.
  • Figure 3: Schematic of a data pre-processing pipeline for preparing datasets to be used in the PR3DICTR framework.
  • Figure 4: Code flow diagram of the PR3DICTR framework.
  • Figure 5: Outline of the classification model framework in PR3DICTR, for a hypothetical 2-label classification task.
  • ...and 1 more figures