Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Comprehensive Performance Testing and External Validation of an AI Algorithm to Detect and Segment Brain Metastases.

Neuro-oncology·2026

Same author

A complicated case of a spinal Scedosporium apiospermum infection with a favorable outcome-case report.

Wiener medizinische Wochenschrift (1946)·2026

Same author

Mind the gap: challenges and future directions for content-based image retrieval in clinical radiology.

Frontiers in radiology·2026

Same author

Intraoperative fusion of models and data for robust distance sensing.

International journal of computer assisted radiology and surgery·2026

Same author

Disentangled generative uncertainty-aware multi-modal diffusion segmentation of medical images.

Medical image analysis·2026

Same author

[Training and Experience of Healthcare Professionals in Clinical Teaching: A Study in Primary Care in Chile].

Revista medica de Chile·2026

Search research articles

Related Experiment Video

Updated: Dec 2, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis.

Alain Jungo¹, Olivier Scheidegger², Mauricio Reyes¹

¹ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland.

Computer Methods and Programs in Biomedicine

|November 2, 2020

Summary

This summary is machine-generated.

The pymia package enhances deep learning for medical image analysis by offering specialized data handling and evaluation tools. This open-source Python package supports various data formats and domain-specific metrics, streamlining research and development.

Keywords:

Data handling Deep learning Evaluation Medical image analysis Metrics

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Published on: November 7, 2025

Related Experiment Videos

Last Updated: Dec 2, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Analysis of Multidimensional Microscopy Data Using Cell-ACDC

Published on: November 7, 2025

Area of Science:

Medical image analysis
Deep learning
Computational biology

Background:

Deep learning frameworks like TensorFlow and PyTorch lack specialized medical imaging functionalities.
Challenges in medical image analysis include 3-D data handling and domain-specific evaluation metrics.
Existing frameworks do not adequately address the unique needs of medical image analysis pipelines.

Purpose of the Study:

Introduce pymia, an open-source Python package designed to bridge the gap in deep learning for medical image analysis.
Provide flexible, framework-independent data handling and evaluation functionalities.
Facilitate the integration of diverse data types and advanced metrics into medical imaging deep learning workflows.

Main Methods:

pymia offers versatile data handling for 2-D, 2.5-D, and 3-D medical images, supporting full- or patch-wise processing.
The package integrates non-image data like demographics and clinical reports into deep learning pipelines.
pymia provides comprehensive evaluation tools with domain-specific metrics for segmentation, reconstruction, and regression tasks, enabling stand-alone reporting and performance monitoring.

Main Results:

pymia demonstrates high flexibility, enabling rapid prototyping and reducing implementation effort for data handling and evaluation.
Data handling and evaluation modules are independent of deep learning frameworks but seamlessly integrate with TensorFlow and PyTorch.
The package has been successfully applied in diverse research projects, including segmentation, reconstruction, and regression tasks.

Conclusions:

pymia effectively addresses the limitations of current deep learning frameworks in medical image analysis.
The package offers a specialized solution for data handling and evaluation, crucial for advancing medical imaging research.
pymia is readily available on GitHub and installable via pip, promoting its adoption in the research community.