GaNDLF: A Generally Nuanced Deep Learning Framework for Scalable End-to-End Clinical Workflows in Medical Imaging

Abstract

Deep Learning (DL) has the potential to optimize machine learning in both the scientific and clinical communities. However, greater expertise is required to develop DL algorithms, and the variability of implementations hinders their reproducibility, translation, and deployment. Here we present the community-driven Generally Nuanced Deep Learning Framework (GaNDLF), with the goal of lowering these barriers. GaNDLF makes the mechanism of DL development, training, and inference more stable, reproducible, interpretable, and scalable, without requiring an extensive technical background. GaNDLF aims to provide an end-to-end solution for all DL-related tasks in computational precision medicine. We demonstrate the ability of GaNDLF to analyze both radiology and histology images, with built-in support for k-fold cross-validation, data augmentation, multiple modalities and output classes. Our quantitative performance evaluation on numerous use cases, anatomies, and computational tasks supports GaNDLF as a robust application framework for deployment in clinical workflows.

arXiv commentDeep Learning, Framework, Segmentation, Regression, Classification, Cross-validation, Data augmentation, Deployment, Clinical, Workflows

References in corpus (26)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Image biomarker standardisation initiative
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• A systematic study of the class imbalance problem in convolutional neural networks
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Albumentations: fast and flexible image augmentations
• Neural Architecture Search: A Survey
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Mixed Precision Training
• Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning
• NiftyNet: a deep-learning platform for medical imaging
• MONAI: An open-source framework for deep learning in healthcare
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection
• UNETR: Transformers for 3D Medical Image Segmentation
• The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort study
• OpenFL: An open-source framework for Federated Learning
• Analysis Towards Classification of Infection and Ischaemia of Diabetic Foot Ulcers
• DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images
• DeepReg: a deep learning toolkit for medical image registration
• pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis
• Brain Extraction from Normal and Pathological Images: A Joint PCA/Image-Reconstruction Approach
• Federated Learning for the Classification of Tumor Infiltrating Lymphocytes
• Learning from Thresholds: Fully Automated Classification of Tumor Infiltrating Lymphocytes for Multiple Cancer Types

Cited by in corpus (5)

• MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation
• The Brain Tumor Segmentation (BraTS) Challenge 2023: Glioma Segmentation in Sub-Saharan Africa Patient Population (BraTS-Africa)
• Integration of nested cross-validation, automated hyperparameter optimization, high-performance computing to reduce and quantify the variance of test performance estimation of deep learning models
• The Federated Tumor Segmentation (FeTS) Challenge
• Efficient 3D Brain Tumor Segmentation with Axial-Coronal-Sagittal Embedding