TY - JOUR
T1 - GaNDLF
T2 - the generally nuanced deep learning framework for scalable end-to-end clinical workflows
AU - Pati, Sarthak
AU - Thakur, Siddhesh P.
AU - Hamamcı, İbrahim Ethem
AU - Baid, Ujjwal
AU - Baheti, Bhakti
AU - Bhalerao, Megh
AU - Güley, Orhun
AU - Mouchtaris, Sofia
AU - Lang, David
AU - Thermos, Spyridon
AU - Gotkowski, Karol
AU - González, Camila
AU - Grenko, Caleb
AU - Getka, Alexander
AU - Edwards, Brandon
AU - Sheller, Micah
AU - Wu, Junwen
AU - Karkada, Deepthi
AU - Panchumarthy, Ravi
AU - Ahluwalia, Vinayak
AU - Zou, Chunrui
AU - Bashyam, Vishnu
AU - Li, Yuemeng
AU - Haghighi, Babak
AU - Chitalia, Rhea
AU - Abousamra, Shahira
AU - Kurc, Tahsin M.
AU - Gastounioti, Aimilia
AU - Er, Sezgin
AU - Bergman, Mark
AU - Saltz, Joel H.
AU - Fan, Yong
AU - Shah, Prashant
AU - Mukhopadhyay, Anirban
AU - Tsaftaris, Sotirios A.
AU - Menze, Bjoern
AU - Davatzikos, Christos
AU - Kontos, Despina
AU - Karargyris, Alexandros
AU - Umeton, Renato
AU - Mattson, Peter
AU - Bakas, Spyridon
N1 - Publisher Copyright:
© The Author(s) 2023.
PY - 2023/12
Y1 - 2023/12
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85162636795
U2 - 10.1038/s44172-023-00066-3
DO - 10.1038/s44172-023-00066-3
M3 - Article
AN - SCOPUS:85162636795
SN - 2731-3395
VL - 2
JO - Communications Engineering
JF - Communications Engineering
IS - 1
M1 - 23
ER -