MONAI Label: A framework for AI-assisted interactive labeling of 3D medical images

Andres Diaz-Pinto; Sachidanand Alle; Vishwesh Nath; Yucheng Tang; Alvin Ihsani; Muhammad Asad; Fernando Pérez-García; Pritesh Mehta; Wenqi Li; Mona Flores; Holger R. Roth; Tom Vercauteren; Daguang Xu; Prerna Dogra; Sebastien Ourselin; Andrew Feng; M. Jorge Cardoso

doi:10.1016/j.media.2024.103207

MONAI Label: A framework for AI-assisted interactive labeling of 3D medical images

Andres Diaz-Pinto^*, Sachidanand Alle, Vishwesh Nath, Yucheng Tang, Alvin Ihsani, Muhammad Asad, Fernando Pérez-García, Pritesh Mehta, Wenqi Li, Mona Flores, Holger R. Roth, Tom Vercauteren, Daguang Xu, Prerna Dogra, Sebastien Ourselin, Andrew Feng, M. Jorge Cardoso

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

Abstract

The lack of annotated datasets is a major bottleneck for training new task-specific supervised machine learning models, considering that manual annotation is extremely expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source framework that facilitates the development of applications based on artificial intelligence (AI) models that aim at reducing the time required to annotate radiology datasets. Through MONAI Label, researchers can develop AI annotation applications focusing on their domain of expertise. It allows researchers to readily deploy their apps as services, which can be made available to clinicians via their preferred user interface. Currently, MONAI Label readily supports locally installed (3D Slicer) and web-based (OHIF) frontends and offers two active learning strategies to facilitate and speed up the training of segmentation algorithms. MONAI Label allows researchers to make incremental improvements to their AI-based annotation application by making them available to other researchers and clinicians alike. Additionally, MONAI Label provides sample AI-based interactive and non-interactive labeling applications, that can be used directly off the shelf, as plug-and-play to any given dataset. Significant reduced annotation times using the interactive model can be observed on two public datasets.

Original language	English
Article number	103207
Journal	Medical Image Analysis
Volume	95
Early online date	21 May 2024
DOIs	https://doi.org/10.1016/j.media.2024.103207
Publication status	Published - Jul 2024

Keywords

3D medical imaging
Active learning
Deep learning
Interactive 3D image segmentation

Access to Document

10.1016/j.media.2024.103207

Cite this

Diaz-Pinto, A., Alle, S., Nath, V., Tang, Y., Ihsani, A., Asad, M., Pérez-García, F., Mehta, P., Li, W., Flores, M., Roth, H. R., Vercauteren, T., Xu, D., Dogra, P., Ourselin, S., Feng, A., & Cardoso, M. J. (2024). MONAI Label: A framework for AI-assisted interactive labeling of 3D medical images. Medical Image Analysis, 95, Article 103207. https://doi.org/10.1016/j.media.2024.103207

@article{4f0663e9d16e4a2e9a36f372e5ff11b7,

title = "MONAI Label: A framework for AI-assisted interactive labeling of 3D medical images",

abstract = "The lack of annotated datasets is a major bottleneck for training new task-specific supervised machine learning models, considering that manual annotation is extremely expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source framework that facilitates the development of applications based on artificial intelligence (AI) models that aim at reducing the time required to annotate radiology datasets. Through MONAI Label, researchers can develop AI annotation applications focusing on their domain of expertise. It allows researchers to readily deploy their apps as services, which can be made available to clinicians via their preferred user interface. Currently, MONAI Label readily supports locally installed (3D Slicer) and web-based (OHIF) frontends and offers two active learning strategies to facilitate and speed up the training of segmentation algorithms. MONAI Label allows researchers to make incremental improvements to their AI-based annotation application by making them available to other researchers and clinicians alike. Additionally, MONAI Label provides sample AI-based interactive and non-interactive labeling applications, that can be used directly off the shelf, as plug-and-play to any given dataset. Significant reduced annotation times using the interactive model can be observed on two public datasets.",

keywords = "3D medical imaging, Active learning, Deep learning, Interactive 3D image segmentation",

author = "Andres Diaz-Pinto and Sachidanand Alle and Vishwesh Nath and Yucheng Tang and Alvin Ihsani and Muhammad Asad and Fernando P{\'e}rez-Garc{\'i}a and Pritesh Mehta and Wenqi Li and Mona Flores and Roth, {Holger R.} and Tom Vercauteren and Daguang Xu and Prerna Dogra and Sebastien Ourselin and Andrew Feng and Cardoso, {M. Jorge}",

note = "Publisher Copyright: {\textcopyright} 2024",

year = "2024",

month = jul,

doi = "10.1016/j.media.2024.103207",

language = "English",

volume = "95",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier",

}

TY - JOUR

T1 - MONAI Label

T2 - A framework for AI-assisted interactive labeling of 3D medical images

AU - Diaz-Pinto, Andres

AU - Alle, Sachidanand

AU - Nath, Vishwesh

AU - Tang, Yucheng

AU - Ihsani, Alvin

AU - Asad, Muhammad

AU - Pérez-García, Fernando

AU - Mehta, Pritesh

AU - Li, Wenqi

AU - Flores, Mona

AU - Roth, Holger R.

AU - Vercauteren, Tom

AU - Xu, Daguang

AU - Dogra, Prerna

AU - Ourselin, Sebastien

AU - Feng, Andrew

AU - Cardoso, M. Jorge

PY - 2024/7

Y1 - 2024/7

N2 - The lack of annotated datasets is a major bottleneck for training new task-specific supervised machine learning models, considering that manual annotation is extremely expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source framework that facilitates the development of applications based on artificial intelligence (AI) models that aim at reducing the time required to annotate radiology datasets. Through MONAI Label, researchers can develop AI annotation applications focusing on their domain of expertise. It allows researchers to readily deploy their apps as services, which can be made available to clinicians via their preferred user interface. Currently, MONAI Label readily supports locally installed (3D Slicer) and web-based (OHIF) frontends and offers two active learning strategies to facilitate and speed up the training of segmentation algorithms. MONAI Label allows researchers to make incremental improvements to their AI-based annotation application by making them available to other researchers and clinicians alike. Additionally, MONAI Label provides sample AI-based interactive and non-interactive labeling applications, that can be used directly off the shelf, as plug-and-play to any given dataset. Significant reduced annotation times using the interactive model can be observed on two public datasets.

AB - The lack of annotated datasets is a major bottleneck for training new task-specific supervised machine learning models, considering that manual annotation is extremely expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source framework that facilitates the development of applications based on artificial intelligence (AI) models that aim at reducing the time required to annotate radiology datasets. Through MONAI Label, researchers can develop AI annotation applications focusing on their domain of expertise. It allows researchers to readily deploy their apps as services, which can be made available to clinicians via their preferred user interface. Currently, MONAI Label readily supports locally installed (3D Slicer) and web-based (OHIF) frontends and offers two active learning strategies to facilitate and speed up the training of segmentation algorithms. MONAI Label allows researchers to make incremental improvements to their AI-based annotation application by making them available to other researchers and clinicians alike. Additionally, MONAI Label provides sample AI-based interactive and non-interactive labeling applications, that can be used directly off the shelf, as plug-and-play to any given dataset. Significant reduced annotation times using the interactive model can be observed on two public datasets.

KW - 3D medical imaging

KW - Active learning

KW - Deep learning

KW - Interactive 3D image segmentation

UR - http://www.scopus.com/inward/record.url?scp=85193484576&partnerID=8YFLogxK

U2 - 10.1016/j.media.2024.103207

DO - 10.1016/j.media.2024.103207

M3 - Article

AN - SCOPUS:85193484576

SN - 1361-8415

VL - 95

JO - Medical Image Analysis

JF - Medical Image Analysis

M1 - 103207

ER -

MONAI Label: A framework for AI-assisted interactive labeling of 3D medical images

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this