NCI Imaging Data Commons

Fedorov, Andrey; Longabaugh, William J.R.; Pot, David; Clunie, David A.; Pieper, Steve; Aerts, Hugo J.W.L.; Homeyer, André; Lewis, Rob; Akbarzadeh, Afshin; Bontempi, Dennis; Clifford, William Kingdon; Herrmann, Markus D.; Höfener, Henning; Octaviano, Igor; Osborne, Chad; Paquette, Suzanne; Petts, James; Punzo, Davide; Reyes, Madelyn; Schacherer, Daniela P.; Mi, Tian; White, G. Edward; Ziegler, Erik; Shmulevich, Ilya; Pihl, Todd; Wagner, U; Farahani, Keyvan; Kikinis, Ron

doi:10.1158/0008-5472.can-21-0950

Cited by 57 publications

(41 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We further show that data can be exchanged and stored using DICOM-compatible image management systems, which already exist in hospitals worldwide and are increasingly being adopted by biomedical imaging research initiatives around the world. For example, the National Cancer Institute's Imaging Data Commons (IDC) in the USA will make large public collections of pathology and radiology images, image annotations, and image analysis results available in DICOM format [52]. The highdicom library will allow researchers to leverage these resources and enable them to readily share their results and make them usable by other researchers.…”

Section: Common Platforms Services and Tools Will Facilitate Enterpri...mentioning

confidence: 99%

Highdicom: a Python Library for Standardized Encoding of Image Annotations and Machine Learning Model Outputs in Pathology and Radiology

Bridge

Gorman

Pieper³

et al. 2022

J Digit Imaging

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) is revolutionizing image-based diagnostics in pathology and radiology. ML models have shown promising results in research settings, but the lack of interoperability between ML systems and enterprise medical imaging systems has been a major barrier for clinical integration and evaluation. The DICOM® standard specifies information object definitions (IODs) and services for the representation and communication of digital images and related information, including image-derived annotations and analysis results. However, the complexity of the standard represents an obstacle for its adoption in the ML community and creates a need for software libraries and tools that simplify working with datasets in DICOM format. Here we present the highdicom library, which provides a high-level application programming interface (API) for the Python programming language that abstracts low-level details of the standard and enables encoding and decoding of image-derived information in DICOM format in a few lines of Python code. The highdicom library leverages NumPy arrays for efficient data representation and ties into the extensive Python ecosystem for image processing and machine learning. Simultaneously, by simplifying creation and parsing of DICOM-compliant files, highdicom achieves interoperability with the medical imaging systems that hold the data used to train and run ML models, and ultimately communicate and store model outputs for clinical use. We demonstrate through experiments with slide microscopy and computed tomography imaging, that, by bridging these two ecosystems, highdicom enables developers and researchers to train and evaluate state-of-the-art ML models in pathology and radiology while remaining compliant with the DICOM standard and interoperable with clinical systems at all stages. To promote standardization of ML research and streamline the ML model development and deployment process, we made the library available free and open-source at https://github.com/herrmannlab/highdicom.

show abstract

Section: Common Platforms Services and Tools Will Facilitate Enterpri...mentioning

confidence: 99%

Highdicom: a Python Library for Standardized Encoding of Image Annotations and Machine Learning Model Outputs in Pathology and Radiology

Bridge

Gorman

Pieper³

et al. 2022

J Digit Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…We further show that data can be exchanged and stored using DICOM-compatible image management systems, which already exist in hospitals worldwide and are increasingly being adopted by biomedical imaging research initiatives around the world. For example, the National Cancer Institute's Imaging Data Commons (IDC) in the United States will make large public collections of pathology and radiology images, image annotations, and image analysis results available in DICOM format [49]. The highdicom library will allow researchers to leverage these resources and enable them to readily share their results and make them usable by other researchers.…”

Section: Scaling To Large Numbers Of Image Annotations or Model Outpu...mentioning

confidence: 99%

Highdicom: A Python library for standardized encoding of image annotations and machine learning model outputs in pathology and radiology

Bridge¹,

Gorman²,

Pieper³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) is revolutionizing image-based diagnostics in pathology and radiology. ML models have shown promising results in research settings, but the lack of interoperability between ML systems and enterprise medical imaging systems has been a major barrier for clinical integration and evaluation. The DICOM ® standard specifies Information Object Definitions (IODs) and Services for the representation and communication of digital images and related information, including image-derived annotations and analysis results. However, the complexity of the standard represents an obstacle for its adoption in the ML community and creates a need for software libraries and tools that simplify working with data sets in DICOM format.Here we present the highdicom library, which provides a high-level application programming interface (API) for the Python programming language that abstracts low-level details of the standard and enables encoding and decoding of image-derived information in DICOM format in a few lines of Python code. The highdicom library leverages NumPy arrays for efficient data representation and ties into the extensive Python ecosystem for image processing and machine learning. Simultaneously, by simplifying creation and parsing of DICOM-compliant files, highdicom achieves interoperability with the medical imaging systems that hold the data used to train and run ML models, and ultimately communicate and store model outputs for clinical use. We demonstrate through experiments with slide microscopy and computed tomography imaging, that, by bridging these two ecosystems, highdicom enables developers and researchers to train and evaluate state-of-the-art ML models in pathology and radiology while remaining compliant with the DICOM standard and interoperable with clinical systems at all stages.To promote standardization of ML research and streamline the ML model development and deployment process, we made the library available free and open-source at https://github.c om/mghcomputationalpathology/highdicom.

show abstract

“…Specifically, it computes aleatoric and epistemic uncertainty values to rank unlabeled images, allowing the clinician/user to segment the harder samples first. It also supports the DICOMweb Standard for webbased medical imaging, enabling users to integrate MONAI Label in their Picture Archiving and Communication System (PACS), XNAT [30], Image Data Commons (IDC) [31] or any other DI-COM system. This feature allows web developers to unlock the power of healthcare images using industry-standard toolsets.…”

Section: Introductionmentioning

confidence: 99%

MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images

Diaz-Pinto¹,

Alle²,

Ihsani³

et al. 2022

Preprint

View full text Add to dashboard Cite

The lack of annotated datasets is a major challenge in training new task-specific supervised AI algorithms as manual annotation is expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source platform that facilitates the development of AI-based applications that aim at reducing the time required to annotate 3D medical image datasets. Through MONAI Label researchers can develop 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 (3DSlicer) 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 labeling apps by making them available to other researchers and clinicians alike. Lastly, MONAI Label provides sample labeling apps, namely DeepEdit and DeepGrow, demonstrating dramatically reduced annotation times.

show abstract

NCI Imaging Data Commons

Cited by 57 publications

References 25 publications

Highdicom: a Python Library for Standardized Encoding of Image Annotations and Machine Learning Model Outputs in Pathology and Radiology

Highdicom: a Python Library for Standardized Encoding of Image Annotations and Machine Learning Model Outputs in Pathology and Radiology

Highdicom: A Python library for standardized encoding of image annotations and machine learning model outputs in pathology and radiology

MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images

Contact Info

Product

Resources

About