DICOM for quantitative imaging biomarker development: a standards based approach to sharing clinical data and structured PET/CT analysis results in head and neck cancer research

Fedorov, Andriy; Clunie, David A.; Ulrich, Ethan; Bauer, Christian; Wahle, Andreas; Brown, Bruce P.; Onken, Michael D.; Riesmeier, Jörg; Pieper, Steve; Kikinis, Ron; Buatti, John M.; Beichel, Reinhard

doi:10.7717/peerj.2057

Cited by 73 publications

(58 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resulting dataset (not just imaging data, but also image annotations and image-derived measurements) is shared as a collection of objects that are encoded using standardized Digital Imaging and Communications in Medicine (DICOM) (ISO 12052:2017) representation 17–19 ( https://www.dicomstandard.org/ ). This continues the precedent we established earlier to utilize standard representation for harmonizing data as applied to quantitative imaging biomarker development 20 .…”

Section: Background and Summarymentioning

confidence: 63%

See 1 more Smart Citation

An annotated test-retest collection of prostate multiparametric MRI

Fedorov

Schwier

Clunie³

et al. 2018

Sci Data

Self Cite

View full text Add to dashboard Cite

Multiparametric Magnetic Resonance Imaging (mpMRI) is widely used for characterizing prostate cancer. Standard of care use of mpMRI in clinic relies on visual interpretation of the images by an expert. mpMRI is also increasingly used as a quantitative imaging biomarker of the disease. Little is known about repeatability of such quantitative measurements, and no test-retest datasets have been available publicly to support investigation of the technical characteristics of the MRI-based quantification in the prostate. Here we present an mpMRI dataset consisting of baseline and repeat prostate MRI exams for 15 subjects, manually annotated to define regions corresponding to lesions and anatomical structures, and accompanied by region-based measurements. This dataset aims to support further investigation of the repeatability of mpMRI-derived quantitative prostate measurements, study of the robustness and reliability of the automated analysis approaches, and to support development and validation of new image analysis techniques. The manuscript can also serve as an example of the use of DICOM for standardized encoding of the image annotation and quantification results.

show abstract

Section: Background and Summarymentioning

confidence: 63%

“…DICOM is the international standard adopted universally by the manufacturers of medical imaging equipment for storing their acquired images. In addition to modality-specific images, DICOM defines multiple types of image-related objects 20 , including the types of data in the present data descriptor.…”

Section: Data Recordsmentioning

confidence: 99%

An annotated test-retest collection of prostate multiparametric MRI

Fedorov

Schwier

Clunie³

et al. 2018

Sci Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…Archive (TCIA) QIN-HEADNECK dataset [3,9,5], which were resampled to isotropic voxels of size 2 × 2 × 2 (mm). The QIN-HEADNECK dataset is originally collected from a set of head and neck cancer patients.…”

Section: Volumetric and 2d Binary Segmentationmentioning

confidence: 99%

Select, Attend, and Transfer: Light, Learnable Skip Connections

Taghanaki

BenTaieb

Sharma

et al. 2019

Machine Learning in Medical Imaging

View full text Add to dashboard Cite

Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients. They equip encoder-decoder-like networks with richer feature representations, but at the cost of higher memory usage, computation, and possibly resulting in transferring non-discriminative feature maps. In this paper, we focus on improving skip connections used in segmentation networks (e.g., U-Net, V-Net, and The One Hundred Layers Tiramisu (DensNet) architectures). We propose light, learnable skip connections which learn to first select the most discriminative channels and then attend to the most discriminative regions of the selected feature maps. The output of the proposed skip connections is a unique feature map which not only reduces the memory usage and network parameters to a high extent, but also improves segmentation accuracy. We evaluate the proposed method on three different 2D and volumetric datasets and demonstrate that the proposed light, learnable skip connections can outperform the traditional heavy skip connections in terms of segmentation accuracy, memory usage, and number of network parameters.Preprint. Work in progress.

show abstract

“…DICOM does provide various generic solutions for annotations, including segmentations, presentation states and structured reports, which are used in other specialties where quantitation is a requirement. [ 30 ] Which choices, for which use cases, and how scalable the existing DICOM solutions will be for very large numbers of annotations, remains to be seen. If necessary, DICOM can add WSI-specific annotation features.…”

Section: F Inal T Houghtsmentioning

confidence: 99%

Digital Imaging and Communications in Medicine Whole Slide Imaging Connectathon at Digital Pathology Association Pathology Visions 2017

Clunie¹,

Hosseinzadeh²,

Wintell

et al. 2018

Journal of Pathology Informatics

Self Cite

View full text Add to dashboard Cite

As digital pathology systems for clinical diagnostic work applications become mainstream, interoperability between these systems from different vendors becomes critical. For the first time, multiple digital pathology vendors have publicly revealed the use of the digital imaging and communications in medicine (DICOM) standard file format and network protocol to communicate between separate whole slide acquisition, storage, and viewing components. Note the use of DICOM for clinical diagnostic applications is still to be validated in the United States. The successful demonstration shows that the DICOM standard is fundamentally sound, though many lessons were learned. These lessons will be incorporated as incremental improvements in the standard, provide more detailed profiles to constrain variation for specific use cases, and offer educational material for implementers. Future Connectathon events will expand the scope to include more devices and vendors, as well as more ambitious use cases including laboratory information system integration and annotation for image analysis, as well as more geographic diversity. Users should request DICOM features in all purchases and contracts. It is anticipated that the growth of DICOM-compliant manufacturers will likely also ease DICOM for pathology becoming a recognized standard and as such the regulatory pathway for digital pathology products.

show abstract

DICOM for quantitative imaging biomarker development: a standards based approach to sharing clinical data and structured PET/CT analysis results in head and neck cancer research

Cited by 73 publications

References 37 publications

An annotated test-retest collection of prostate multiparametric MRI

An annotated test-retest collection of prostate multiparametric MRI

Select, Attend, and Transfer: Light, Learnable Skip Connections

Digital Imaging and Communications in Medicine Whole Slide Imaging Connectathon at Digital Pathology Association Pathology Visions 2017

Contact Info

Product

Resources

About