The SIMP Tool: Facilitating Digital Library, Metadata, and Preservation Workflow at the University of Utah's J. Willard Marriott Library

Neatrour, Anna; Brunsvik, Matt; Buckner, Sean; McBride, Brian; Myntti, Jeremy

doi:10.1045/july2014-neatrour

Cited by 7 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A U-net model was trained over a pretrained EfficientNet encoder using soft dice loss and cross entropy loss. For model encoder, efficient net was used within the Pytorch segmentation libraries [ 39 ]. The model decoder was composed of five up sampling layers after using the default SIMP library [ 39 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease

et al. 2022

View full text Add to dashboard Cite

Organ volume measurements are a key metric for managing ADPKD (the most common inherited renal disease). However, measuring organ volumes is tedious and involves manually contouring organ outlines on multiple cross-sectional MRI or CT images. The automation of kidney contouring using deep learning has been proposed, as it has small errors compared to manual contouring. Here, a deployed open-source deep learning ADPKD kidney segmentation pipeline is extended to also measure liver and spleen volumes, which are also important. This 2D U-net deep learning approach was developed with radiologist labeled T2-weighted images from 215 ADPKD subjects (70% training = 151, 30% validation = 64). Additional ADPKD subjects were utilized for prospective (n = 30) and external (n = 30) validations for a total of 275 subjects. Image cropping previously optimized for kidneys was included in training but removed for the validation and inference to accommodate the liver which is closer to the image border. An effective algorithm was developed to adjudicate overlap voxels that are labeled as more than one organ. Left kidney, right kidney, liver and spleen labels had average errors of 3%, 7%, 3%, and 1%, respectively, on external validation and 5%, 6%, 5%, and 1% on prospective validation. Dice scores also showed that the deep learning model was close to the radiologist contouring, measuring 0.98, 0.96, 0.97 and 0.96 on external validation and 0.96, 0.96, 0.96 and 0.95 on prospective validation for left kidney, right kidney, liver and spleen, respectively. The time required for manual correction of deep learning segmentation errors was only 19:17 min compared to 33:04 min for manual segmentations, a 42% time saving (p = 0.004). Standard deviation of model assisted segmentations was reduced to 7, 5, 11, 5 mL for right kidney, left kidney, liver and spleen respectively from 14, 10, 55 and 14 mL for manual segmentations. Thus, deep learning reduces the radiologist time required to perform multiorgan segmentations in ADPKD and reduces measurement variability.

show abstract

Section: Methodsmentioning

confidence: 99%

“…For model encoder, efficient net was used within the Pytorch segmentation libraries [ 39 ]. The model decoder was composed of five up sampling layers after using the default SIMP library [ 39 ]. After each epoch, validation was performed, saving the best model checkpoints until convergence ( Figure 1 ).…”

Section: Methodsmentioning

confidence: 99%

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Items approved are then uploaded into the SIMP Tool, a system created by the Marriott Library to process content for ingestion into the library's digital asset management and digital preservation systems. The SIMP Tool creates derivatives needed for online display, runs optical character recognition on text files, conducts a fixity check, and assigns an Archival Resource Key as a unique identifier (Neatrour et al, 2014).…”

Section: Dlp 364mentioning

confidence: 99%

Documenting contemporary regional history: the Utah COVID-19 digital collection

Neatrour

Myntti

Wittmann

2020

DLP

Self Cite

View full text Add to dashboard Cite

Purpose When faced with events, such as the global pandemic of coronavirus disease 2019 (COVID-19), libraries have a unique opportunity to develop a community facing response through born-digital collections. These collections provide challenges for metadata creation, collection development policies, workflows, and digital preservation. This paper aims to provide an overview of the Utah COVID-19 digital collection, with a discussion of impact and lessons learned. Design/methodology/approach This paper provides a case study of a born-digital collection initiative undertaken at the University of Utah in response to the COVID-19 pandemic. The project prompted engagement with the University of Utah communities and people across the state. Workflows, metadata management and partnerships are discussed, to provide a model for institutions developing similar projects during a time of crisis. Findings While the project was launched with open-ended and flexible goals, the response from the community has been both surprising and gratifying. Statistics and examples demonstrating reuse of collection materials are provided to highlight the impact and potential of community engagement. Originality/value Digital collecting projects during a historical event are not new, however the restrictions placed upon people worldwide during the COVID-19 pandemic created interesting circumstances for building this collection. Several lessons were learned throughout the project which will be useful for other institutions embarking upon related projects.

show abstract

“…The modular design is functional on many platforms, allowing law libraries the flexibility to adapt to the ever-changing environment of digital library development and the evolving nature of digital preservation systems. (Neatrour et al , 2014).…”

Section: The Submission Information Metadata Packaging Toolmentioning

confidence: 99%

Digital preservation of law reviews: Two ways

Craigle

2017

DLP

View full text Add to dashboard Cite

Purpose This paper will aim to explain two strategies for digital preservation of law reviews, informing law librarians of the options which might best suit their needs. Design/methodology/approach On November 7, 2008, the Durham Statement on Open Access to Legal Scholarship was released to the public. One of its main tenets – that law schools and libraries “stop publishing journals in print format and rely instead on electronic publication coupled with a commitment to keep the electronic versions available in stable, open, digital formats” – was an open call to law libraries to start thinking about digital preservation strategies for their law reviews. The Legal Information Preservation Alliance responded to the need by developing the Law Review Preservation Program, an initiative, which archives law reviews hosted on the Bepress Digital Commons (DC) platform in Controlled LOCKSS (Lots of Copies Keep Stuff Safe) or CLOCKSS. Findings For those law libraries without subscriptions to DC, there is an open-source, freely available alternative solution for ingesting digital law reviews into any preservation platform. This application, called the Submission Information Metadata Packaging, or SIMP tool was developed at the J. Willard Marriott Library at the University of Utah, initially as a solution for ingesting content into the Ex Libris Rosetta Digital preservation platform, as part of a CONTENTdm digital asset management workflow. Though the development of the SIMP tool was inspired by Marriott’s need to ingest digital files from CONTENTdm to Rosetta, they built it to work with any Digital Asset Management System and Digital preservation platform. Originality/value Digital Preservation of law reviews is in its infancy. This is one of the first articles of its kind to provide specific solutions and technical advice for law libraries.

show abstract

The SIMP Tool: Facilitating Digital Library, Metadata, and Preservation Workflow at the University of Utah's J. Willard Marriott Library

Cited by 7 publications

References 0 publications

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease

Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease

Documenting contemporary regional history: the Utah COVID-19 digital collection

Digital preservation of law reviews: Two ways

Contact Info

Product

Resources

About