Observations from the Data Integration and Imaging Informatics (DI-Cubed) Project

In this paper we explore extending the concept of common cross-study Common Data Element concepts beyond simple demographics to cover disease-specific concepts relevant to imaging. We test interactively linking the resulting database to the associated images in a federated manner. We examine the use of existing standards, not only for terminology, but for interchange of serialized data in forms familiar to imaging and clinical trials specialists and their dedicated systems. Our intent is to perform preliminary work to inform both the upcoming Imaging Data Commons specifically, as well as more general integration projects beyond imaging.

Download Full-text

Quantitative Imaging Informatics for Cancer Research

JCO Clinical Cancer Informatics ◽

10.1200/cci.19.00165 ◽

2020 ◽

pp. 444-453 ◽

Cited By ~ 1

Author(s):

Andrey Fedorov ◽

Reinhard Beichel ◽

Jayashree Kalpathy-Cramer ◽

David Clunie ◽

Michael Onken ◽

...

Keyword(s):

Cancer Research ◽

Best Practices ◽

Cancer Imaging ◽

Quantitative Imaging ◽

Imaging Informatics ◽

Imaging Data ◽

Communication Interface ◽

3D Slicer ◽

And Training ◽

Data Commons

PURPOSE We summarize Quantitative Imaging Informatics for Cancer Research (QIICR; U24 CA180918), one of the first projects funded by the National Cancer Institute (NCI) Informatics Technology for Cancer Research program. METHODS QIICR was motivated by the 3 use cases from the NCI Quantitative Imaging Network. 3D Slicer was selected as the platform for implementation of open-source quantitative imaging (QI) tools. Digital Imaging and Communications in Medicine (DICOM) was chosen for standardization of QI analysis outputs. Support of improved integration with community repositories focused on The Cancer Imaging Archive (TCIA). Priorities included improved capabilities of the standard, toolkits and tools, reference datasets, collaborations, and training and outreach. RESULTS Fourteen new tools to support head and neck cancer, glioblastoma, and prostate cancer QI research were introduced and downloaded over 100,000 times. DICOM was amended, with over 40 correction proposals addressing QI needs. Reference implementations of the standard in a popular toolkit and standalone tools were introduced. Eight datasets exemplifying the application of the standard and tools were contributed. An open demonstration/connectathon was organized, attracting the participation of academic groups and commercial vendors. Integration of tools with TCIA was improved by implementing programmatic communication interface and by refining best practices for QI analysis results curation. CONCLUSION Tools, capabilities of the DICOM standard, and datasets we introduced found adoption and utility within the cancer imaging community. A collaborative approach is critical to addressing challenges in imaging informatics at the national and international levels. Numerous challenges remain in establishing and maintaining the infrastructure of analysis tools and standardized datasets for the imaging community. Ideas and technology developed by the QIICR project are contributing to the NCI Imaging Data Commons currently being developed.

Download Full-text

Development of a Flexible Imaging Data Integration Tool for Multicenter Clinical Trials

Proceedings of the 2nd International Conference on Medical and Health Informatics - ICMHI '18 ◽

10.1145/3239438.3239449 ◽

2018 ◽

Author(s):

Jingyi Shi ◽

Jeff Carr ◽

Yaorong Ge

Keyword(s):

Clinical Trials ◽

Data Integration ◽

Imaging Data ◽

Flexible Imaging ◽

Multicenter Clinical Trials

Download Full-text

Incorporating radiomics into clinical trials: expert consensus on considerations for data-driven compared to biologically driven quantitative biomarkers

European Radiology ◽

10.1007/s00330-020-07598-8 ◽

2021 ◽

Author(s):

Laure Fournier ◽

Lena Costaridou ◽

Luc Bidaut ◽

Nicolas Michoux ◽

Frederic E. Lecouvet ◽

...

Keyword(s):

Clinical Trials ◽

Quantitative Imaging ◽

A Priori ◽

External Validation ◽

Data Driven ◽

Imaging Biomarkers ◽

Clinical Validation ◽

Biological Processes ◽

Imaging Data ◽

Selection Of

Abstract Existing quantitative imaging biomarkers (QIBs) are associated with known biological tissue characteristics and follow a well-understood path of technical, biological and clinical validation before incorporation into clinical trials. In radiomics, novel data-driven processes extract numerous visually imperceptible statistical features from the imaging data with no a priori assumptions on their correlation with biological processes. The selection of relevant features (radiomic signature) and incorporation into clinical trials therefore requires additional considerations to ensure meaningful imaging endpoints. Also, the number of radiomic features tested means that power calculations would result in sample sizes impossible to achieve within clinical trials. This article examines how the process of standardising and validating data-driven imaging biomarkers differs from those based on biological associations. Radiomic signatures are best developed initially on datasets that represent diversity of acquisition protocols as well as diversity of disease and of normal findings, rather than within clinical trials with standardised and optimised protocols as this would risk the selection of radiomic features being linked to the imaging process rather than the pathology. Normalisation through discretisation and feature harmonisation are essential pre-processing steps. Biological correlation may be performed after the technical and clinical validity of a radiomic signature is established, but is not mandatory. Feature selection may be part of discovery within a radiomics-specific trial or represent exploratory endpoints within an established trial; a previously validated radiomic signature may even be used as a primary/secondary endpoint, particularly if associations are demonstrated with specific biological processes and pathways being targeted within clinical trials. Key Points • Data-driven processes like radiomics risk false discoveries due to high-dimensionality of the dataset compared to sample size, making adequate diversity of the data, cross-validation and external validation essential to mitigate the risks of spurious associations and overfitting. • Use of radiomic signatures within clinical trials requires multistep standardisation of image acquisition, image analysis and data mining processes. • Biological correlation may be established after clinical validation but is not mandatory.

Download Full-text

Sensor, Signal, and Imaging Informatics

Yearbook of Medical Informatics ◽

10.15265/iy-2017-019 ◽

2017 ◽

Vol 26 (01) ◽

pp. 120-124

Author(s):

W. Hsu ◽

S. Park ◽

Charles Kahn

Keyword(s):

Medical Informatics ◽

Scientific Work ◽

Imaging Informatics ◽

Sensor Signal ◽

Imaging Data ◽

Extensive Search ◽

Challenges And Opportunities ◽

Final Selection ◽

Selection Of

Summary Objective: To summarize significant contributions to sensor, signal, and imaging informatics published in 2016. Methods: We conducted an extensive search using PubMed® and Web of Science® to identify the scientific contributions published in 2016 that addressed sensors, signals, and imaging in medical informatics. The three section editors selected 15 candidate best papers by consensus. Each candidate article was reviewed by the section editors and at least two other external reviewers. The final selection of the six best papers was conducted by the editorial board of the Yearbook. Results: The selected papers of 2016 demonstrate the important scientific advances in management and analysis of sensor, signal, and imaging information. Conclusion: The growing volume of signal and imaging data provides exciting new challenges and opportunities for research in medical informatics. Evolving technologies provide faster and more effective approaches for pattern recognition and diagnostic evaluation. The papers selected here offer a small glimpse of the high-quality scientific work published in 2016 in the domain of sensor, signal, and imaging informatics.

Download Full-text

Applicability of a Web-Based, Individualized Exercise Intervention in Patients With Liver Disease, Cystic Fibrosis, Esophageal Cancer, and Psychiatric Disorders: Process Evaluation of 4 Ongoing Clinical Trials (Preprint)

10.2196/preprints.8607 ◽

2017 ◽

Author(s):

Daniel Pfirrmann ◽

Nils Haller ◽

Yvonne Huber ◽

Patrick Jung ◽

Klaus Lieb ◽

...

Keyword(s):

Physical Activity ◽

Cystic Fibrosis ◽

Clinical Trials ◽

Liver Disease ◽

Activity Level ◽

Daily Routine ◽

Intervention Period ◽

Web Based ◽

Significant Change ◽

Disease Specific

BACKGROUND In the primary and secondary prevention of civilization diseases, regular physical activity is recommended in international guidelines to improve disease-related symptoms, delay the progression of the disease, or to enhance postoperative outcomes. In the preoperative context, there has been a paradigm shift in favor of using preconditioning concepts before surgery. Web-based interventions seem an innovative and effective tool for delivering general information, individualized exercise recommendations, and peer support. OBJECTIVE Our first objective was to assess feasibility of our Web-based interventional concept and analyze similarities and differences in a sustained exercise implementation in different diseases. The second objective was to investigate the overall participants’ satisfaction with our Web-based concept. METHODS A total of 4 clinical trials are still being carried out, including patients with esophageal carcinoma scheduled for oncologic esophagectomy (internet-based perioperative exercise program, iPEP, study), nonalcoholic fatty liver disease (hepatic inflammation and physical performance in patients with nonalcoholic steatohepatitis, HELP, study), depression (exercise for depression, EXDEP, study), and cystic fibrosis (cystic fibrosis online mentoring for microbiome, exercise, and diet, COMMED, study). During the intervention period, the study population had access to the website with disease-specific content and a disease-specific discussion forum. All participants received weekly, individual tailored exercise recommendations from the sports therapist. The main outcome was the using behavior, which was obtained by investigating the log-in rate and duration. RESULTS A total of 20 participants (5 from each trial) were analyzed. During the intervention period, a regular contact and a consequent implementation of exercise prescription were easily achieved in all substudies. Across the 4 substudies, there was a significant decrease in log-in rates (P<.001) and log-in durations (P<.001) over time. A detailed view of the different studies shows a significant decrease in log-in rates and log-in durations in the HELP study (P=.004; P=.002) and iPEP study (P=.02; P=.001), whereas the EXDEP study (P=.58; P=.38) and COMMED study (P=.87; P=.56) showed no significant change over the 8-week intervention period. There was no significant change in physical activity within all studies (P=.31). Only in the HELP study, the physical activity level increased steadily over the period analyzed (P=.045). Overall, 17 participants (85%, 17/20) felt secure and were not scared of injury, with no major differences in the subtrials. CONCLUSIONS The universal use of the Web-based intervention appears to be applicable across the heterogonous collectives of our study patients with regard to age and disease. Although the development of physical activity shows only moderate improvements, flexible communication and tailored support could be easily integrated into patients’ daily routine. CLINICALTRIAL iPEP study: ClinicalTrials.gov NCT02478996; https://clinicaltrials.gov/ct2/show/NCT02478996 (Archived by WebCite at http://www.webcitation.org/6zL1UmHaW); HELP study: ClinicalTrials.gov NCT02526732; http://www.webcitation.org/6zJjX7d6K (Archived by WebCite at http://www.webcitation.org/6Nch4ldcL); EXDEP study: ClinicalTrials.gov NCT02874833; https://clinicaltrials.gov/ct2/show/NCT02874833 (Archived by WebCite at http://www.webcitation.org/6zJjj7FuA)

Download Full-text

Disparities in government and nonprofit organization funding may hinder clinical trial development for underfunded cancers.

Journal of Clinical Oncology ◽

10.1200/jco.2021.39.15_suppl.1573 ◽

2021 ◽

Vol 39 (15_suppl) ◽

pp. 1573-1573

Author(s):

Suneel Deepak Kamath

Keyword(s):

Clinical Trial ◽

Clinical Trials ◽

Pearson Correlation ◽

Nonprofit Organization ◽

Correlation Coefficients ◽

Descriptive Statistics ◽

Incidence And Mortality ◽

High Incidence ◽

Uterine Cancers ◽

Disease Specific

1573 Background: National Cancer Institute (NCI) and nonprofit organization (NPO) funding is critical for research and advocacy, but may not be equitable across cancers. This could negatively impact clinical trial development for underfunded cancers. Methods: This study evaluated funding from the NCI and NPOs with > $5 million in annual revenue supporting leukemia, lymphoma, melanoma, lung, breast, colorectal, pancreatic, hepatobiliary, prostate, ovarian, cervical and endometrial cancers from 2015-2018 based on publically available reports and tax records. The primary objectives were to assess for disparities in NCI and NPO funding across different cancers compared to their median incidence and mortality from 2015-2018, and to determine if underfunding correlates with fewer clinical trials found in clinicaltrials.gov. Correlations between combined NCI and NPO funding for each cancer and its incidence, mortality and number of clinical trials were evaluated using descriptive statistics and Pearson correlation coefficients. Results: Diseases with the largest combined NCI+NPO funding were breast ($3.75 billion), leukemia ($1.99 billion) and lung cancer ($1.56 billion). Those with the least funding were endometrial ($94 million), cervical ($292 million), and hepatobiliary cancers ($348 million). These data are summarized in the Table. Disease-specific NCI+NPO funding correlated well with incidence, but less so with mortality (Pearson correlation coefficients: 0.74 and 0.63, respectively). Disease-specific NPO funding correlated moderately well with incidence, but was poorly correlated with mortality (Pearson correlation coefficients: 0.54 and 0.39, respectively). Breast cancer, leukemia and lymphoma were consistently well-funded compared to their incidence and mortality, while colorectal, lung, hepatobiliary and uterine cancers were consistently underfunded. The amount of NCI funding, NPO funding and combined NCI+NPO funding for a particular cancer each correlated strongly with the number of clinical trials for that disease (Pearson correlation coefficients: 0.88, 0.87 and 0.91, respectively). Conclusions: Many cancers with high incidence and mortality are underfunded. Cancers with higher mortality rates receive less funding, particularly from NPOs. Underfunding strongly correlates with fewer clinical trials, which could impede future advances in underfunded cancers.[Table: see text]

Download Full-text