High-throughput image labeling and quality control for clinical trials using machine learning

Simple item page
dc.contributor.authorRobert, J. Harrisen_US
dc.contributor.authorTeng, Pangyuen_US
dc.contributor.authorNagarajan, Maheshen_US
dc.contributor.authorLiza, Shresthaen_US
dc.contributor.authorXiang, Luen_US
dc.contributor.authorRamakrishna, Bharathen_US
dc.contributor.authorPeiyun, Luen_US
dc.contributor.authorTheo, Sanforden_US
dc.contributor.authorHeather, Clemen_US
dc.contributor.authorMegan, McRobertsen_US
dc.contributor.authorGoldin, Jonathanen_US
dc.contributor.authorBrown, Matten_US
dc.date.accessioned2020-05-06T08:32:42Z
dc.date.available2020-05-06T08:32:42Z
dc.date.issued2018-10
dc.description.abstractBackground:Manually importing and analyzing image data can be time-consuming, prone to human error, and costly for large clinical trial datasets. This can lead to delays in quality control (QC) feedback to imaging sites and in obtaining data analysis results. Herein we describe the creation and application of a high-throughput review process for import, classification, labeling and QC of large multimodal clinical trial image datasets.Methods:Automated methods were used to remove patient identifying information, extract image header data, and filter image data for usability. A convolutional neural net was applied to estimate anatomy for CT images. Internal scores were assigned for each image series to identify the optimal series for labeling and reading of each anatomical region. Image QC reports were automatically generated for all patients.Results:In combined studies for which 204,492 series were received, 27,841 series were identified as usable and 13,415 series were labeled. Using this high-throughput method, total work-hours required per time point were reduced by an approximate factor of ten when compared to traditional review and labeling methods. Our anatomic classification system identified 95.7% of image series correctly, with the remaining series being manually corrected before labeling and analysis. Conclusions: A high-throughput image analysis pipeline was implemented in a large combined dataset of clinical trial image series. This pipeline can be applied across other studies and modalities for fast image data characterization, labeling and QC.en_US
dc.identifier.affiliationsMedQIA LLC, Los Angeles, CA, USAen_US
dc.identifier.affiliationsDepartment of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA, USAen_US
dc.identifier.citationRobert J. Harris, Teng Pangyu, Nagarajan Mahesh, Liza Shrestha, Xiang Lu, Ramakrishna Bharath, Peiyun Lu, Theo Sanford, Heather Clem, Megan McRoberts, Goldin Jonathan, Brown Matt. High-throughput image labeling and quality control for clinical trials using machine learning. International Journal of Clinical Trials. 2018 Oct; 5(4): 161-169en_US
dc.identifier.issn2349-3240
dc.identifier.issn2349-3259
dc.identifier.placeIndiaen_US
dc.identifier.urihttps://imsear.searo.who.int/handle/123456789/200902
dc.languageenen_US
dc.publisherMedip Academyen_US
dc.relation.issuenumber4en_US
dc.relation.volume5en_US
dc.source.urihttps://dx.doi.org/10.18203/2349-3259.ijct20184398en_US
dc.subjectImage intakeen_US
dc.subjectHigh-throughputen_US
dc.subjectMachine learningen_US
dc.subjectDICOMen_US
dc.subjectData managemenen_US
dc.titleHigh-throughput image labeling and quality control for clinical trials using machine learningen_US
dc.typeJournal Articleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ijct2018v5n4p161.pdf
Size:
650.1 KB
Format:
Adobe Portable Document Format
Download
Collections
International Journal of Clinical Trials