Standardized representation of the LIDC annotations using DICOM

Abstract

The Lung Imaging Data Consortium and Image Database Resource Initiative (LIDC) conducted a multi-site reader study that produced a comprehensive database of Computed Tomography (CT) scans for over 1000 subjects annotated by multiple expert readers. The result is hosted in the LIDC-IDRI collection of The Cancer Imaging Archive (TCIA). Annotations that accompany the images of the collection are stored using project-specific XML representation. This complicates their reuse, since no general-purpose tools are available to visualize or query those objects, and makes harmonization with other similar type of data non-trivial. To make the LIDC dataset more FAIR (Findable, Accessible, Interoperable, Reusable) to the research community, we prepared their standardized representation using the Digital Imaging and Communications in Medicine (DICOM) standard. This manuscript is intended to serve as a companion to the dataset to facilitate its reuse.

DICOM re‐encoding of volumetrically annotated Lung Imaging Database Consortium (LIDC) nodules

“…Both DICOM CT images and XML files are publicly shared in the TCIA LIDC‐IDRI collection 6 . The DICOM dataset presented in this manuscript and containing the DICOM encoded annotations is available on TCIA at https://doi.org/10.7937/TCIA.2018.h7umfurq 20 …”

“…This work makes use of tools developed earlier for interpreting XML annotations of LIDC 13 and for generating the standardized DICOM representations for image analysis results 17,18 . A preprint describing this approach and dataset appeared earlier 19 …”

“…6 The DICOM dataset presented in this manuscript and containing the DICOM encoded annotations is available on TCIA at https://doi.org/10.7937/TCIA.2018.h7umfurq. 20 An understanding of the content of XML annotations produced by the LIDC initiative can be gained through the peerreviewed manuscripts published by the initiative, [3][4][5] and the documentation linked from the TCIA LIDC-IDRI collection page. 6 Briefly, the initiative distinguished between the three groups of findings, as defined by Armato et al 5 : "(a) "nodules ≥ 3 mm" (defined as any lesion considered to be a nodule with greatest in-plane dimension in the range 3-30 mm regardless of presumed histology); (b) "nodules < 3 mm" (defined as any lesion considered to be a nodule with greatest in-plane dimension <3 mm that is not clearly benign); and (c) "non-nodules ≥ 3 mm" any other pulmonary lesion, such as an apical scar, with greatest in-plane dimension greater than or equal to 3 mm that does not possess features consistent with those of a nodule)".…”

Lung Cancer Detection Based on CT Scan Images by Using Deep Transfer Learning

“…To improve research and development activities, the Lung Image Database Consortium (LIDC) [18] was initiated by the National Cancer Institute (NCI). The LIDC database was created with three categories of objects to be marked by four radiologists: Nodules greater than or equal to 3 mm in diameter, of presumed histology, Nodules less than 3 mm in diameter of an indeterminate nature, non-Nodules that are less than 3 mm but are benign.…”

DICOM re‐encoding of volumetrically annotated Lung Imaging Database Consortium (LIDC) nodules

“…6 The DICOM dataset presented in this manuscript and containing the DICOM encoded annotations is available on TCIA at https://doi.org/10.7937/TCIA.2018.h7umfurq. 20 An understanding of the content of XML annotations produced by the LIDC initiative can be gained through the peerreviewed manuscripts published by the initiative, [3][4][5] and the documentation linked from the TCIA LIDC-IDRI collection page. 6 Briefly, the initiative distinguished between the three groups of findings, as defined by Armato et al 5 : "(a) "nodules ≥ 3 mm" (defined as any lesion considered to be a nodule with greatest in-plane dimension in the range 3-30 mm regardless of presumed histology); (b) "nodules < 3 mm" (defined as any lesion considered to be a nodule with greatest in-plane dimension <3 mm that is not clearly benign); and (c) "non-nodules ≥ 3 mm" any other pulmonary lesion, such as an apical scar, with greatest in-plane dimension greater than or equal to 3 mm that does not possess features consistent with those of a nodule)".…”