Print This Page

Slide 1
SPIE Medical Imaging Conference
Lung Imaging Database Consortium (LIDC)
LIDC Data Elements and Data Collection Process
February 13, 2005

Slide 2
The Database

• The Database will contain:
  1. A collection of CT scan images

Slide 3-8
Low Dose Lung Cancer Screen CTs - illustrate with a series of images; the last image shows the lesion

Slide 9
The Database

• CT scan image data
  1. Low Dose, Full Chest Lung Cancer Screening CTs
  2. Conventional Dose, Full Chest CTs (Retrospective Cases, e.g. Lung Ca Patients)
  3. Conventional Dose, Limited Chest CTs (e.g. Scan of a single nodule; biopsy)
• All image data in DICOM format
• Indexing to identify cases of each type

Slide 10
The database will contain:

1. A collection of CT scan images
2. Technical factors about the CT scan

Slide 11

• Technical factors about the CT scan
  • All Image data will be anonymized
  • Much of DICOM header info will be preserved and stored along with image data
  • Database fields (can be queried) will have Non-patient information from DICOM header

Slide 12

• Technical factors about the CT scan
  • Technical factors such as:
    • kVp
    • Tube current
    • Rotation time
    • Exposure
    • Reconstructed slice thickness and slice location (will still have to calc. spacing)
    • Reconstruction algorithm
    • Reconstructed field of view, pixel size
• Content in private fields WILL BE removed

Slide 13

• The database will contain:
  1. A collection of CT scan images
  2. Technical factors about the CT scan
  3. Nodule Markings and Descriptions

Slide 14

• Nodule Markings and Descriptions
  1. For Nodules > 3 mm diameter
     • Radiologist drawn boundaries
     • Description of characteristics (from defined list)
  2. For Nodules
     • Radiologist marks only centroid
     • No description characteristics

Slide 15
Nodule Marking: Initial Approach

• Multiple Reads with Multiple Readers
  • First Read - 4 readers, each reads independently (Blinded)
  • Compile 4 blinded reads and distribute to readers
  • Second Read - Same 4 readers, this time unblinded to the results of the other readers from the first reading.
  • No forced consensus on either location of nodules nor on their boundaries.

Slides 16-20
Blinded reads by 4 readers marking nodules on a CT image

Slides 21-26
Unblinded reads by 4 readers marking nodules on a CT image; same case as previous slides. Final slide shows all the markings.

Slides 28-40
Case 5, Slice 19 Partial CT of the lung image, with the blinded and unblinded reads by 4 readers using 3 marking methods

Slides 41-42
The marked nodule showing probability of being inside the boundary on a gray scale and bounded by an edge.

Slide 43
The Database

• The database will contain:
  1. A collection of CT scan images
  2. Technical factors about the CT scan
  3. Nodule Markings and Descriptions
  4. Pathology results or diagnosis information whenever available

Slide 44
Pathology Information
In those cases in which pathology is available, we will extract from reports:

• Whether histology or cytology was performed
  • If histology, try to establish the cell type according to WHO classifications
  • If cytology, establish whether it was benign or malignant

Slide 45

• If no pathology, other diagnostic information may be substituted when available (such as 2 years Dx F/U with no change in radiographic appearance).
• If neither is available, then case will be used for detection purposes only.

Slide 46
Summary

• LIDC Data Elements
  • Image Data
  • Technical Factors
  • Radiologists' Contours of Nodules
  • • Data Collection Process
• Diagnosis Information where available