Order from Lab 7C362B

Radiology scans

De-identified CT, MRI and mammography studies as original DICOM, each with the signed radiologist report and, for a large share, the diagnosis confirmed later (pathology, surgery or 12-month follow-up) with its source and date. We have scans with reports; we are short of scans where we know what the patient really had.

How answering works

Any number of people fill one order. The lab receives one dataset, in its own columns.

Your agent reads the order
It looks at what you hold and says which columns you can fill, and what is missing.
Mora checks what you send
Every record: no copies, no personal data, not already public, not on Mora from someone else.
The lab pays per record it accepts
The lab named the price. You fill as much of the order as you can.

The columns the lab wants

You do not need every column. Mora says which ones each dataset fills.

Column Type What it must hold

patient_id id Generated id, the same patient keeps one id across all studies and sites

site_id id Hospital or imaging centre, generated id, with country and kind of site

study_id id One exam; re-hashed StudyInstanceUID

dicom_series DICOM files Full series, original 12 to 16 bit pixel data, lossless; no PNG or JPEG exports

modality label CT, MR, MG, DX, read from the DICOM header

body_part label Body part examined, from the header

manufacturer_model text Scanner maker and model, slice thickness, contrast, from the header

study_date_shifted date Date shifted per patient, intervals between studies kept

age_band label Age in 5-year bands

sex label Patient sex

report_text text Signed final report, findings and impression, de-identified, original language

report_status label Preliminary, final or addendum

radiologist_id id Who signed the report, generated id

confirmed_diagnosis label What the patient really had, ICD-10 or SNOMED code

confirmation_source label Histopathology, surgery, follow-up imaging or clinical discharge

days_to_confirmation number Days from scan to confirmation; proves the answer came after the scan

negative_followup_months number For a normal scan: months of follow-up without disease, 12 at least

Column	Type	What it must hold
`patient_id`	id	Generated id, the same patient keeps one id across all studies and sites
`site_id`	id	Hospital or imaging centre, generated id, with country and kind of site
`study_id`	id	One exam; re-hashed StudyInstanceUID
`dicom_series`	DICOM files	Full series, original 12 to 16 bit pixel data, lossless; no PNG or JPEG exports
`modality`	label	CT, MR, MG, DX, read from the DICOM header
`body_part`	label	Body part examined, from the header
`manufacturer_model`	text	Scanner maker and model, slice thickness, contrast, from the header
`study_date_shifted`	date	Date shifted per patient, intervals between studies kept
`age_band`	label	Age in 5-year bands
`sex`	label	Patient sex
`report_text`	text	Signed final report, findings and impression, de-identified, original language
`report_status`	label	Preliminary, final or addendum
`radiologist_id`	id	Who signed the report, generated id
`confirmed_diagnosis`	label	What the patient really had, ICD-10 or SNOMED code
`confirmation_source`	label	Histopathology, surgery, follow-up imaging or clinical discharge
`days_to_confirmation`	number	Days from scan to confirmation; proves the answer came after the scan
`negative_followup_months`	number	For a normal scan: months of follow-up without disease, 12 at least

How much, in the lab's words

250,000 studies from about 150,000 patients (CT, MRI, mammography), at least 5 hospitals and 3 scanner makers, every study with a final report, at least 75,000 studies with a confirmed diagnosis. Roughly 50 TB of DICOM.

studies
images
reports
outcomes
annotations
priors
rights