Second Look would have cut missed breast cancers by at least a quarter

FDA concluded that Second Look's marks would have cut missed cancers on earlier screening mammograms by at least 26.2%. In a prospective test, work-ups rose from 16.6% to 17.2%.

  • Not rated an organization

    The reduction in missed cancers was estimated on past films that no radiologist read with the marks, so no gain at any screening site is measured.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Unaided readings of the same earlier mammograms, which had missed every one of the cancers. Assumed without a measurement.

Without the system
306 retrospectively visible false negatives at most
With it
At least 80.3 of them estimated to be worked up with the marks
The system’s part
All 177 cancers had been missed in unaided reading, and FDA reviewers estimate how many of them the system's marks would have brought to work-up. The estimate rests on panel reads and conservative assumptions. The summary describes pattern recognition algorithms and classifiers but does not say whether they learned from data.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
Second Look
Made by
CADx Medical Systems, Inc. (listed as iCAD, Inc. in the FDA database)
Used by
CADx Medical Systems (ROSE-1 study on earlier screening mammograms from 17 institutions and ROSE-2 study at 5 institutions)
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    U.S. Food and Drug Administration, Center for Devices and Radiological Health. Summary of Safety and Effectiveness Data for Second Look (P010034). Approved 2002-01-31.

    The use of the Second Look™ system on screening mammograms led to a clinically significant reduction in missed cancers (false negatives) of at least 26.2% (95% CI 21.9%, 30.7%).

Details

AI system

Workflow

The system digitized each film with a laser scanner and marked possible calcification clusters with rectangles and possible masses with ellipses. Radiologists read each case in the usual way before they looked at the printed marks.

Follow-up

Conditions for replication

The radiologist completes the initial reading before reviewing the marks. Work-up decisions rest on review of the mammogram and supporting clinical information.

Entry details

Sector

Healthcare.

Purpose

CADx Medical Systems built Second Look to mark regions of interest on screening mammograms so that radiologists look at them again after their first reading.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Second Look would have cut missed breast cancers by at least a quarter (AIBD-0797). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0797.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions