マンモグラフィ読影用人工知能モデルのバージョン別性能比較

Marthe Larsen¹, Christoph I Lee², Marie B Bergan¹

¹Department of Breast Cancer Screening, The Cancer Registry, Norwegian Institute of Public Health, Oslo, Norway.

European radiology

|January 13, 2026

要旨

Objectives:

Studies have reported promising results regarding artificial intelligence (AI) as a tool for improved mammographic screening interpretive performance. We analyzed AI malignancy risk scores from two versions of the same commercial AI model.

Materials And Methods:

This retrospective cohort study used data from 117,709 screening examinations performed in BreastScreen Norway 2009-2018. The mammograms were processed by two versions of the commercially available AI model, Transpara (version 1.7 and 2.1). The distributions of exam-level risk scores (AI score 1-10) and risk categories were evaluated for both AI versions on all examinations, including 737 screen-detected and 200 interval cancers. Scores between 1-7 were categorized as low risk, 8-9 as intermediate risk, and 10 as high risk of malignancy.

Results:

Area under the receiver operating curve was 0.908 (95% CI: 0.986-0.920) for version 1.7 and 0.928 (95% CI: 0.917-0.939) for 2.1 when screen-detected and interval cancers were considered as positive cases (p < 0.001). A total of 87.1% (642/737) and 93.5% (689/737) of the screen-detected cancers had an AI score of 10 with version 1.7 and 2.1, respectively. Among interval cancers, 45.0% (90/200) had AI score 10 with version 1.7 and 44.5% (89/200) had AI score 10 with version 2.1.

Conclusion:

A higher proportion of screen-detected breast cancers had the highest AI score of 10 with the newer version of the AI model compared to the older version. For interval cancers, there was no difference in the proportion of cases assigned to the highest score between the two versions.

Key Points:

Question Studies have reported promising results regarding the use of AI in mammography screening, but comparisons of updated versus older versions are less studied. Findings In our study, 87.1% (642/737) of the screen-detected cancers were classified with a high malignancy risk score by the old version, while it was 93.5% (689/737) for the newer version. Clinical relevance Understanding how version updates of AI models might impact screening mammography performance will be important for future quality assurance and validation of AI models.

キーワード:

人工知能乳がんマンモグラフィスクリーニング

さらに関連する動画

07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.4K

関連する概念動画

01:13

Multiple Comparison Tests

Multiple comparison test, abbreviated as MCT, is a post hoc analysis generally performed after comparing multiple samples with one or more tests. An MCT will help identify a significantly different sample among multiple samples or a factor among multiple factors.
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...

01:14

Mechanical Efficiency of Real Machines

The mechanical efficiency of a machine is a fundamental concept that describes how effectively a machine can convert input work into output work. According to this concept, the efficiency of a machine is equal to the ratio of the output work to the input work. An ideal machine, meaning a machine that has no energy losses, has an efficiency of one. This implies that the input work and the output work are equal.
However, in reality, no machine can be truly ideal, and all of them experience some...