Impact of Different Mammography Systems on Artificial Intelligence                     Performance in Breast Cancer Screening

Vries, Clarisse F. de; Colosimo, Samantha J.; Staff, Roger T.; Dymiter, Jaroslaw A.; Yearsley, Joseph; Dinneen, Deirdre; Boyle, Moragh; Harrison, David; Anderson, Lesley A.; Lip, Gerald; Black, Corri; Murray, Alison D.; Wilde, Katie; Blackwood, James D.; Butterly, Claire; Zurowski, John; Eilbeck, Jon; McSkimming, Colin

doi:10.1148/ryai.220146

Cited by 18 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As has been demonstrated by Vries et al 4 processing can affect the outcome of AI, even at a level where readers do not detect a difference. It is reasonable to assume that other factors impacting the visual appearance of images or statistical distributions within the image data may similarly impact AI reader performance.…”

Section: Discussionmentioning

confidence: 80%

“…There is some evidence that small changes in image processing, hardly visible to the human eye, impact the effectiveness of AI. 4 AI-software is a blackbox and so it is not known which image features influence the AI decision; potentially these image features could be related to the software and hardware which is used. In addition to image processing there are other differences that could potentially affect the appearance of images and thus AI, such as dose level, changes to the detector design, detector ageing, type of anti-scatter grid or type of compression paddle.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Survey of image processing settings used for mammography systems in the United Kingdom: how variable is it?

Mackenzie,

Loveland,

van Engen

2024

17th International Workshop on Breast Imaging (IWBI 2024)

View full text Add to dashboard Cite

The aim was to undertake a national survey of the setup of mammography imaging systems in the UK, we were particularly interested in image processing and software version. We created a program that can extract selected tags from the DICOM header. 28 medical physics departments used the program on processed images of the TORMAM phantom acquired since 2023 and this produced data for 497 systems. We received data for 7 different models of mammography systems. We found that currently in use each model had between 2 and 7 different versions of software for the acquisition workstation. Each of the systems had multiple versions of image processing settings, a preliminary investigation with TORMAM demonstrated large differences in the appearance of the image for the same x-ray model. The Fujifilm, GE and Siemens systems showed differences in the setup of the dose levels. In addition to these settings there were differences in the paddles used and grid type. Our snapshot of system set up showed that there is a potential for the images to appear differently according to the settings seen in the headers. These differences may affect the outcomes of AI and also human readers. Thus the introduction of AI must take these differences into consideration and the inevitably changes of settings in the future. There are responsibilities on AI suppliers, physics, mammographic equipment manufacturers, and breast-screening units to manage the use of AI and ensure the outcomes of breast screening are not adversely affected by the set-up of equipment.

show abstract

Section: Discussionmentioning

confidence: 80%

Section: Introductionmentioning

confidence: 99%

Survey of image processing settings used for mammography systems in the United Kingdom: how variable is it?

Mackenzie,

Loveland,

van Engen

2024

17th International Workshop on Breast Imaging (IWBI 2024)

View full text Add to dashboard Cite

show abstract

“…However, there are significant barriers to the implementation of AI applications in breast imaging, including inconsistent performance, significant cost, and IT requirements, along with the lack of radiologist, patient, and referring provider familiarity and trust [66]. Additionally, there are meaningful concerns for the generalizability of AI algorithms in breast imaging, with a recent publication showing significant performance degradation of an AI algorithm that was trained using images from a specific manufacturer when tested using an updated system/software from that same manufacturer [67]. This required sitespecific modification of the algorithm to improve its performance.…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

Artificial Intelligence Applications in Breast Imaging: Current Status and Future Directions

et al. 2023

View full text Add to dashboard Cite

Attempts to use computers to aid in the detection of breast malignancies date back more than 20 years. Despite significant interest and investment, this has historically led to minimal or no significant improvement in performance and outcomes with traditional computer-aided detection. However, recent advances in artificial intelligence and machine learning are now starting to deliver on the promise of improved performance. There are at present more than 20 FDA-approved AI applications for breast imaging, but adoption and utilization are widely variable and low overall. Breast imaging is unique and has aspects that create both opportunities and challenges for AI development and implementation. Breast cancer screening programs worldwide rely on screening mammography to reduce the morbidity and mortality of breast cancer, and many of the most exciting research projects and available AI applications focus on cancer detection for mammography. There are, however, multiple additional potential applications for AI in breast imaging, including decision support, risk assessment, breast density quantitation, workflow and triage, quality evaluation, response to neoadjuvant chemotherapy assessment, and image enhancement. In this review the current status, availability, and future directions of investigation of these applications are discussed, as well as the opportunities and barriers to more widespread utilization.

show abstract

“…Here, UPA adds an important safeguard for identifying performance drift in new deployments. Additionally, we believe that local validation on representative data 5 , regular AI audits 34 , and a careful analysis of discordant cases remain critical components for safe clinical deployment and the assurance that AI continues to be safe over time.…”

Section: Discussionmentioning

confidence: 99%

Automatic correction of performance drift under acquisition shift in medical image classification

Roschewitz,

Khara,

Yearsley

et al. 2023

Nat Commun

View full text Add to dashboard Cite

Image-based prediction models for disease detection are sensitive to changes in data acquisition such as the replacement of scanner hardware or updates to the image processing software. The resulting differences in image characteristics may lead to drifts in clinically relevant performance metrics which could cause harm in clinical decision making, even for models that generalise in terms of area under the receiver-operating characteristic curve. We propose Unsupervised Prediction Alignment, a generic automatic recalibration method that requires no ground truth annotations and only limited amounts of unlabelled example images from the shifted data distribution. We illustrate the effectiveness of the proposed method to detect and correct performance drift in mammography-based breast cancer screening and on publicly available histopathology data. We show that the proposed method can preserve the expected performance in terms of sensitivity/specificity under various realistic scenarios of image acquisition shift, thus offering an important safeguard for clinical deployment.

show abstract

Impact of Different Mammography Systems on Artificial Intelligence Performance in Breast Cancer Screening

Cited by 18 publications

References 10 publications

Survey of image processing settings used for mammography systems in the United Kingdom: how variable is it?

Survey of image processing settings used for mammography systems in the United Kingdom: how variable is it?

Artificial Intelligence Applications in Breast Imaging: Current Status and Future Directions

Automatic correction of performance drift under acquisition shift in medical image classification

Contact Info

Product

Resources

About