Determination of contrast-detail curves in mammography image quality assessment by a parametric model observer

Kretz, T.; Anton, Mathias; Schaeffter, Tobias; Elster, Clemens

doi:10.1016/j.ejmp.2019.05.008

Cited by 7 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Using an ensemble instead of a single network allows the predictions Table 1. The simulation parameters used by the software for the virtual mammography [29]. The software considers the tube voltage, current-exposure time product and the noise level which is defined as the standard deviation of the Gaussian white noise that is fed into a Gaussian filter which simulates the noise in mammography images.…”

Section: Details On Training and Used Datamentioning

confidence: 99%

Explainability for deep learning in mammography image quality assessment

Amanova

Martin

Elster

2022

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

The application of deep learning has recently been proposed for the assessment of image quality in mammography. It was demonstrated in a proof-of-principle study that the proposed approach can be more efficient than currently applied automated conventional methods. However, in contrast to conventional methods, the deep learning approach has a black-box nature and, before it can be recommended for the routine use, it must be understood more thoroughly. For this purpose, we propose and apply a new explainability method: the oriented, modified integrated gradients (OMIG) method. The design of this method is inspired by the integrated gradients method but adapted considerably to the use case at hand. To further enhance this method, an upsampling technique is developed that produces high-resolution explainability maps for the downsampled data used by the deep learning approach. Comparison with established explainability methods demonstrates that the proposed approach yields substantially more expressive and informative results for our specific use case. Application of the proposed explainability approach generally confirms the validity of the considered deep learning-based mammography image quality assessment method. Specifically, it is demonstrated that the predicted image quality is based on a meaningful mapping that makes successful use of certain geometric structures of the images. In addition, the novel explainability method helps us to identify the parts of the employed phantom that have the largest impact on the predicted image quality, and to shed some light on cases in which the trained neural networks fail to work as expected. While tailored to assess a specific approach from deep learning for mammography image quality assessment, the proposed explainability method could also become relevant in other, similar deep learning applications based on high-dimensional images.

show abstract

Section: Details On Training and Used Datamentioning

confidence: 99%

Explainability for deep learning in mammography image quality assessment

Amanova

Martin

Elster

2022

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…1) Simulated images: An in-house tool for virtual mammography [29] was used to simulate images of the CDMAM phantom. The virtual mammography simulates a xray spectrum according to the target material, the voltage and the exposure time current product.…”

Section: B Datamentioning

confidence: 99%

“…The EUREF Guideline procedure is used to determine these contrast-detail curves. The EUREF Guideline procedure has to be applied to a group of images, and the uncertainty of the resulting contrast-detail curve depends essentially on the number of images in that group [29]. For the real images, all 48 images were used to calculate one contrast-detail curve, which was then assigned to all 48 images.…”

Section: B Datamentioning

confidence: 99%

See 1 more Smart Citation

Mammography Image Quality Assurance Using Deep Learning

Kretz

Mueller

Schaeffter

et al. 2020

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

According to the European Reference Organization for Quality Assured Breast Cancer Screening and Diagnostic Services (EUREF) image quality in mammography is assessed by recording and analyzing a set of images of the CDMAM phantom. The EUREF procedure applies an automated analysis combining image registration, signal detection and nonlinear fitting. We present a proof of concept for an endto-end deep learning framework that assesses image quality on the basis of single images as an alternative. Methods: Virtual mammography is used to generate a database with known ground truth for training a regression convolutional neural net (CNN). Training is carried out by continuously extending the training data and applying transfer learning. Results: The trained net is shown to correctly predict the image quality of simulated and real images. Specifically, image quality predictions on the basis of single images are of similar quality as those obtained by applying the EUREF procedure with 16 images. Our results suggest that the trained CNN generalizes well. Conclusion: Mammography image quality assessment can benefit from the proposed deep learning approach. Significance: Deep learning avoids cumbersome pre-processing and allows mammography image quality to be estimated reliably using single images.

show abstract

“…In recent years deep neural networks have proven to be a useful and powerful tool in various tasks, ranging from medical applications [19,20], over language processing [15,31] to computer vision [16,42], robotics [24,27,34] and autonomous driving [9,13]. In many applications, especially those in which reliability and safety are crucial [25,30,39], it is valuable, if not indispensable, to know the uncertainty behind a prediction of a neural network.…”

Section: Introductionmentioning

confidence: 99%

Aleatoric Uncertainty for Errors-in-Variables Models in Deep Regression

Martin

Elster

2022

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

A Bayesian treatment of deep learning allows for the computation of uncertainties associated with the predictions of deep neural networks. We show how the concept of Errors-in-Variables can be used in Bayesian deep regression to also account for the uncertainty associated with the input of the employed neural network. The presented approach thereby exploits a relevant, but generally overlooked, source of uncertainty and yields a decomposition of the predictive uncertainty into an aleatoric and epistemic part that is more complete and, in many cases, more consistent from a statistical perspective. We discuss the approach along various simulated and real examples and observe that using an Errors-in-Variables model leads to an increase in the uncertainty while preserving the prediction performance of models without Errors-in-Variables. For examples with known regression function we observe that this ground truth is substantially better covered by the Errors-in-Variables model, indicating that the presented approach leads to a more reliable uncertainty estimation.

show abstract

Determination of contrast-detail curves in mammography image quality assessment by a parametric model observer

Cited by 7 publications

References 31 publications

Explainability for deep learning in mammography image quality assessment

Explainability for deep learning in mammography image quality assessment

Mammography Image Quality Assurance Using Deep Learning

Aleatoric Uncertainty for Errors-in-Variables Models in Deep Regression

Contact Info

Product

Resources

About