Artifacts in contrast-enhanced mammography: are there differences between vendors?

Optimizing contrast enhanced mammography: A comprehensive review of artefacts, causes, and remedies

Contrast enhanced mammography (CEM) is a promising imaging technique in breast imaging, combining efficiency and cost-effectiveness with the ability to provide structural as well as functional information. However, like all imaging modalities, CEM is prone to artifacts that can occur at various stages of the process, including patient preparation, image acquisition, equipment calibration, and digital subtraction. Recognising and rectifying these artifacts is essential for achieving optimal image quality and accurate diagnosis. The purpose of this article is to familiarise the readers with common artifacts encountered during CEM and minimise their impact on image interpretation, with a focus on strategies for optimising CEM imaging. We have also described a few previously uncharted CEM-specific artifacts observed in our clinical experience. Additionally, this review highlights major pitfalls encountered during CEM reporting and measures to improve diagnostic accuracy.

Contrast-enhanced mammography improves patient access to functional breast imaging

Imaging research pathways focus increasingly on the development of individualised approaches to breast cancer detection, diagnosis and management. Detection of breast cancer with X-ray mammography may fail in some cancer subtypes with limited changes in morphology/tissue density and in women with dense breasts. International organisations offer recommendations for contrast-enhanced breast imaging, as it provides superior sensitivity for screening, local staging and assessment of neoadjuvant treatment response, when compared with standard X-ray mammography (including tomosynthesis) and breast ultrasound. Arguably, the evidence base is stronger for contrast-enhanced MRI (CE-MRI). Unfortunately, patient access to breast MRI in rural and remote areas is limited by practical limitations and equipment licensing restrictions. Moreover, breast MRI is an expensive test, likely to be out of reach for many women. Contrast-enhanced mammography (CEM) offers an attractive alternative to improve patient access to functional breast imaging. It is a new type of digital, dual energy X-ray mammography that can be performed on most modern units, following a relatively inexpensive hard- and software upgrade. In this paper, we review the rapidly accumulating evidence that CEM can provide similar diagnostic accuracy to CE-MRI, though at a significantly lower cost and offering greater comfort to the patient. The adoption of CEM can help meet the anticipated increased demand for CE-MRI.

Uncertainty-aware multiple-instance learning for reliable classification: Application to optical coherence tomography

Deep learning classification models for medical image analysis often perform well on data from scanners that were used to acquire the training data. However, when these models are applied to data from different vendors, their performance tends to drop substantially. Artifacts that only occur within scans from specific scanners are major causes of this poor generalizability. We aimed to enhance the reliability of deep learning classification models using a novel method called Uncertainty-Based Instance eXclusion (UBIX). UBIX is an inference-time module that can be employed in multiple-instance learning (MIL) settings. MIL is a paradigm in which instances (generally crops or slices) of a bag (generally an image) contribute towards a bag-level output. Instead of assuming equal contribution of all instances to the bag-level output, UBIX detects instances corrupted due to local artifacts on-the-fly using uncertainty estimation, reducing or fully ignoring their contributions before MIL pooling. In our experiments, instances are 2D slices and bags are volumetric images, but alternative definitions are also possible. Although UBIX is generally applicable to diverse classification tasks, we focused on the staging of age-related macular degeneration in optical coherence tomography. Our models were trained on data from a single scanner and tested on external datasets from different vendors, which included vendor-specific artifacts. UBIX showed reliable behavior, with a slight decrease in performance (a decrease of the quadratic weighted kappa (κw) from 0.861 to 0.708), when applied to images from different vendors containing artifacts; while a state-of-the-art 3D neural network without UBIX suffered from a significant detriment of performance (κw from 0.852 to 0.084) on the same test set. We showed that instances with unseen artifacts can be identified with OOD detection. UBIX can reduce their contribution to the bag-level predictions, improving reliability without retraining on new data. This potentially increases the applicability of artificial intelligence models to data from other scanners than the ones for which they were developed. The source code for UBIX, including trained model weights, is publicly available through https://github.com/qurAI-amsterdam/ubix-for-reliable-classification.

Investigation of test methods for QC in dual-energy based contrast-enhanced digital mammography systems: II. Artefacts/uniformity, exposure time and phantom-based dosimetry

Part II of this study describes constancy tests for artefacts and image uniformity, exposure time, and phantom-based dosimetry; these are applied to four mammography systems equipped with contrast enhanced mammography (CEM) capability. Artefacts were tested using a breast phantom that simulated breast shape and thickness change at the breast edge. Image uniformity was assessed using rectangular poly(methyl)methacrylate PMMA plates at phantom thicknesses of 20, 40 and 60 mm, for the low energy (LE), high energy (HE) images and the recombined CEM image. Uniformity of signal and of the signal to noise ratio was quantified. To estimate CEM exposure times, breast simulating blocks were imaged in automatic exposure mode. The resulting x-ray technique factors were then set manually and exposure time for LE and HE images and total CEM acquisition time was measured with a multimeter. Mean glandular dose (MGD) was assessed as a function of simulated breast thickness using three different phantom compositions: (i) glandular and adipose breast tissue simulating blocks combined to give glandularity values that were typical of those in a screening population, as thickness was changed (ii) PMMA sheets combined with polyethylene blocks (iii) PMMA sheets with spacers. Image uniformity was superior for LE compared to HE images. Two systems did not generate recombined images for the uniformity test when the detector was fully covered. Acquisition time for a CEM image pair for a 60 mm thick breast equivalent phantom ranged from 3.4 to 10.3 s. Phantom composition did not have a strong influence on MGD, with differences generally smaller than 10%. MGD for the HE images was lower than for the LE images, by a factor of between 1.3 and 4.0, depending on system and simulated breast thickness. When combined with the iodine signal assessment in part I, these tests provide a comprehensive assessment of CEM system imaging performance.

How to Recognize and Correct Artifacts on Contrast-Enhanced Mammography

Contrast-enhanced mammography (CEM) has emerged as an important new technology in breast imaging. It can demonstrate a number of imaging artifacts that have the potential to limit interpretation by either obscuring or potentially mimicking disease. Commonly encountered artifacts on CEM include patient motion artifacts (ripple and misregistration), pectoral highlighting artifact, breast implant artifact, halo artifact, corrugation artifact, cloudy fat artifact, contrast artifacts (retention and contamination), skin artifacts (skin line enhancement and skin overexposure), and skin lesions. Skin lesions may demonstrate a variety of imaging appearances and have both benign and malignant etiologies. It is important that the technologist, radiologist, and physicist be aware of potential artifacts and skin enhancement on CEM that may affect interpretation and understand their causes and potential solutions.

Artifact reduction in contrast-enhanced mammography

OBJECTIVE

To evaluate the effectiveness of a new algorithm developed to reduce artifacts in dual-energy subtraction (DES) contrast-enhanced mammography (CEM) images while preserving contrast enhancement of possible lesions.

METHODS

A retrospective multi-reader paired study was performed by using 134 CEM studies obtained from the first 134 women enrolled in a prospective clinical study aiming to compare the clinical performance of CEM to those of breast MRI in screening of women at increased risk of breast cancer. Four experienced readers compared independently the standard (STD) DES images with those obtained by reprocessing the raw images by a new algorithm (NEW), expected to reduce the DES artifact intensity. The intensity of three types of artifacts (breast-in-breast, ripple, and skinfold enhancement) and the intensity of possible contrast uptake were assessed visually and rated using a categorical ordinal scale. Proportions of images rated by the majority of readers as "Absent", "Weak", "Medium", "Strong" in each artifact intensity category were compared between the two algorithms. P-values lower than 0.05 were considered statistically significant.

RESULTS

The NEW algorithm succeeded in eliminating 84.5% of breast-in-breast artifacts, 84.2% of ripple artifacts, and 56.9% of skinfold enhancement artifacts versus STD DES images, and reduced the artifact intensity in 12.1%, 13.0%, and 28.8% of the images, respectively. The visibility of lesion contrast uptake was the same with the STD and the NEW algorithms.

CONCLUSION

The new dual-energy subtraction algorithm demonstrated to be effective in reducing/eliminating CEM-related artifacts while preserving lesion contrast enhancement.

Identifying factors that may influence the classification performance of radiomics models using contrast-enhanced mammography (CEM) images

Background

Radiomics plays an important role in the field of oncology. Few studies have focused on the identification of factors that may influence the classification performance of radiomics models. The goal of this study was to use contrast-enhanced mammography (CEM) images to identify factors that may potentially influence the performance of radiomics models in diagnosing breast lesions.

Methods

A total of 157 women with 161 breast lesions were included. Least absolute shrinkage and selection operator (LASSO) regression and the random forest (RF) algorithm were employed to construct radiomics models. The classification result for each lesion was obtained by using 100 rounds of five-fold cross-validation. The image features interpreted by the radiologists were used in the exploratory factor analyses. Univariate and multivariate analyses were performed to determine the association between the image features and misclassification. Additional exploratory analyses were performed to examine the findings.

Results

Among the lesions misclassified by both LASSO and RF ≥ 20% of the iterations in the cross-validation and those misclassified by both algorithms ≤5% of the iterations, univariate analysis showed that larger lesion size and the presence of rim artifacts and/or ripple artifacts were associated with more misclassifications among benign lesions, and smaller lesion size was associated with more misclassifications among malignant lesions (all p <  0.050). Multivariate analysis showed that smaller lesion size (odds ratio [OR] = 0.699, p = 0.002) and the presence of air trapping artifacts (OR = 35.568, p = 0.025) were factors that may lead to misclassification among malignant lesions. Additional exploratory analyses showed that benign lesions with rim artifacts and small malignant lesions (< 20 mm) with air trapping artifacts were misclassified by approximately 50% more in rate compared with benign and malignant lesions without these factors.

Conclusions

Lesion size and artifacts in CEM images may affect the diagnostic performance of radiomics models. The classification results for lesions presenting with certain factors may be less reliable.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-022-00460-8.