A model observer study using acquired mammographic images of an anthropomorphic breast phantom

Overview of trials on artificial intelligence algorithms in breast cancer screening - A roadmap for international evaluation and implementation

Accumulating evidence from retrospective studies demonstrate at least non-inferior performance when using AI algorithms with different strategies versus double-reading in mammography screening. In addition, AI algorithms for mammography screening can reduce work load by moving to single human reading. Prospective trials are essential to avoid unintended adverse consequences before incorporation of AI algorithms into UK's National Health Service (NHS) Breast Screening Programme (BSP). A stakeholders' meeting was organized in Newnham College, Cambridge, UK to undertake a review of the current evidence to enable consensus discussion on next steps required before implementation into a screening programme. It was concluded that a multicentre multivendor testing platform study with opt-out consent is preferred. AI thresholds from different vendors should be determined while maintaining non-inferior screening performance results, particularly ensuring recall rates are not increased. Automatic recall of cases using an agreed high sensitivity AI score versus automatic rule out with a low AI score set at a high sensitivity could be used. A human reader should still be involved in decision making with AI-only recalls requiring human arbitration. Standalone AI algorithms used without prompting maintain unbiased screening reading performance, but reading with prompts should be tested prospectively and ideally provided for arbitration.

A voxel-by-voxel method for mixing two filaments during a 3D printing process for soft-tissue replication in an anthropomorphic breast phantom

Objective. In this study, a novel voxel-by-voxel mixing method is presented, according to which two filaments of different material are combined during the three dimensional (3D) printing process.Approach. In our approach, two types of filaments were used for the replication of soft-tissues, a polylactic acid (PLA) filament and a polypropylene (PP) filament. A custom-made software was used, while a series of breast patient CT scan images were directly associated to the 3D printing process. Each phantom´s layer was printed twice, once with the PLA filament and a second time with the PP filament. For each material, the filament extrusion rate was controlled voxel-by-voxel and was based on the Hounsfield units (HU) of the imported CT images. The phantom was scanned at clinical CT, breast tomosynthesis and micro CT facilities, as the major processing was performed on data from the CT. A side by side comparison between patient´s and phantom´s CT slices by means of profile and histogram comparison was accomplished. Further, in case of profile comparison, the Pearson´s coefficients were calculated.Main results. The visual assessment of the distribution of the glandular tissue in the CT slices of the printed breast anatomy showed high degree of radiological similarity to the corresponding patient´s glandular distribution. The profile plots´ comparison showed that the HU of the replicated and original patient soft tissues match adequately. In overall, the Pearson´s coefficients were above 0.91, suggesting a close match of the CT images of the phantom with those of the patient. The overall HU were close in terms of HU ranges. The HU mean, median and standard deviation of the original and the phantom CT slices were -149, -167, ±65 and -121, -130, ±91, respectively.Significance. The results suggest that the proposed methodology is appropriate for manufacturing of anthropomorphic soft tissue phantoms for x-ray imaging and dosimetry purposes, since it may offer an accurate replication of these tissues.

Convolutional neural network -based phantom image scoring for mammography quality control

BACKGROUND

Visual evaluation of phantom images is an important, but time-consuming part of mammography quality control (QC). Consistent scoring of phantom images over the device's lifetime is highly desirable. Recently, convolutional neural networks (CNNs) have been applied to a wide range of image classification problems, performing with a high accuracy. The purpose of this study was to automate mammography QC phantom scoring task by training CNN models to mimic a human reviewer.

METHODS

Eight CNN variations consisting of three to ten convolutional layers were trained for detecting targets (fibres, microcalcifications and masses) in American College of Radiology (ACR) accreditation phantom images and the results were compared with human scoring. Regular and artificially degraded/improved QC phantom images from eight mammography devices were visually evaluated by one reviewer. These images were used in training the CNN models. A separate test set consisted of daily QC images from the eight devices and separately acquired images with varying dose levels. These were scored by four reviewers and considered the ground truth for CNN performance testing.

RESULTS

Although hyper-parameter search space was limited, an optimal network depth after which additional layers resulted in decreased accuracy was identified. The highest scoring accuracy (95%) was achieved with the CNN consisting of six convolutional layers. The highest deviation between the CNN and the reviewers was found at lowest dose levels. No significant difference emerged between the visual reviews and CNN results except in case of smallest masses.

CONCLUSION

A CNN-based automatic mammography QC phantom scoring system can score phantom images in a good agreement with human reviewers, and can therefore be of benefit in mammography QC.

3D printing methods for radiological anthropomorphic phantoms

Three dimensional (3D) printing technology has been widely evaluated for the fabrication of various anthropomorphic phantoms during the last couple of decades. The demand for such high quality phantoms is constantly rising and gaining an ever-increasing interest. Although, in a short time 3D printing technology provided phantoms with more realistic features when compared to the previous conventional methods, there are still several aspects to be explored. One of these aspects is the further development of the current 3D printing methods and software devoted to radiological applications. The current 3D printing software and methods usually employ 3D models, while the direct association of medical images with the 3D printing process is needed in order to provide results of higher accuracy and closer to the actual tissues' texture. Another aspect of high importance is the development of suitable printing materials. Ideally, those materials should be able to emulate the entire range of soft and bone tissues, while still matching the human's anatomy. Five types of 3D printing methods have been mainly investigated so far: (a) solidification of photo-curing materials; (b) deposition of melted plastic materials; (c) printing paper-based phantoms with radiopaque ink; (d) melting or binding plastic powder; and (e) bio-printing. From the first and second category, polymer jetting technology and fused filament fabrication (FFF), also known as fused deposition modelling (FDM), are the most promising technologies for the fulfilment of the requirements of realistic and radiologically equivalent anthropomorphic phantoms. Another interesting approach is the fabrication of radiopaque paper-based phantoms using inkjet printers. Although, this may provide phantoms of high accuracy, the utilized materials during the fabrication process are restricted to inks doped with various contrast materials. A similar condition applies to the polymer jetting technology, which despite being quite fast and very accurate, the utilized materials are restricted to those capable of polymerization. The situation is better for FFF/FDM 3D printers, since various compositions of plastic filaments with external substances can be produced conveniently. Although, the speed and accuracy of this 3D printing method are lower compared to the others, the relatively low-cost, constantly improving resolution, sufficient printing volume and plethora of materials are quite promising for the creation of human size heterogeneous phantoms and their adaptation to the treatment procedures of patients in the current health systems.

Explainability for deep learning in mammography image quality assessment

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 gradientsmethod 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 (IQA) 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 IQA, the proposed explainability method could also become relevant in other, similar deep learning applications based on high-dimensional images.

The regression detectability index RDI for mammography images of breast phantoms with calcification-like objects and anatomical background

Currently, quality assurance measurements in mammography are performed on unprocessed images. For diagnosis, however, radiologists are provided with processed images. This image processing is optimised for images of human anatomy and therefore does not always perform satisfactorily with technical phantoms. To overcome this problem, it may be possible to use anthropomorphic phantoms reflecting the anatomic structure of the human breast in place of technical phantoms when carrying out task-specific quality assessment using model observers. However, the use of model observers is hampered by the fact that a large number of images needs to be acquired. A recently published novel observer called the regression detectability index (RDI) needs significantly fewer images, but requires the background of the images to be flat. Therefore, to be able to apply the RDI to images of anthropomorphic phantoms, the anatomic background needs to be removed. For this, a procedure in which the anatomical structures are fitted by thin plate spline (TPS) interpolation has been developed. When the object to be detected is small, such as a calcification-like lesion, it is shown that the anatomic background can be removed successfully by subtracting the TPS interpolation, which makes the background-free image accessible to the RDI. We have compared the detectability obtained by the RDI with TPS background subtraction to results of the channelized Hotelling observer (CHO) and human observers. With the RDI, results for the detectabilityd'can be obtained using 75% fewer images compared to the CHO, while the same uncertainty ofd'is achieved. Furthermore, the correlation ofd'(RDI) with the results of human observers is at least as good as that ofd'(CHO) with human observers.

RDI[Formula: see text]a regression detectability index for quality assurance in: x-ray imaging

Novel iterative image reconstruction methods can help reduce the required radiation dose in x-ray diagnostics such as computed tomography (CT), while maintaining sufficient image quality. Since some of the established image quality measures are not appropriate for reliably judging the quality of images derived by iterative methods, alternative approaches such as task-specific quality assessment would be highly desirable for acceptance or constancy testing. Task-based image quality methods are also closer to tasks performed by the radiologists, such as lesion detection. However, this approach is usually hampered by a huge workload, since hundreds of images are usually required for its application. It is demonstrated that the proposed approach works reliably on the basis of significantly fewer images, and that it correlates well with results obtained from human observers.

Breast phantoms for 2D digital mammography with realistic anatomical structures and attenuation characteristics based on clinical images using 3D printing

The aim of this work was to develop a production process for breast phantoms for 2D digital mammography (DM) with realistic anatomical structures and attenuation characteristics based on clinical images using 3D printing. The presented production process is based on PolyJet 3D printing technology using a polypropylene like printing material. First, an attenuation calibration function for this material and the achievable lateral resolution of the printing process of about 200 µm was determined. Subsequently, to generate the digital 3D model of the breast phantom, the pixel intensities of the unprocessed clinical image that are related to the attenuation along the z-axis of the breast, were converted to corresponding phantom heights using the calibration function. To validate the process, an image of the 3D printed breast phantom was acquired on the full field digital mammography (FFDM) system used for calibration and compared with the clinical image in terms of anatomical structures and associated attenuation characteristics. The exposure parameters and image impression of the phantom were evaluated using five other FFDM systems of different manufacturers and types. Results demonstrated that the anatomical structures in the images and the attenuation characteristics of a female breast and the derived phantom agreed on the FFDM system used for calibration. The automatic exposure control segmentation, the automatically selected exposure parameters and the image postprocessing of the clinical and phantom image indicated a high level of conformity. As shown, the phantom is also suitable for other FFDM systems. In conclusion, an approach to produce anthropomorphic breast phantoms for DM offering realistic anatomical structures and attenuation characteristics based on clinical images was successfully developed. As shown, the phantom realistically simulated the original female breast. Therefore, it is expected that such phantoms are promising to support bridging the gap between physical-technical and diagnostic image quality assessment. In addition, they enable a variety of practical and scientific applications for which present technical phantoms are not suitable.

Optimization of the difference-of-Gaussian channel sets for the channelized Hotelling observer

The channelized-Hotelling observer (CHO) was investigated as a surrogate of human observers in task-based image quality assessment. The CHO with difference-of-Gaussian (DoG) channels has shown potential for the prediction of human detection performance in digital mammography (DM) images. However, the DoG channels employ parameters that describe the shape of each channel. The selection of these parameters influences the performance of the DoG CHO and needs further investigation. The detection performance of the DoG CHO was calculated and correlated with the detection performance of three humans who evaluated DM images in 2-alternative forced-choice experiments. A set of DM images of an anthropomorphic breast phantom with and without calcification-like signals was acquired at four different dose levels. For each dose level, 200 square regions-of-interest (ROIs) with and without signal were extracted. Signal detectability was assessed on ROI basis using the CHO with various DoG channel parameters and it was compared to that of the human observers. It was found that varying these DoG parameter values affects the correlation (r 2 ) of the CHO with human observers for the detection task investigated. In conclusion, it appears that the the optimal DoG channel sets that maximize the prediction ability of the CHO might be dependent on the type of background and signal of ROIs investigated.

Can a channelized Hotelling observer assess image quality in acquired mammographic images of an anthropomorphic breast phantom including image processing?

PURPOSE

To study the feasibility of a channelized Hotelling observer (CHO) to predict human observer performance in detecting calcification-like signals in mammography images of an anthropomorphic breast phantom, as part of a quality control (QC) framework.

METHODS

A prototype anthropomorphic breast phantom with inserted gold disks of 0.25 mm diameter was imaged with two different digital mammography x-ray systems at four different dose levels. Regions of interest (ROIs) were extracted from the acquired processed and unprocessed images, signal-present and signal-absent. The ROIs were evaluated by a CHO using four different formulations of the difference of Gaussian (DoG) channel sets. Three human observers scored the ROIs in a two-alternative forced-choice experiment. We compared the human and the CHO performance on the simple task to detect calcification-like disks in ROIs with and without postprocessing. The proportion of correct responses of the human reader (PC_H ) and the CHO (PC_CHO ) was calculated and the correlation between the two was analyzed using a mixed-effect regression model. To address the signal location uncertainty, the impact of shifting the DoG channel sets in all directions up to two pixels was evaluated. Correlation results including the goodness of fit (r² ) of PC_H and PC_CHO for all different parameters were evaluated.

RESULTS

Subanalysis by system yielded strong correlations between PC_H and PC_CHO , with r² between PC_H and PC_CHO was found to be between 0.926 and 0.958 for the unshifted and between 0.759 and 0.938 for the shifted channel sets, respectively. However, the linear fit suggested a slight system dependence. PC_CHO with shifted channel sets increased CHO performance but the correlation with humans was decreased. These correlations were not considerably affected by of the DoG channel set used.

CONCLUSIONS

There is potential for the CHO to be used in QC for the evaluation of detectability of calcification-like signals. The CHO can predict the PC of humans in images of calcification-like signals of two different systems. However, a global model to be used for all systems requires further investigation.

Signal template generation from acquired images for model observer-based image quality analysis in mammography

Mammography images undergo vendor-specific processing, which may be nonlinear, before radiologist interpretation. Therefore, to test the entire imaging chain, the effect of image processing should be included in the assessment of image quality, which is not current practice. For this purpose, model observers (MOs), in combination with anthropomorphic breast phantoms, are proposed to evaluate image quality in mammography. In this study, the nonprewhitening MO with eye filter and the channelized Hotelling observer were investigated. The goal of this study was to optimize the efficiency of the procedure to obtain the expected signal template from acquired images for the detection of a 0.25-mm diameter disk. Two approaches were followed: using acquired images with homogeneous backgrounds (approach 1) and images from an anthropomorphic breast phantom (approach 2). For quality control purposes, a straightforward procedure using a single exposure of a single disk was found adequate for both approaches. However, only approach 2 can yield templates from processed images since, due to its nonlinearity, image postprocessing cannot be evaluated using images of homogeneous phantoms. Based on the results of the current study, a phantom should be designed, which can be used for the objective assessment of image quality.

Internal breast dosimetry in mammography: Monte Carlo validation in homogeneous and anthropomorphic breast phantoms with a clinical mammography system

PURPOSE

To validate Monte Carlo (MC)-based breast dosimetry estimations using both a homogeneous and a 3D anthropomorphic breast phantom under polyenergetic irradiation for internal breast dosimetry purposes.

METHODS

Experimental measurements were performed with a clinical digital mammography system (Mammomat Inspiration, Siemens Healthcare), using the x-ray spectrum selected by the automatic exposure control and a tube current-exposure time product of 360 mAs. A homogeneous 50% glandular breast phantom and a 3D anthropomorphic breast phantom were used to investigate the dose at different depths (range 0-4 cm with 1 cm steps) for the homogeneous case and at a depth of 2.25 cm for the anthropomorphic case. Local dose deposition was measured using thermoluminescent dosimeters (TLD), metal oxide semiconductor field-effect transistor dosimeters (MOSFET), and GafChromic™ films. A Geant4-based MC simulation was modified to match the clinical experimental setup. Thirty sensitive volumes (3.2 × 3.2 × 0.38 mm3 ) on the axial-phantom plane were included at each depth in the simulation to characterize the internal dose variation and compare it to the experimental TLD and MOSFET measurements. The experimental 2D dose maps obtained with the GafChromic™ films were compared to the simulated 2D dose distributions.

RESULTS

Due to the energy dependence of the dosimeters and due to x-ray beam hardening, dosimeters based on these three technologies have to be calibrated at each depth of the phantom. As expected, the dose was found to decrease with increasing phantom depth, with the reduction being ~93% after 4 cm for the homogeneous breast phantom. The 2D dose map showed nonuniformities in the dose distribution in the axial plane of the phantom. The mean combined standard uncertainty increased with phantom depth by up to 5.3% for TLD, 6.3% for MOSFET, and 9.6% for GafChromic™ film. In the case of a heterogeneous phantom, the dosimeters are able to detect local dose gradient variations. In particular, GafChromic™ film showed local dose variations of about 46% at the boundaries of two materials.

CONCLUSIONS

Results showed a good agreement between experimental measurements (with TLD and MOSFET) and MC data for both homogeneous and anthropomorphic breast phantoms. Larger discrepancies are found when comparing the GafChromic™ dose values to the MC results due to the inherent less precise nature of the former. MC validations in a heterogeneous background at the level of local dose deposition and in absolute terms play a fundamental role in the development of an accurate method to estimate radiation dose. The potential introduction of a breast dosimetry model involving a nonhomogeneous glandular/adipose tissue composition makes the validation of internal dose distributions estimates crucial.