Low-energy Images Research Articles

Investigation of test methods for QC in dual-energy based contrast-enhanced digital mammography systems: I. Iodine signal testing

The technique of dual-energy contrast enhanced mammography (CEM) visualizes iodine uptake in cancerous breast lesions following an intravenous injection of a contrast medium. The CEM image is generated by recombining two images acquired in rapid succession: a low energy image, with a mean energy below the iodine K-edge, and a higher energy image. The first part of this study examines the use of both commercially available and custom made phantoms to investigate iodine imaging under different imaging conditions, with the focus on quality control (QC) testing. Four CEM equipped systems were included in the study, with units from Fujifilm, GE Healthcare, Hologic and Siemens-Healthineers. The CEM parameters assessed in part I were: (1) image signal as a function of iodine concentration, measured in breast tissue simulating backgrounds of varying thickness and adipose/glandular compositions; (2) normal breast texture cancellation in homogeneous and structured backgrounds; (3) visibility of iodinated structures. For all four systems, a linear response to iodine concentration was found but the degree to which this was independent of background composition differed between the systems. Good cancellation of the glandular tissue inserts was found on all the units. Visibility scores of iodinated targets were similar between the four systems. Specialized phantoms are needed to fully evaluate important CEM performance markers, such as system response to iodine concentration and the ability of the system to cancel background texture. An extensive evaluation of the iodine signal imaging performance is recommended at the Commissioning stage for a new CEM device.

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.

Role of contrast-enhanced mammography in the preoperative detection of ductal carcinoma in situ of the breasts: a comparison with low-energy image and magnetic resonance imaging.

To compare contrast-enhanced mammography (CEM) with low-energy image (LEI) alone and with magnetic resonance imaging (MRI) in the preoperative diagnosis of ductal carcinoma in situ (DCIS). In this single-center retrospective study, we reviewed 98 pure DCIS lesions in 96 patients who underwent CEM and MRI within 2weeks preoperatively. The diagnostic performances of each imaging modality, lesion morphology, and extent were evaluated. The sensitivity of CEM to DCIS was similar to that of MRI (92.9% vs. 93.9%, p = 0.77) and was significantly higher than that of LEI alone (76.5%, p = 0.002). The sensitivity of CEM to calcified DCIS (92.4%) was not significantly different from LEI alone (92.4%) and from MRI (93.9%, p = 1.00). However, CEM contributed to the simultaneous comparison of calcifications with enhancements. CEM had considerably higher sensitivity compared with LEI alone (93.8% vs. 43.8%, p < 0.001) and performed similarly to MRI (93.8%, p = 1.00) for noncalcified DCIS. All DCIS lesions were enhanced in MRI, whereas 94.9% (93/98) were enhanced in CEM. Non-mass enhancement was the most common presentation (CEM 63.4% and MRI 66.3%). The difference between the lesion size on each imaging modality and the histopathological size was smallest in MRI, followed by CEM, and largest in LEI. CEM was more sensitive than LEI alone and comparable to MRI in DCIS diagnosis. The enhanced morphology of DCIS in CEM was consistent with that in MRI. CEM was superior to LEI alone in size measurement of DCIS. This study investigated the value of CEM in the diagnosis and evaluation of DCIS, aiming to offer a reference for the selection of examination methods for DCIS and contribute to the early diagnosis and precise treatment of DCIS. • DCIS is an important indication for breast surgery. Early and accurate diagnosis is crucial for DCIS treatment and prognosis. • CEM overcomes the deficiency of mammography in noncalcified DCIS diagnosis, exhibiting similar sensitivity to MRI; and CEM contributes to the comparison of calcification and enhancement of calcified DCIS, thereby outperforming MRI. • CEM is superior to LEI alone and slightly inferior to MRI in the size evaluation of DCIS.

An Efficient Transformer Model for Synthesizing Dual Energy CT from Single Energy Scanner

Dual-energy CT can be used to optimize radiation treatment. Recently, deep learning has been demonstrated to synthesize high-energy CT images from low-energy ones for dose reduction and lower CT system burden. As the state-of-the-art deep learning architecture, the computation burden of Transformer increases quadratically with the feature size, making the model training resource-demanding or even infeasible. Here, we introduce an efficient transformer for the balance between CT image synthesis quality and computational burden. The model is a U-shape deep neural network with encoders and decoders built by Transformer blocks. The model input is low-energy 100kVp CT image and the output is high-energy 140kVp one. Each block has a Self Channel Correlation Unit (SCCU) and a Self Spatial Attention Unit (SSAU). Local shortcuts are applied for both units. Under-sampling operation achieved by pixel shuffling is used to obtain multi-scale feature maps, and the transformer block is applied on each feature scale. Symmetric skip connection sending features from shallow layers to deep layers, thus an additional 1 × 1 convolution is used for feature fusion in each decoder. In a SCCU, the feature is first mapped to one Query, one Key, and one Value. Then the Query and the Key tensors perform matrix multiplication to compute cross covariance of feature channels. The channel correlation score can be obtained by normalization of the covariance, and it is used to weight the Value tensor. As a result, the model complexity only increases linearly with the feature size. Besides the channel weighting, we enhance spatial information using SSAU, where the feature is mapped to two tensors. One tensor after activation is used to point-wisely calibrate another tensor. Additional Transformer blocks are cascaded to the last decoder for feature refinement. Because of the structure similarity of low- and high-energy CT images, a global shortcut is used to ease model training. Clinical iodine contrast-enhanced dual energy CT image datasets of 19 patients are used in this study. The dual-energy scanning is performed by a SOMATOM Definition Flash DECT scanner. We split the datasets into training dataset of 15 patients, validation dataset of 1 patient, and testing dataset of 3 patients. The image size is 512 × 512 with pixel size 0.5 × 0.5 mm2. The U-Net model with 1.95M parameters and 44.87G FLOPS achieved the averaged PSNR value of 44.55 dB (s.t.d. 1.34) and averaged RMSE value of 0.0060 (s.t.d. 0.001). In comparison, our efficient Transformer with 1.408M parameters and 31.375G FLOPS achieved the averaged PSNR value of 44.78 dB (s.t.d. 1.37) and RMSE value of 0.0059 (s.t.d. 0.001), demonstrating our model has better performance with small model size and less computation. The efficient Transformer model allows high-resolution CT image synthesis with small model scale and computation burden from low-energy CT image.

Early detection of hypervascularization in hepatocellular carcinoma (≤2 cm) on hepatic arterial phase with virtual monochromatic imaging: Comparison with low-tube voltage CT.

This study aims to assess the diagnostic value of virtual monochromatic image (VMI) at low keV energy for early detection of small hepatocellular carcinoma (HCC) in hepatic arterial phase compared with low-tube voltage (80 kVp) CT generated from dual-energy CT (DE-CT). A total of 107 patients with 114 hypervascular HCCs (≤2 cm) underwent DE-CT, 140 kVp, blended 120 kVp, and 80 kVp images were generated, as well as 40 and 50 keV. CT numbers of HCCs and the standard deviation as image noise on psoas muscle were measured. The contrast-to-noise ratios (CNR) of HCC were compared among all techniques. Overall image quality and sensitivity for detecting HCC hypervascularity were qualitatively assessed by three readers. The mean CT numbers, CNR, and image noise were highest at 40 keV followed by 50 keV, 80 kVp, blended 120 kVp, and 140 kVp. Significant differences were found in all evaluating endpoints except for mean image noise of 50 keV and 80 kVp. Image quality of 40 keV was the lowest, but still it was considered acceptable for diagnostic purposes. The mean sensitivity for detecting lesion hypervascularity with 40 keV (92%) and 50 keV (84%) was higher than those with 80 kVp (56%). Low keV energy images were superior to 80 kVp in detecting hypervascularization of early HCC.

Impact of Phantom Size on Low-Energy Virtual Monoenergetic Images of Three Dual-Energy CT Platforms.

The purpose of this study was to compare the quality of low-energy virtual monoenergetic images (VMIs) obtained with three Dual-Energy CT (DECT) platforms according to the phantom diameter. Three sections of the Mercury Phantom 4.0 were scanned on two generations of split-filter CTs (SFCT-1st and SFCT-2nd) and on one Dual-source CT (DSCT). The noise power spectrum (NPS), task-based transfer function (TTF), and detectability index (d') were assessed on VMIs from 40 to 70 keV. The highest noise magnitude values were found with SFCT-1st and noise magnitude was higher with DSCT than with SFCT-2nd for 26 cm (10.2% ± 1.3%) and 31 cm (7.0% ± 2.5%), and the opposite for 36 cm (-4.2% ± 2.5%). The highest average NPS spatial frequencies and TTF values at 50% (f50) values were found with DSCT. For all energy levels, the f50 values were higher with SFCT-2nd than SFCT-1st for 26 cm (3.2% ± 0.4%) and the opposite for 31 cm (-6.9% ± 0.5%) and 36 cm (-5.6% ± 0.7%). The lowest d' values were found with SFCT-1st. For all energy levels, the d' values were lower with DSCT than with SFCT-2nd for 26 cm (-6.2% ± 0.7%), similar for 31 cm (-0.3% ± 1.9%) and higher for 36 cm (5.4% ± 2.7%). In conclusion, compared to SFCT-1st, SFCT-2nd exhibited a lower noise magnitude and higher detectability values. Compared with DSCT, SFCT-2nd had a lower noise magnitude and higher detectability for the 26 cm, but the opposite was true for the 36 cm.

Characterization of single- and multi-energy CT performance of an oral dark borosilicate contrast media using a clinical photon-counting-detector CT platform.

The feasibility of oral dark contrast media is under exploration in abdominal computed tomography (CT) applications. One of the experimental contrast media in this class is dark borosilicate contrast media (DBCM), which has a CT attenuation lower than that of intra-abdominal fat. To evaluate the performances of DBCM using single- and multi-energy CT imaging on a clinical photon-counting-detector CT (PCD-CT). Five vials, three with iodinated contrast agent (5, 10, and 20mg/mL; Omnipaque 350) and two with DBCM (6% and 12%; Nextrast, Inc.), and one solid-water rod (neutral contrast agent) were inserted into two multi-energy CT phantoms, and scanned on a clinical PCD-CT system (NAEOTOM Alpha) at 90, 120, 140, Sn100, and Sn140 kV (Sn: tin filter) in multi-energy mode. CARE keV IQ level was 180 (CTDIvol: 3.0 and 12.0 mGy for the small and large phantoms, respectively). Low-energy threshold images were reconstructed with a quantitative kernel (Qr40, iterative reconstruction strength 2) and slice thickness/increment of 2.0/2.0mm. Virtual monoenergetic images (VMIs) were reconstructed from 40 to 140keV at 10keV increments. On all images, average CT numbers for each vial/rod were measured using circular region-of-interests and averaged over eight slices. The contrast-to-noise ratio (CNR) of iodine (5mg/mL) against DBCM was calculated and plotted against tube potential and VMI energy level, and compared to the CNR of iodine against water. Similar analyses were performed on iodine maps and VNC images derived from the multi-energy scan at 120kV. With increasing kV or VMI keV, the negative HU of DBCM decreased only slightly, whereas the positive HU of iodine decreased across all contrast concentrations and phantom sizes. CT numbers for DBCM decreased from -178.5±9.6 to -194.4±6.3 HU (small phantom) and from -181.7±15.7 to -192.1±11.9 HU (large phantom) for DBCM-12% from 90 to Sn140 kV; on VMIs, the CT numbers for DBCM decreased minimally from -147.1±15.7 to -185.1±9.2 HU (small phantom) and -158.8±28.6 to -188.9±14.7 HU (large phantom) from 40 to 70keV, but remained stable from 80 to 140keV. The highest iodine CNR against DBCM in low-energy threshold images was seen at 90 or Sn140 kV for the small phantom, whereas all CNR values from low-energy threshold images for the large phantom were comparable. The CNR values of iodine against DBCM computed on VMIs were highest at 40 or 70keV depending on iodine and DBCM concentrations. The CNR values of iodine against DBCM were consistently higher than iodine to water (up to 460% higher dependent on energy level). Further, the CNR of iodine compared to DBCM is less affected by VMI energy level than the identical comparison between iodine and water: CNR values at 140keV were reduced by 46.6% (small phantom) or 42.6% (large phantom) compared to 40keV; CNR values for iodine compared to water were reduced by 86.3% and 83.8% for similar phantom sizes, respectively. Compared to 70keV VMI, the iodine CNR against DBCM was 13%-79% lower on iodine maps and VNC. When evaluated at different tube potentials and VMI energy levels using a clinical PCD-CT system, DBCM showed consistently higher CNR compared to iodine versus water (a neutral contrast).

Monte Carlo model of a prototype flat-panel detector for multi-energy applications in radiotherapy.

The incorporation of multi-energy capabilities into radiotherapy flat-panel detectors offers advantages including enhanced soft tissue visualization by reduction of signal from overlapping anatomy such as bone in 2D image projections; creation of virtual monoenergetic images for 3D contrast enhancement, metal artefact reduction and direct acquisition of relative electron density. A novel dual-layer on-board imager offering dual energy processing capabilities is being designed. As opposed to other dual-energy implementation techniques which require separate acquisition with two different x-ray spectra, the dual-layer detector design enables simultaneous acquisition of high and low energy images with a single exposure. A computational framework is required to optimize the design parameters and evaluate detector performance for specific clinical applications. In this study, we report on the development of a Monte Carlo (MC) model of the imager including model validation. The stack-up of the dual-layer imager (DLI) was implemented in GEANT4 Application for Tomographic Emission (GATE). The DLI model has an active area of 43×43 cm2 , with top and bottom Cesium Iodide (CsI) scintillators of 600 and 800μm thickness, respectively. Measurement of spatial resolution and imaging of dedicated multi-material dual-energy (DE) phantoms were used to validate the model. The modulation transfer function (MTF) of the detector was calculated for a 120 kVp x-ray spectrum using a 0.5mm thick tantalum edge rotated by 2.5o . For imaging validation, the DE phantom was imaged using a 140 kVp x-ray spectrum. For both validation simulations, corresponding measurements were done using an initial prototype of the imager. Agreement between simulations and measurement was assessed using normalized root mean square error (NRMSE) and 1D profile difference for the MTF and phantom images respectively. Further comparison between measurement and simulation was made using virtual monoenergetic images (VMIs) generated from basis material images derived using precomputed look-up tables. The MTF of the bottom layer of the dual-layer model shows values decreasing more quickly with spatial frequency, compared to the top layer, due to the thicker bottom scintillator thickness and scatter from the top layer. A comparison with measurement shows NRMSE of 0.013 and 0.015 as well as identical MTF50 of 0.8 mm1 and 1.0 mm1 for the top and bottom layer respectively. For the DE imaging of the DE-phantom, although a maximum deviation of 3.3% is observed for the 10mm aluminum and Teflon inserts at the top layer, the agreement for all other inserts is less than 2.2% of the measured value at both layers. Material decomposition of simulated scatter-free DE images gives an average accuracy in PMMA and aluminum composition of 4.9% and 10.3% for 11-30mm PMMA and 1-10mm aluminum objects respectively. A comparison of decomposed values using scatter containing measured and simulated DE images shows good agreement within statistical uncertainty. Validation using both MTF and phantom imaging shows good agreement between simulation and measurements. With the present configuration of the digital prototype, the model can generate material decomposed images and virtual monoenergetic images.

Breast cancer diagnosis from contrast-enhanced mammography using multi-feature fusion neural network.

To develop an end-to-end deep neural network for the classification of contrast-enhanced mammography (CEM) images to facilitate breast cancer diagnosis in the clinic. In this retrospective mono-centric study, patients who underwent CEM examinations from January 2019 to August 2021 were enrolled. A multi-feature fusion network combining low-energy (LE) and dual-energy subtracted (DES) images and dual view, as well as bilateral information, was trained and tested using a large CEM dataset with a diversity of breast tumors for breast lesion classification. Its generalization performance was further evaluated on two external datasets. Results were reported using AUC, accuracy, sensitivity, and specificity. A total of 2496 patients (mean age, 53 years ± 12 (standard deviation)) were included and divided into a training set (1718), a validation set (255), and a testing set (523). The proposed CEM-based multi-feature fusion network achieved the best diagnosis performance with an AUC of 0.96 (95% confidence interval (CI): 0.95, 0.97), compared with the no-fusion model, the left-right fusion model, and the multi-feature fusion network with only LE image inputs. Our models reached an AUC of 0.90 (95% CI: 0.85, 0.94) on a full-field digital mammograph (FFDM) external dataset (86 patients), and an AUC of 0.92 (95% CI: 0.89, 0.95) on a CEM external dataset (193 patients). The developed multi-feature fusion neural network achieved high performance in CEM image classification and was able to facilitate CEM-based breast cancer diagnosis. Compared with low-energy images, CEM images have greater sensitivity and similar specificity in malignant breast lesion detection. The multi-feature fusion neural network is a promising computer-aided diagnostic tool for the clinical diagnosis of breast cancer. • Deep convolutional neural networks have the potential to facilitate contrast-enhanced mammography-based breast cancer diagnosis. • The multi-feature fusion neural network reaches high accuracies in the classification of contrast-enhanced mammography images. • The developed model is a promising diagnostic tool to facilitate clinical breast cancer diagnosis.

Dual-Energy CT for Pediatric Thoracic Imaging: A Review.

Dual-energy CT has expanded the potential of thoracic imaging in both children and adults. Data processing allows material- and energy-specific reconstructions, which improve material differentiation and tissue characterization compared with single-energy CT. Material-specific reconstructions include iodine, virtual unenhanced, perfusion blood volume, and lung vessel images, which can improve assessment of vascular, mediastinal, and parenchymal abnormalities. The energy-specific reconstruction algorithm allows virtual monoenergetic reconstructions, including low-energy images to increase iodine conspicuity and high-energy images to reduce beam-hardening and metal artifacts. This review highlights dual-energy CT principles, hardware, and postprocessing algorithms; the clinical applications of dual-energy CT; and the potential benefits of photon counting (the most recently introduced iteration of spectral imaging) in pediatric thoracic imaging.

Impact of virtual monoenergetic levels on coronary plaque volume components using photon-counting computed tomography

ObjectivesVirtual monoenergetic images (VMIs) from photon-counting CT (PCCT) may change quantitative coronary plaque volumes. We aimed to assess how plaque component volumes change with respect to VMIs.MethodsCoronary CT angiography (CTA) images were acquired using a dual-source PCCT and VMIs were reconstructed between 40 and 180 keV in 10-keV increments. Polychromatic images at 120 kVp (T3D) were used as reference. Quantitative plaque analysis was performed on T3D images and segmentation masks were copied to VMI reconstructions. Calcified plaque (CP; > 350 Hounsfield units, HU), non-calcified plaque (NCP; 30 to 350 HU), and low-attenuation NCP (LAP; − 100 to 30 HU) volumes were calculated using fixed thresholds.ResultsWe analyzed 51 plaques from 51 patients (67% male, mean age 65 ± 12 years). Average attenuation and contrast-to-noise ratio (CNR) decreased significantly with increasing keV levels, with similar values observed between T3D and 70 keV images (299 ± 209 vs. 303 ± 225 HU, p = 0.15 for mean HU; 15.5 ± 3.7 vs. 15.8 ± 3.5, p = 0.32 for CNR). Mean NCP volume was comparable between T3D and 100–180-keV reconstructions. There was a monotonic decrease in mean CP volume, with a significant difference between all VMIs and T3D (p < 0.05). LAP volume increased with increasing keV levels and all VMIs showed a significant difference compared to T3D, except for 50 keV (28.0 ± 30.8 mm3 and 28.6 ± 30.1 mm3, respectively, p = 0.63).ConclusionsEstimated coronary plaque volumes significantly differ between VMIs. Normalization protocols are needed to have comparable results between future studies, especially for LAP volume which is currently defined using a fixed HU threshold.Clinical relevance statementDifferent virtual monoenergetic images from photon-counting CT alter attenuation values and therefore corresponding plaque component volumes. New clinical standards and protocols are required to determine the optimal thresholds to derive plaque volumes from photon-counting CT.Key Points• Utilizing different VMI energy levels from photon-counting CT for the analysis of coronary artery plaques leads to substantial changes in attenuation values and corresponding plaque component volumes.• Low-energy images (40–70 keV) improved contrast-to-noise ratio, however also increased image noise.• Normalization protocols are needed to have comparable results between future studies, especially for low-attenuation plaque volume which is currently defined using a fixed HU threshold.

Radiomics of contrast-enhanced spectral mammography for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer.

Neoadjuvant chemotherapy (NAC) has been regarded as one of the standard treatments for patients with locally advanced breast cancer. No previous study has investigated the feasibility of using a contrast-enhanced spectral mammography (CESM)-based radiomics nomogram to predict pathological complete response (pCR) after NAC. To develop and validate a CESM-based radiomics nomogram to predict pCR after NAC in breast cancer. A total of 118 patients were enrolled, which are divided into a training dataset including 82 patients (with 21 pCR and 61 non-pCR) and a testing dataset of 36 patients (with 9 pCR and 27 non-pCR). The tumor regions of interest (ROIs) were manually segmented by two radiologists on the low-energy and recombined images and radiomics features were extracted. Intraclass correlation coefficients (ICCs) were used to assess the intra- and inter-observer agreements of ROI features extraction. In the training set, the variance threshold, SelectKBest method, and least absolute shrinkage and selection operator regression were used to select the optimal radiomics features. Radiomics signature was calculated through a linear combination of selected features. A radiomics nomogram containing radiomics signature score (Rad-score) and clinical risk factors was developed. The receiver operating characteristic (ROC) curve and calibration curve were used to evaluate prediction performance of the radiomics nomogram, and decision curve analysis (DCA) was used to evaluate the clinical usefulness of the radiomics nomogram. The intra- and inter- observer ICCs were 0.769-0.815 and 0.786-0.853, respectively. Thirteen radiomics features were selected to calculate Rad-score. The radiomics nomogram containing Rad-score and clinical risk factor showed an encouraging calibration and discrimination performance with area under the ROC curves of 0.906 (95% confidence interval (CI): 0.840-0.966) in the training dataset and 0.790 (95% CI: 0.554-0.952) in the test dataset. The CESM-based radiomics nomogram had good prediction performance for pCR after NAC in breast cancer; therefore, it has a good clinical application prospect.

Combining Deep Learning and Handcrafted Radiomics for Classification of Suspicious Lesions on Contrast-enhanced Mammograms.

Background Handcrafted radiomics and deep learning (DL) models individually achieve good performance in lesion classification (benign vs malignant) on contrast-enhanced mammography (CEM) images. Purpose To develop a comprehensive machine learning tool able to fully automatically identify, segment, and classify breast lesions on the basis of CEM images in recall patients. Materials and Methods CEM images and clinical data were retrospectively collected between 2013 and 2018 for 1601 recall patients at Maastricht UMC+ and 283 patients at Gustave Roussy Institute for external validation. Lesions with a known status (malignant or benign) were delineated by a research assistant overseen by an expert breast radiologist. Preprocessed low-energy and recombined images were used to train a DL model for automatic lesion identification, segmentation, and classification. A handcrafted radiomics model was also trained to classify both human- and DL-segmented lesions. Sensitivity for identification and the area under the receiver operating characteristic curve (AUC) for classification were compared between individual and combined models at the image and patient levels. Results After the exclusion of patients without suspicious lesions, the total number of patients included in the training, test, and validation data sets were 850 (mean age, 63 years ± 8 [SD]), 212 (62 years ± 8), and 279 (55 years ± 12), respectively. In the external data set, lesion identification sensitivity was 90% and 99% at the image and patient level, respectively, and the mean Dice coefficient was 0.71 and 0.80 at the image and patient level, respectively. Using manual segmentations, the combined DL and handcrafted radiomics classification model achieved the highest AUC (0.88 [95% CI: 0.86, 0.91]) (P < .05 except compared with DL, handcrafted radiomics, and clinical features model, where P = .90). Using DL-generated segmentations, the combined DL and handcrafted radiomics model showed the highest AUC (0.95 [95% CI: 0.94, 0.96]) (P < .05). Conclusion The DL model accurately identified and delineated suspicious lesions on CEM images, and the combined output of the DL and handcrafted radiomics models achieved good diagnostic performance. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Bahl and Do in this issue.

An efficient hybrid computer-aided breast cancer diagnosis system with wavelet packet transform and synthetically-generated contrast-enhanced spectral mammography images

Contrast-enhanced spectral mammography (CESM) is an emerging modality for breast cancer diagnosis. This work investigates the feasibility of a computationally-efficient computer-aided diagnosis (CAD) system for breast lesion classification. Moreover, to avoid the need for intravenous contrast agents, we investigated the synthesis of contrast-enhanced (SynCESM) images. A total of 504 pairs of low-energy (LE) and CESM images were collected from 160 female subjects. A semi-automatic active-contour method was used for lesion segmentation. Then, 20 morphological and textural features were extracted. To improve the computational efficiency of the proposed system, the wavelet packet transform (WPT) was applied. Then, the same features were extracted from the WPT-approximated segmented lesions. Using LE images, a sigmoid-kernel SVM classifier exhibited a 90.20% accuracy, an 88.39% sensitivity, an 88.26% specificity, and a 0.92 AUC. The per-frame classification time was significantly reduced from 1.1046 s to 0.0734 s with WPT. Using CESM images, we achieved a 93.26% accuracy, a 95.94% sensitivity, a 93.37% specificity, a 0.94 AUC, and a 0.0657 s classification time. Interestingly, with SynCESM images, reasonable performance was still obtained with a 92.14% accuracy, a 93.87% sensitivity, a 91.58% specificity, a 0.93 AUC and a 0.0657 s classification time. Finally, with hybrid pairs of LE and CESM images, we got the best performance with a 96.87% accuracy, a 97.23% sensitivity, a 95.47% specificity, a 0.98 AUC, and a 0.0696 s classification time. The results demonstrate several advantages of the proposed system including its clinical feasibility, lower complexity, and reduced need for contrast agents via synthetic data generation.

Deep-learning convolutional neural network-based scatter correction for contrast enhanced digital breast tomosynthesis in both cranio-caudal and mediolateral-oblique views.

Scatter radiation in contrast-enhanced digital breast tomosynthesis (CEDBT) reduces the image quality and iodinated lesion contrast. Monte Carlo simulation can provide accurate scatter estimation at the cost of computational burden. A model-based convolutional method trades off accuracy for processing speed. The purpose of this study is to develop a fast and robust deep-learning (DL) convolutional neural network (CNN)-based scatter correction method for CEDBT. Projection images and scatter maps of digital anthropomorphic breast phantoms were generated using Monte Carlo simulations. Experiments were conducted to validate the simulated scatter-to-primary ratio (SPR) at different locations of a breast phantom. Simulated projection images were used for CNN training and testing. Two separate U-Nets [low-energy (LE)-CNN and high-energy (HE)-CNN] were trained for LE and HE spectrum, respectively. CNN-based scatter correction was applied to a clinical case with a malignant iodinated mass to evaluate the influence on the lesion detection. The average and standard deviation of mean absolute percentage error of LE-CNN and HE-CNN estimated scatter map are and , respectively. For clinical cases, the lesion signal difference to noise ratio average improvement was 190% after CNN-based scatter correction. To conduct scatter correction on clinical CEDBT images, the whole process of loading CNNs parameters and scatter correction for LE and HE images took , with 9GB GPU computational cost. The SPR variation across the breast agrees between experimental measurements and Monte Carlo simulations. We developed a CNN-based scatter correction method for CEDBT in both CC view and mediolateral-oblique view with high accuracy and fast speed.

Breast Imaging Reporting and Data System and Contrast Enhancement Mammography: Lesion Conspicuity Likelihood of Malignancy and Relationship With Breast Tumor Receptor Status

The new version of the Contrast Enhanced Mammography (CEM) Breast imaging Reporting and Data System (BIRADs) encourages investigations of a new enhancement descriptor: "Lesion Conspicuity" (LC). The study aims to assess the diagnostic performance and the relationship with the receptor profile of this new enhancement descriptor. Three hundred twenty-five patients with 381 breast lesions who underwent CEM before histological assessmentwere selected. Four radiologists, blinded to each other, categorized LC into the following levels: absent, low, moderate, and high. Considering moderate and high evaluations as predictive of malignancy, the diagnostic performance of CEM was calculated using histological results of the biopsy as the gold standard. The association between LC values and the receptor profile of the neoplasms was also evaluated. The median age at the CEM examination was 50 years (IQR: 45-59). Considering the value of LC of the most experienced radiologist with the interpretation of Low Energy images (LE), we obtained a sensitivity (SE) of 91.9% (95% CI: 88.6%-95.2%) and a specificity (SP) of 67.2% (95% CI: 58.9%-75.5%). An association between "high" lesion conspicuity with ER/PgR not expressed (p=0.025), with Ki-67>20% (p=0.033), and with Grading G3 (p=0.020) was observed. The new feature of enhancement, "Lesion Conspicuity", demonstrated satisfactory performance in predicting the malignancy of lesions and significant correlation with the receptor profile of malignant breast neoplasms.

Contrast Enhanced Mammography (CEM) Enhancing Asymmetry: Single-Center First Case Analysis

(1) Purpose: The latest Breast Imaging Reporting and Data System (BI-RADS) lexicon for CEM introduced a new descriptor, enhancing asymmetries (EAs). The purpose of this study was to determine which types of lesions were correlated with EAs. (2) Methods: A total of 3359 CEM exams, executed at AOUC Careggi in Florence, Italy between 2019 and 2021 were retrospectively assessed by two radiologists. For each of the EAs found, the size, the enhancing conspicuity (degree of enhancement relative to background described as low, moderate, or high), whether there was a corresponding finding in the traditional radiology images (US or mammography), the biopsy results when performed including any follow-up exams, and the presence of background parenchymal enhancement (BPE) of the normal breast tissue (minimal, mild, moderate, marked) were described. (3) Results: A total of 64 women were included, 36 of them underwent CEM for a preoperative staging assessment, and 28 for a problem-solving examination. Among the 64 EAs, 19/64 (29.69%) resulted in being category B5 (B5) lesions, 5/64 (7.81%) as category B3 (B3) lesions, and 40/64(62.50%) were negative or benign either after biopsy or second-look exams or follow-up. We assessed that EAs with higher enhancing conspicuity correlated significantly with a higher risk of B5 lesions (p: 0.0071), especially bigger ones (p: 0.0274). Conclusions: EAs can relate both with benign and tumoral lesions, and they need to be assessed as the other CEM descriptors, with re-evaluation of low-energy images and second-look exams, particularly larger EAs with higher enhancing conspicuity.

Accuracy and precision of contrast enhanced mammography versus MRI for predicting breast cancer size: how "good" are they really?

To evaluate and compare the accuracy and precision of contrast-enhanced mammography (CEM) vs MRI to predict the size of biopsy-proven invasive breast cancer. Prospective study, 59 women with invasive breast cancer on needle biopsy underwent CEM and breast MRI. Two breast radiologists read each patient's study, with access limited to one modality. CEM lesion size was measured using low-energy and recombined images and on MRI, the first post-contrast series. Extent of abnormality per quadrant was measured for multifocal lesions. Reference standards were size of largest invasive malignant lesion, invasive (PathInvasive) and whole (PathTotal). Pre-defined clinical concordance ±10 mm. Mean patient age 56 years, 42 (71%) asymptomatic. Lesions were invasive ductal carcinoma 40 (68%) with ductal carcinoma in situ (31/40) in 78%, multifocal in 12 (20%). Median lesion size was 17 mm (invasive) and 27 mm (total), range (5-125 mm). Lin's concordance correlation coefficients for PathTotal 0.75 (95% CI 0.6, 0.84) and 0.71 (95% CI 0.56, 0.82) for MRI and contrast-enhanced spectral mammography (CESM) respectively. Mean difference for total size, 3% underestimated and 4% overestimated, and for invasive 41% and 50% overestimate on MRI and CESM respectively. LOAs for PathTotal varied from 60% under to a 2.4 or almost threefold over estimation. MRI was concordant with PathTotal in 36 (64%) cases compared with 32 (57%) for CESM. Both modalities concordant in 26 (46%) cases respectively. Neither CEM nor MRI have sufficient accuracy to direct changes in planned treatment without needle biopsy confirmation. Despite small mean differences in lesion size estimates using CEM or MRI, the 95% limits of agreement do not meet clinically acceptable levels.

Deformable registration with intensity correction for CESM monitoring response to Neoadjuvant Chemotherapy

This paper proposes a robust longitudinal registration method for Contrast Enhanced Spectral Mammography in monitoring neoadjuvant chemotherapy. Because breast texture intensity changes with the treatment, a non-rigid registration procedure with local intensity compensations is developed. The approach allows registering the low energy images of the exams acquired before and after the chemotherapy. The measured motion is then applied to the corresponding recombined images. The difference of registered images, called residual, makes vanishing the breast texture that did not changed between the two exams. Consequently, this registered residual allows identifying local density and iodine changes, especially in the lesion area. The method is validated with a synthetic NAC case where ground truths are available. Then the procedure is applied to 51 patients with 208 CESM image pairs acquired before and after the chemotherapy treatment. The proposed registration converged in all 208 cases. The intensity-compensated registration approach is evaluated with different mathematical metrics and through the repositioning of clinical landmarks (RMSE: 5.9 mm) and outperforms state-of-the-art registration techniques.

Contrast-enhanced mammography in the assessment of residual disease after neoadjuvant treatment.

To investigate the utility of contrast-enhanced mammography (CEM) as an alternative to breast MRI for the evaluation of residual disease after neoadjuvant treatment (NAT). This prospective study enrolled consecutive women undergoing NAT for breast cancer from July 2017-July 2019. Breast MRI and CEM exams performed after completion of NAT were read independently by two breast radiologists. Residual disease and lesion size on MRI and CEM recombined (RI) and low-energy images (LEI) were compared. Histopathology was considered the reference standard. Statistical analysis was performed using McNemar's and Leisenring's tests. Multiple comparison adjustment was made using Bonferroni procedure. Lesion sizes were correlated using Kendall's tau coefficient. There were 110 participants with 115 breast cancers. Residual disease (invasive cancer or ductal carcinoma in situ) was detected in 83/115 (72%) lesions on pathology, 71/115 (62%) on MRI, 55/115 (48%) on CEM RI, and 75/115 (65%) on CEM LEI. When using multiple comparison adjustment, no significant differences were detected between MRI combined with CEM LEI and CEM RI combined with CEM LEI, in terms of accuracy (MRI: 77%, CEM: 72%; p ≥ 0.99), sensitivity (MRI: 88%, CEM: 81%; p ≥ 0.99), specificity (MRI: 47%, CEM: 50%; p ≥ 0.99), PPV (MRI: 81%, CEM: 81%; p ≥ 0.99), or NPV (MRI: 60%, CEM: 50%; p ≥ 0.99). Size correlation between pathology and both MRI combined with CEM LEI and CEM RI combined with CEM LEI was moderate: τ = 0. 36 vs 0.33 (p ≥ 0.99). Contrast-enhanced mammography is an acceptable alternative to breast MRI for the detection of residual disease after neoadjuvant treatment.