Journal of Medical Imaging最新文献

Purpose: We characterize the flying focal spot (FFS) technology in digital breast tomosynthesis (DBT), designed to overcome source motion blurring.

Approach: A wide-angle DBT system with continuous gantry and focus motion ("uncompensated focus") and a system with FFS were compared for image sharpness and lesion detectability. The modulation transfer function (MTF) was assessed as a function of height in the projections and reconstructed images, along with lesion detectability using the contrast detail phantom for mammography (CDMAM) and the L1 phantom.

Results: For the uncompensated focus system, the spatial frequency for 25% MTF value ( $f_{25\%}$ ) measured at 2, 4, and 6 cm in DBT projections fell by 35%, 49%, and 59%, respectively in the tube-travel direction compared with the FFS system. There was no significant difference in $f_{25\%}$ for the front-back and tube-travel directions for the FFS unit. The in-plane MTF in the tube-travel direction also improved with the FFS technology.The threshold gold thickness ( $T_t$ ) for the 0.16-mm diameter discs of contrast detail phantom for mammography (CDMAM) improved for the FFS system in DBT mode, especially at greater heights above the table; $T_t$ at 45 and 65 mm improved by 16% and 24%, respectively, compared with the uncompensated focus system. In addition, improvements in calcification and mass detection in a structured background were observed for DBT and synthetic mammography. The FFS system demonstrated faster scan times (4.8 s versus 21.7 s), potentially reducing patient motion artifacts.

Conclusions: The FFS technology offers isotropic resolution, improved small detail detectability, and faster scan times in DBT mode compared with the traditional continuous gantry and focus motion approach.

Purpose: We investigated the feasibility and advantages of using non-contrast CT calcium score (CTCS) images to assess pericoronary adipose tissue (PCAT) and its association with major adverse cardiovascular events (MACE). PCAT features from coronary computed tomography angiography (CCTA) have been shown to be associated with cardiovascular risk but are potentially confounded by iodine. If PCAT in CTCS images can be similarly analyzed, it would avoid this issue and enable its inclusion in formal risk assessment from readily available, low-cost CTCS images.

Approach: To identify coronaries in CTCS images that have subtle visual evidence of vessels, we registered CTCS with paired CCTA images having coronary labels. We developed an "axial-disk" method giving regions for analyzing PCAT features in three main coronary arteries. We analyzed hand-crafted and radiomic features using univariate and multivariate logistic regression prediction of MACE and compared results against those from CCTA.

Results: Registration accuracy was sufficient to enable the identification of PCAT regions in CTCS images. Motion or beam hardening artifacts were often prevalent in "high-contrast" CCTA but not CTCS. Mean HU and volume were increased in both CTCS and CCTA for the MACE group. There were significant positive correlations between some CTCS and CCTA features, suggesting that similar characteristics were obtained. Using hand-crafted/radiomics from CTCS and CCTA, AUCs were 0.83/0.79 and 0.83/0.77, respectively, whereas Agatston gave AUC = 0.73.

Conclusions: Preliminarily, PCAT features can be assessed from three main coronary arteries in non-contrast CTCS images with performance characteristics that are at the very least comparable to CCTA.

Thanks to reviewers who served the Journal of Medical Imaging in 2024.

Purpose: The restoration of images affected by blur and noise has been widely studied and has broad potential for applications including in medical imaging modalities such as computed tomography. Recently, deep learning approaches have demonstrated the potential to enhance image quality beyond classic limits; however, most deep learning models attempt a blind restoration problem and base their restoration on image inputs alone without direct knowledge of the image noise and blur properties. We present a method that leverages both degraded image inputs and a characterization of the system's blur and noise to combine modeling and deep learning approaches.

Approach: Different methods to integrate these auxiliary inputs are presented, namely, an input-variant and a weight-variant approach wherein the auxiliary inputs are incorporated as a parameter vector before and after the convolutional block, respectively, allowing easy integration into any convolutional neural network architecture.

Results: The proposed model shows superior performance compared with baseline models lacking auxiliary inputs. Evaluations are based on the average peak signal-to-noise ratio and structural similarity index measure, selected examples of top and bottom 10% performance for varying approaches, and an input space analysis to assess the effect of different noise and blur on performance. In addition, the proposed model exhibits a degree of robustness when the blur and noise parameters deviate from their true values.

Conclusion: Results demonstrate the efficacy of providing a deep learning model with auxiliary inputs, representing system blur and noise characteristics, to enhance the performance of the model in image restoration tasks.

Purpose: Conventional metrics used for assessing digital mammography (DM) and digital breast tomosynthesis (DBT) image quality, including noise, spatial resolution, and detective quantum efficiency, do not necessarily predict how well the system will perform in a clinical task. A number of existing phantom-based methods have their own limitations, such as unrealistic uniform backgrounds, subjective scoring using humans, and regular signal patterns unrepresentative of common clinical findings. We attempted to address this problem with a realistic breast phantom with random hydroxyapatite microcalcifications and semi-automated deep learning-based image scoring. Our goal was to develop a methodology for objective task-based assessment of image quality for tomosynthesis and DM systems, which includes an anthropomorphic phantom, a detection task (microcalcification clusters), and automated performance evaluation using a convolutional neural network.

Approach: Experimental 2D and pseudo-3D mammograms of an anthropomorphic inkjet-printed breast phantom with inserted microcalcification clusters were collected on clinical mammography systems to train a signal-present/signal-absent image classifier based on Resnet-18 architecture. In a separate validation study using simulations, this Resnet-18 classifier was shown to approach the performance of an ideal observer. Microcalcification detection performance was evaluated as a function of four dose levels using receiver operating characteristic (ROC) analysis [i.e., area under the ROC curve (AUC)]. To demonstrate the use of this evaluation approach for assessing different technologies, the method was applied to two different mammography systems, as well as to mammograms with re-binned pixels emulating a lower-resolution X-ray detector.

Results: Microcalcification detectability, as assessed by the deep learning classifier, was observed to vary with the exposure incident on the breast phantom for both DM and tomosynthesis. At full dose, experimental AUC was 0.96 (for DM) and 0.95 (for DBT), whereas at half dose, it dropped to 0.85 and 0.71, respectively. AUC performance on DM was significantly decreased with an effective larger pixel size obtained with re-binning. The task-based assessment approach also showed the superiority of a newer mammography system compared with an older system.

Conclusions: An objective task-based methodology for assessing the image quality of mammography and tomosynthesis systems is proposed. Possible uses for this tool could be quality control, acceptance, and constancy testing, assessing the safety and effectiveness of new technology for regulatory submissions, and system optimization. The results from this study showed that the proposed evaluation method using a deep learning model observer can track differences in microcalcification signal detectability with varied exposure conditions.

Purpose: The purpose is to describe the Malmö Breast Tomosynthesis Screening Project from the beginning to where we are now, and thoughts for the future.

Approach: In two acts, we describe the efforts made by our research group to improve breast cancer screening by introducing digital breast tomosynthesis (DBT), all the way from initial studies to a large prospective population-based screening trial and beyond.

Results: Our studies have shown that DBT has significant advantages over digital mammography (DM), the current gold standard method for breast cancer screening in Europe, in many aspects except a major one-the increased radiologist workload introduced with DBT compared with DM. It is foreseen that AI could be a viable solution to overcome this problem.

Conclusions: We have proved that one-view DBT is a highly efficient screening approach with respect to diagnostic performance.

Purpose: Use of mechanical imaging (MI) as complementary to digital mammography (DM), or in simultaneous digital breast tomosynthesis (DBT) and MI - DBTMI, has demonstrated the potential to increase the specificity of breast cancer screening and reduce unnecessary biopsies compared with DM. The aim of this study is to investigate the increase in the radiation dose due to the presence of an MI sensor during simultaneous image acquisition when automatic exposure control is used.

Approach: A radiation dose study was conducted on clinically available breast imaging systems with and without an MI sensor present. Our estimations were based on three approaches. In the first approach, exposure values were compared in paired clinical DBT and DBTMI acquisitions in 97 women. In the second approach polymethyl methacrylate (PMMA) phantoms of various thicknesses were used, and the average glandular dose (AGD) values were compared. Finally, a rectangular PMMA phantom with a 45 mm thickness was used, and the AGD values were estimated based on air kerma measurements with an electronic dosemeter.

Results: The relative increase in exposure estimated from digital imaging and communications in medicine headers when using an MI sensor in clinical DBTMI was $11.9\%\pm 10.4$ . For the phantom measurements of various thicknesses of PMMA, the relative increases in the AGD for DM and DBT measurements were, on average, $10.7\%\pm 3.1$ and $11.4\%\pm 3.0$ , respectively. The relative increase in the AGD using the electronic dosemeter was $11.2\%\pm <0.001$ in DM and $12.2\%\pm <0.001$ in DBT. The average difference in dose between the methods was $11.5\%\pm 3.3$ .

Conclusions: Our measurements suggest that the use of simultaneous breast radiography and MI increases the AGD by an average of $11.5\%\pm 3.3$ . The increase in dose is within the acceptable values for mammography screening recommended by European guidelines.

Purpose: The prevalence of type 2 diabetes mellitus (T2DM) has been steadily increasing over the years. We aim to predict the occurrence of T2DM using mammography images within 5 years using two different methods and compare their performance.

Approach: We examined 312 samples, including 110 positive cases (developed T2DM after 5 years) and 202 negative cases (did not develop T2DM) using two different methods. In the first method, a radiomics-based approach, we utilized radiomics features and machine learning (ML) algorithms. The entire breast region was chosen as the region of interest for extracting radiomics features. Then, a binary breast image was created from which we extracted 668 features and analyzed them using various ML algorithms. In the second method, a complex convolutional neural network (CNN) with a modified ResNet architecture and various kernel sizes was applied to raw mammography images for the prediction task. A nested, stratified five-fold cross-validation was done for both parts A and B to compute accuracy, sensitivity, specificity, and area under the receiver operating curve (AUROC). Hyperparameter tuning was also done to enhance the model's performance and reliability.

Results: The radiomics approach's light gradient boosting model gave 68.9% accuracy, 30.7% sensitivity, 89.5% specificity, and 0.63 AUROC. The CNN method achieved an AUROC of 0.58 over 20 epochs.

Conclusion: Radiomics outperformed CNN by 0.05 in terms of AUROC. This may be due to the more straightforward interpretability and clinical relevance of predefined radiomics features compared with the complex, abstract features learned by CNNs.

Purpose: Diffusion magnetic resonance imaging (dMRI) quantitatively estimates brain microstructure, diffusion tractography being one clinically utilized framework. To advance such dMRI approaches, direct quantitative comparisons between microscale anisotropy and orientation are imperative. Complete backscattering Mueller matrix polarized light imaging (PLI) enables the imaging of thin and thick tissue specimens to acquire numerous optical metrics not possible through conventional transmission PLI methods. By comparing complete PLI to dMRI within the ferret optic chiasm (OC), we may investigate the potential of this PLI technique as a dMRI validation tool and gain insight into the microstructural and orientational sensitivity of this imaging method in different tissue thicknesses.

Approach: Post-mortem ferret brain tissue samples (whole brain, $n=1$ and OC, $n=3$ ) were imaged with both dMRI and complete backscattering Mueller matrix PLI. The specimens were sectioned and then reimaged with PLI. Region of interest and correlation analyses were performed on scalar metrics and orientation vectors of both dMRI and PLI in the coherent optic nerve and crossing chiasm.

Results: Optical retardance and dMRI fractional anisotropy showed similar trends between metric values and were strongly correlated, indicating a bias to macroscale architecture in retardance. Thick tissue displays comparable orientation between the diattenuation angle and dMRI fiber orientation distribution glyphs that are not evident in the retardance angle.

Conclusions: We demonstrate that backscattering Mueller matrix PLI shows potential as a tool for microstructural dMRI validation in thick tissue specimens. Performing complete polarimetry can provide directional characterization and potentially microscale anisotropy information not available by conventional PLI alone.

Purpose: Digital phantoms are one of the key components of virtual imaging trials (VITs) that aim to assess and optimize new medical imaging systems and algorithms. However, these phantoms vary in their voxel resolution, appearance, and structural details. We investigate whether and how variations between digital phantoms influence system optimization with digital breast tomosynthesis (DBT) as a chosen modality.

Methods: We selected widely used and open-access digital breast phantoms created with different methods and generated an ensemble of DBT images to test acquisition strategies. Human observer performance was evaluated using localization receiver operating characteristic (LROC) studies for each phantom type. Noise power spectrum and gaze metrics were also employed to compare phantoms and generated images.

Results: Our LROC results show that the arc samplings for peak performance were $\sim 2.5\mathrm{deg}$ and 6 deg in Bakic and XCAT breast phantoms, respectively, for the 3-mm lesion detection task and indicate that system optimization outcomes from VITs can vary with phantom types and structural frequency components. In addition, a significant correlation ( $p<0.01$ ) between gaze metrics and diagnostic performance suggests that gaze analysis can be used to understand and evaluate task difficulty in VITs.

Conclusion: Our results point to the critical need to evaluate realism in digital phantoms and ensure sufficient structural variations at spatial frequencies relevant to the intended task. Standardizing phantom generation and validation tools may help reduce discrepancies among independently conducted VITs for system or algorithmic optimizations.