Monitoring Methodology for an AI Tool for Breast Cancer Screening Deployed in Clinical Centers.

We propose a methodology for monitoring an artificial intelligence (AI) tool for breast cancer screening when deployed in clinical centers. An AI trained to detect suspicious regions of interest in the four views of a mammogram and to characterize their level of suspicion with a score ranging from one (low suspicion) to ten (high suspicion of malignancy) was deployed in four radiological centers across the US. Results were collected between April 2021 and December 2022, resulting in a dataset of 36,581 AI records. To assess the behavior of the AI, its score distribution in each center was compared to a reference distribution obtained in silico using the Pearson correlation coefficient (PCC) between each center AI score distribution and the reference. The estimated PCCs were 0.998 [min: 0.993, max: 0.999] for center US-1, 0.975 [min: 0.923, max: 0.986] for US-2, 0.995 [min: 0.972, max: 0.998] for US-3 and 0.994 [min: 0.962, max: 0.982] for US-4. These values show that the AI behaved as expected. Low PCC values could be used to trigger an alert, which would facilitate the detection of software malfunctions. This methodology can help create new indicators to improve monitoring of software deployed in hospitals.

Comparison of propagation-based CT using synchrotron radiation and conventional cone-beam CT for breast imaging.

OBJECTIVES: To evaluate and compare the image quality of propagation-based phase-contrast computed tomography (PB-CT) using synchrotron radiation and conventional cone-beam breast computed tomography (CBBCT) based on various radiological image quality criteria. METHODS: Eight excised breast tissue samples of various sizes and containing different lesion types were scanned using PB-CT at a synchrotron facility and using CBBCT at a university-affiliated breast imaging centre. PB-CT scans were performed at two different mean glandular dose (MGD) levels: standard (5.8 mGy) and low (1.5 mGy), for comparison with CBBCT scans at the standard MGD (5.8 mGy). Image quality assessment was carried out using six quality criteria and six independent medical imaging experts in a reading room with mammography workstations. The interobserver agreement between readers was evaluated using intraclass correlation coefficient (ICC), and image quality was compared between the two breast imaging modalities using the area under the visual grading characteristic curve (AUCVGC). RESULTS: Interobserver agreement between the readers showed moderate reliability for five image criteria (ICC: ranging from 0.488 to 0.633) and low reliability for one criterion (image noise) (ICC 0.307). For five image quality criteria (overall quality, perceptible contrast, lesion sharpness, normal tissue interfaces, and calcification visibility), both standard-dose PB-CT images (AUCVGC 0.958 to 1, p ≤ .05) and low dose PB-CT images (AUCVGC 0.785 to 0.834, p ≤ .05) were of significantly higher image quality than standard-dose CBBCT images. CONCLUSIONS: Synchrotron-based PB-CT can achieve a significantly higher radiological image quality at a substantially lower radiation dose compared with conventional CBBCT. KEY POINTS: • PB-CT using synchrotron radiation results in higher image quality than conventional CBBCT for breast imaging. • PB-CT using synchrotron radiation requires a lower radiation dose than conventional CBBCT for breast imaging. • PB-CT can help clinicians diagnose patients with breast cancer.

Improving Breast Cancer Detection Accuracy of Mammography with the Concurrent Use of an Artificial Intelligence Tool.

PURPOSE: To evaluate the benefits of an artificial intelligence (AI)-based tool for two-dimensional mammography in the breast cancer detection process. MATERIALS AND METHODS: In this multireader, multicase retrospective study, 14 radiologists assessed a dataset of 240 digital mammography images, acquired between 2013 and 2016, using a counterbalance design in which half of the dataset was read without AI and the other half with the help of AI during a first session and vice versa during a second session, which was separated from the first by a washout period. Area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and reading time were assessed as endpoints. RESULTS: The average AUC across readers was 0.769 (95% CI: 0.724, 0.814) without AI and 0.797 (95% CI: 0.754, 0.840) with AI. The average difference in AUC was 0.028 (95% CI: 0.002, 0.055, P = .035). Average sensitivity was increased by 0.033 when using AI support (P = .021). Reading time changed dependently to the AI-tool score. For low likelihood of malignancy (< 2.5%), the time was about the same in the first reading session and slightly decreased in the second reading session. For higher likelihood of malignancy, the reading time was on average increased with the use of AI. CONCLUSION: This clinical investigation demonstrated that the concurrent use of this AI tool improved the diagnostic performance of radiologists in the detection of breast cancer without prolonging their workflow.Supplemental material is available for this article.© RSNA, 2020.

Hard and soft X-ray imaging to resolve human ovarian cortical structures.

Laboratory and synchrotron X-ray tomography are powerful tools for non-invasive studies of biological samples at micrometric resolution. In particular, the development of phase contrast imaging is enabling the visualization of sample details with a small range of attenuation coefficients, thus allowing in-depth analyses of anatomical and histological structures. Reproductive medicine is starting to profit from these techniques, mainly applied to animal models. This study reports the first imaging of human ovarian tissue where the samples consisted of surgically obtained millimetre fragments, properly fixed, stained with osmium tetroxide and included in epoxydic resin. Samples were imaged by the use of propagation phase contrast synchrotron radiation micro-computed tomography (microCT), obtained at the SYRMEP beamline of Elettra light source (Trieste, Italy), and X-ray absorption microCT at the Theoretical Biology MicroCT Imaging Laboratory in Vienna, Austria. The reconstructed microCT images were compared with the soft X-ray absorption and phase contrast images acquired at the TwinMic beamline of Elettra in order to help with the identification of structures. The resulting images allow the regions of the cortex and medulla of the ovary to be distinguished, identifying early-stage follicles and visualizing the distribution of blood vessels. The study opens to further application of micro-resolved 3D imaging to improve the understanding of human ovary's structure and support diagnostics as well as advances in reproductive technologies.

Advancements towards the implementation of clinical phase-contrast breast computed tomography at Elettra.

Breast computed tomography (BCT) is an emerging application of X-ray tomography in radiological practice. A few clinical prototypes are under evaluation in hospitals and new systems are under development aiming at improving spatial and contrast resolution and reducing delivered dose. At the same time, synchrotron-radiation phase-contrast mammography has been demonstrated to offer substantial advantages when compared with conventional mammography. At Elettra, the Italian synchrotron radiation facility, a clinical program of phase-contrast BCT based on the free-space propagation approach is under development. In this paper, full-volume breast samples imaged with a beam energy of 32 keV delivering a mean glandular dose of 5 mGy are presented. The whole acquisition setup mimics a clinical study in order to evaluate its feasibility in terms of acquisition time and image quality. Acquisitions are performed using a high-resolution CdTe photon-counting detector and the projection data are processed via a phase-retrieval algorithm. Tomographic reconstructions are compared with conventional mammographic images acquired prior to surgery and with histologic examinations. Results indicate that BCT with monochromatic beam and free-space propagation phase-contrast imaging provide relevant three-dimensional insights of breast morphology at clinically acceptable doses and scan times.

Advanced 3D Imaging of Uterine Leiomyoma's Morphology by Propagation-based Phase-Contrast Microtomography.

Uterine leiomyoma is the most common benign smooth muscle tumor in women pelvis, originating from the myometrium. It is caused by a disorder of fibrosis, with a large production and disruption of extracellular matrix (ECM). Medical treatments are still very limited and no preventative therapies have been developed. We supposed that synchrotron-based phase-contrast microtomography (PhC-microCT) may be an appropriate tool to assess the 3D morphology of uterine leiomyoma, without the use of any contrast agent. We used this technique to perform the imaging and the quantitative morphometric analysis of healthy myometrium and pathologic leiomyomas. The quantitative morphometric analysis of collagen bundles was coupled to the Roschger approach. This method, previously only used to evaluate mineralized bone density distribution, was applied here to study the fibrosis mass density distribution in healthy and pathologic biopsies from two patients. This protocol was shown to be powerful in studying uterine leiomyomas, detecting also small signs of the ECM alteration. This is of paramount importance not only for the follow-up of the present study, i.e. the investigation of different compounds and their possible therapeutic benefits, but also because it offers new methodologic possibilities for future studies of the ECM in soft tissues of different body districts.

Toward Improving Breast Cancer Imaging: Radiological Assessment of Propagation-Based Phase-Contrast CT Technology.

RATIONALE AND OBJECTIVES: This study employs clinical/radiological evaluation in establishing the optimum imaging conditions for breast cancer imaging using the X-ray propagation-based phase-contrast tomography. MATERIALS AND METHODS: Two series of experiments were conducted and in total 161 synchrotron-based computed tomography (CT) reconstructions of one breast mastectomy specimen were produced at different imaging conditions. Imaging factors include sample-to-detector distance, X-ray energy, CT reconstruction method, phase retrieval algorithm applied to the CT projection images and maximum intensity projection. Observers including breast radiologists and medical imaging experts compared the quality of the reconstructed images with reference images approximating the conventional (absorption) CT. Various radiological image quality attributes in a visual grading analysis design were used for the radiological assessments. RESULTS: The results show that the application of the longest achievable sample-to-detector distance (9.31 m), the lowest employed X-ray energy (32 keV), the full phase retrieval, and the maximum intensity projection can significantly improve the radiological quality of the image. Several combinations of imaging variables resulted in images with very high-quality scores. CONCLUSION: The results of the present study will support future experimental and clinical attempts to further optimize this innovative approach to breast cancer imaging.

Towards synchrotron phase-contrast lung imaging in patients - a proof-of-concept study on porcine lungs in a human-scale chest phantom.

In-line free propagation phase-contrast synchrotron tomography of the lungs has been shown to provide superior image quality compared with attenuation-based computed tomography (CT) in small-animal studies. The present study was performed to prove the applicability on a human-patient scale using a chest phantom with ventilated fresh porcine lungs. Local areas of interest were imaged with a pixel size of 100 µm, yielding a high-resolution depiction of anatomical hallmarks of healthy lungs and artificial lung nodules. Details like fine spiculations into surrounding alveolar spaces were shown on a micrometre scale. Minor differences in artificial lung nodule density were detected by phase retrieval. Since we only applied a fraction of the X-ray dose used for clinical high-resolution CT scans, it is believed that this approach may become applicable to the detailed assessment of focal lung lesions in patients in the future.

Advantages of breast cancer visualization and characterization using synchrotron radiation phase-contrast tomography.

The aim of this study was to highlight the advantages that propagation-based phase-contrast computed tomography (PB-CT) with synchrotron radiation can provide in breast cancer diagnostics. For the first time, a fresh and intact mastectomy sample from a 60 year old patient was scanned on the IMBL beamline at the Australian Synchrotron in PB-CT mode and reconstructed. The clinical picture was described and characterized by an experienced breast radiologist, who underlined the advantages of providing diagnosis on a PB-CT volume rather than conventional two-dimensional modalities. Subsequently, the image quality was assessed by 11 breast radiologists and medical imaging experts using a radiological scoring system. The results indicate that, with the radiation dose delivered to the sample being equal, the accuracy of a diagnosis made on PB-CT images is significantly higher than one using conventional techniques.

High-Resolution X-Ray Phase-Contrast 3-D Imaging of Breast Tissue Specimens as a Possible Adjunct to Histopathology.

Histopathological analysis is the current gold standard in breast cancer diagnosis and management, however, as imaging technology improves, the amount of potential diagnostic information that may be demonstrable radiologically should also increase. We aimed to evaluate the potential clinical usefulness of 3-D phase-contrast micro-computed tomography (micro-CT) imaging at high spatial resolutions as an adjunct to conventional histological microscopy. Ten breast tissue specimens, 2 mm in diameter, were scanned at the SYRMEP beamline of the Elettra Synchrotron using the propagation-based phase-contrast micro-tomography method. We obtained pixel size images, which were analyzed and compared with corresponding histological sections examined under light microscopy. To evaluate the effect of spatial resolution on breast cancer diagnosis, scans with four different pixel sizes were also performed. Our comparative analysis revealed that high-resolution images can enable, at a near-histological level, detailed architectural assessment of tissue that may permit increased breast cancer diagnostic sensitivity and specificity when compared with current imaging practices. The potential clinical applications of this method are also discussed.

Drought-induced embolism in stems of sunflower: A comparison of in vivo micro-CT observations and destructive hydraulic measurements.

Vulnerability curves (VCs) are a useful tool to investigate the susceptibility of plants to drought-induced hydraulic failure, and several experimental techniques have been used for their measurement. The validity of the bench dehydration method coupled to hydraulic measurements, considered as a 'golden standard', has been recently questioned calling for its validation with non-destructive methods. We compared the VCs of a herbaceous crop plant (Helianthus annuus) obtained during whole-plant dehydration followed by i) hydraulic flow measurements in stem segments (classical destructive method) or by ii) in vivo micro-CT observations of stem xylem conduits in intact plants. The interpolated P50 values (xylem water potential inducing 50% loss of hydraulic conductance) were -1.74 MPa and -0.87 MPa for the hydraulic and the micro-CT VC, respectively. Interpolated P20 values were similar, while P50 and P80 were significantly different, as evidenced by non-overlapping 95% confidence intervals. Our results did not support the tension-cutting artefact, as no overestimation of vulnerability was observed when comparing the hydraulic VC to that obtained with in vivo imaging. After one scan, 25% of plants showed signs of x-ray induced damage, while three successive scans caused the formation of a circular brownish scar in all tested plants. Our results support the validity of hydraulic measurements of samples excised under tension provided standard sampling and handling protocols are followed, but also show that caution is needed when investigating vital plant processes with x-ray imaging.

Meniscal Ossicles as micro-CT Imaging Biomarker in a Rodent Model of Antigen-Induced Arthritis: a Synchrotron-Based X-ray Pilot Study.

It is increasingly recognized that early detection of bone erosion plays an important role in the overall evaluation of rheumatoid arthritis and in the choice of the correct treatment approach. Since an appropriate use of imaging biomarkers in preclinical settings offers the prospect of smaller and optimized sample size, in the present study we define an anatomical imaging biomarker that could be objectively measured from micro-CT imaging data as an indicator of bone erosion in arthritis process. The well-characterized antigen-induced arthritis (AIA) model in rats was used. The animals were divided into 2 groups: arthritic disease control and arthritic having been administrated with the tumor necrosis factor alpha-blocking agent (Humira). Rats were sacrificed in the acute phase of AIA; peripheral blood and synovial tissue were collected for assessment of arthritis. Ex vivo micro-CT tomography of knee joints was performed at the Elettra synchrotron light source (Trieste, Italy). Overall, results from this study suggest that use of high-resolution micro-CT analysis coupled with meniscal ossicles bone parameters quantification provide a powerful combination to enhance data interpretation and assessment of disease-modifying drugs in an animal model of arthritis.

X-ray microtomography observations of xylem embolism in stems of Laurus nobilis are consistent with hydraulic measurements of percentage loss of conductance.

Drought-induced xylem embolism is a serious threat to plant survival under future climate scenarios. Hence, accurate quantification of species-specific vulnerability to xylem embolism is a key to predict the impact of climate change on vegetation. Low-cost hydraulic measurements of embolism rate have been suggested to be prone to artefacts, thus requiring validation by direct visualization of the functional status of xylem conduits using nondestructive imaging techniques, such as X-ray microtomography (microCT). We measured the percentage loss of conductance (PLC) of excised stems of Laurus nobilis (laurel) dehydrated to different xylem pressures, and compared results with direct observation of gas-filled vs water-filled conduits at a synchrotron-based microCT facility using a phase contrast imaging modality. Theoretical PLC calculated on the basis of microCT observations in stems of laurel dehydrated to different xylem pressures overall were in agreement with hydraulic measurements, revealing that this species suffers a 50% loss of xylem hydraulic conductance at xylem pressures averaging -3.5 MPa. Our data support the validity of estimates of xylem vulnerability to embolism based on classical hydraulic techniques. We discuss possible causes of discrepancies between data gathered in this study and those of recent independent reports on laurel hydraulics.