No abstract

In this work, a computer-aided tool for detection was developed to segment breast masses from clinical ultrasound (US) scans. The underlying Multi U-net algorithm is based on convolutional neural networks. Under the Mayo Clinic Institutional Review Board protocol, a prospective study of the automatic segmentation of suspicious breast masses was performed. The cohort consisted of 258 female patients who were clinically identified with suspicious breast masses and underwent clinical US scan and breast biopsy. The computer-aided detection tool effectively segmented the breast masses, achieving a mean Dice coefficient of 0.82, a true positive fraction (TPF) of 0.84, and a false positive fraction (FPF) of 0.01. By avoiding positioning of an initial seed, the algorithm is able to segment images in real time (13–55 ms per image), and can have potential clinical applications. The algorithm is at par with a conventional seeded algorithm, which had a mean Dice coefficient of 0.84 and performs significantly better (P< 0.0001) than the original U-net algorithm.

Singular value based spatiotemporal clutter filtering (SVD-STF) can significantly improve the sensitivity of blood flow imaging in small vessels without using contrast agents. However, despite effective clutter filtering, large physiological motion in thyroid imaging can impact coherent integration of the Doppler signal and degrade the visualization of the underlying vasculature. In this study, we hypothesize that motion correction of the clutter filtered Doppler ensemble, prior to the power Doppler estimation, can considerably improve the visualization of smalls vessels in suspicious thyroid nodules. We corroborated this hypothesis by conducting in vivo experiments on 10 female patients in the age group 44–82 yrs, with at least one thyroid nodule suspicious of malignancy, with recommendation for fine needle aspiration biopsy. Ultrasound images were acquired using a clinical ultrasound scanner, implemented with compounded plane wave imaging. Axial and lateral displacements associated with the thyroid nodules were estimated using 2D normalized cross-correlation. Subsequently, the tissue clutter associated with the Doppler ensemble was suppressed using SVD-STF. Motion correction of the clutter-filtered Doppler ensemble was achieved using a spline based sub-pixel interpolation. The results demonstrated that power Doppler images of thyroid nodules were noticeably degraded due to large physiological motion of the pulsating carotid artery in the proximity. The resultant power Doppler images were corrupted with signal distortion, motion blurring and occurrence of artificial shadow vessels and displayed visibly low signal-to-background contrast. In contrast, the power Doppler images obtained from the motion corrected ultrasound data addressed the issue and considerabley improved the visualization of blood flow. The signal-to-noise ratio and the contrast-to-noise ratio increased by up to 15.2 dB and 12.1 dB, respectively. Across the ten subjects, the highest improvement was observed for the nodule with the largest motion. These preliminary results show the ability of using motion correction to improve the visualization of small vessel blood flow in thyroid, without using any contrast agents. The results of this feasibility study were encouraging, and warrant further development and more in vivo validation in moving tissues and organs.

In vivo estimations of the frequency-dependent acoustic attenuation (α) and backscatter (η) coefficients using radio frequency (RF) echoes acquired with clinical ultrasound systems must be independent of the data acquisition setup and the estimation procedures. In a recent in vivo assessment of these parameters in rodent mammary tumors, overall agreement was observed among α and η estimates using data from four clinical imaging systems. In some cases, particularly in highly attenuating heterogeneous tumors, multi-system variability was observed. This paper compares α and η estimates of a well-characterized rodent-tumor-mimicking homogeneous phantom scanned using 7 transducers with the same four clinical imaging systems: a Siemens Acuson S2000, an Ultrasonix RP, a Zonare Z.one, and a VisualSonics Vevo2100. α and η estimates of lesion-mimicking spheres in the phantom were independently assessed by three research groups, who analyzed their system’s RF echo signals. Imaging-system-based estimates of α and η of both lesion-mimicking spheres were comparable to through-transmission laboratory estimates and to predictions using Faran’s theory, respectively. A few notable variations in results among the clinical systems were observed, but the average and maximum percent difference between α estimates and laboratory-assessed values was 11% and 29%, respectively. Excluding a single outlier dataset, the average and maximum average difference between η estimates for the clinical systems and values predicted from scattering theory was 16% and 33%, respectively. These results were an improvement over previous inter-laboratory comparisons of attenuation and backscatter estimates. Although the standardization of our estimation methodologies can be further improved, this study validates our results from previous rodent breast-tumor model studies.

Purpose or objectiveThe objective of this study is to assess correlation between bladder wall mechanical properties obtained by ultrasound bladder vibrometry (UBV) and urodynamic study (UDS) measurements in a group of patients undergoing clinical UDS procedure.Materials and methodsConcurrent UBV and UDS were performed on 70 patients with neurogenic bladders (56 male and 14 female). Bladder wall mechanical properties measured by UBV at different filling volumes were correlated with recorded detrusor pressure (Pdet) values. Mean, median and standard deviation of correlation values were calculated and the significance of these observations was tested.ResultsBladder wall mechanical properties obtained by UBV as group velocity squared and elasticity showed high correlations with Pdet measured at different volumes (median correlation 0.73, CI: 0.64–0.80 and 0.72, CI: 0.56–0.82 respectively). The correlation of group velocity squared and elasticity with Pdet were both significantly higher than 0.5.ConclusionsThe results of this study suggest that UBV can closely monitor changes in bladder wall mechanical properties at different volumes in a group of patients undergoing UDS. The high correlation between UBV parameters and detrusor pressure measurements suggests that UBV can be utilized as a reliable and cost-effective tool for assessment of the bladder wall mechanical changes in a noninvasive fashion.