Segmentation Enhanced Elastic Image Registration for 2D Speckle Tracking Echocardiography—Performance Study In Silico

Although the two dimensional Speckle Tracking Echocardiography has gained a strong position among medical diagnostic techniques in cardiology, it still requires further developments to improve its repeatability and reliability. Few works have attempted to incorporate the left ventricle segmentation results in the process of displacements and strain estimation to improve its performance. We proposed the use of mask information as an additional penalty in the elastic image registration based displacements estimation. This approach was studied using a short axis view synthetic echocardiographic data, segmented using an active contour method. The obtained masks were distorted to a different degree, using different methods to assess the influence of the segmentation quality on the displacements and strain estimation process. The results of displacements and circumferential strain estimations show, that even though the method is dependent on the mask quality, the potential loss in accuracy due to the poor segmentation quality is much lower than the potential accuracy gain in cases where the segmentation performs well.

Fast and Accurate U-Net Model for Fetal Ultrasound Image Segmentation

U-Net based algorithms, due to their complex computations, include limitations when they are used in clinical devices. In this paper, we addressed this problem through a novel U-Net based architecture that called fast and accurate U-Net for medical image segmentation task. The proposed fast and accurate U-Net model contains four tuned 2D-convolutional, 2D-transposed convolutional, and batch normalization layers as its main layers. There are four blocks in the encoder-decoder path. The results of our proposed architecture were evaluated using a prepared dataset for head circumference and abdominal circumference segmentation tasks, and a public dataset (HC18-Grand challenge dataset) for fetal head circumference measurement. The proposed fast network significantly improved the processing time in comparison with U-Net, dilated U-Net, R2U-Net, attention U-Net, and MFP U-Net. It took 0.47 seconds for segmenting a fetal abdominal image. In addition, over the prepared dataset using the proposed accurate model, Dice and Jaccard coefficients were 97.62% and 95.43% for fetal head segmentation, 95.07%, and 91.99% for fetal abdominal segmentation. Moreover, we have obtained the Dice and Jaccard coefficients of 97.45% and 95.00% using the public HC18-Grand challenge dataset. Based on the obtained results, we have concluded that a fine-tuned and a simple well-structured model used in clinical devices can outperform complex models.

Feasibility of Quantitative Tissue Characterization Using Novel Parameters Extracted From Photoacoustic Power Spectrum Considering Multiple Absorbers

Frequency domain analysis of radio frequency signal is performed to differentiate between different tissue categories in terms of spectral parameters. However, due to complex relationship between the absorber size and spectral parameters, they cannot be used for quantitative tissue characterization. In an earlier study, we showed that using linear relationship between absorber size and two new spectral parameters namely number of lobes and average lobe width, absorber size can be successfully recovered from photoacoustic signal generated by single absorber. As actual biological tissue contains multiple absorbers, in this study we extended the application of these two new spectral parameters for computing absorber size from signals generated by multiple PA absorbers. We revisited our analytical model to establish two new linear relationships between the absorber radius and number of lobes as well as average lobe width considering multiple absorbers with bandlimited acquisition. A simulation study was performed to validate these linear relationships. A retrospective ex vivo study, in which the spectral parameters were computed using multiwavelength photoacoustic signals, was performed with freshly exercised thyroid specimens from 38 actual human patients undergoing thyroidectomy after having a diagnosis of suspected thyroid lesions. From statistical analysis it is shown that both the parameters were significantly different between malignant and non-malignant thyroid and malignant and normal thyroid tissue. Performance of the supervised classification with the computed spectral parameters showed that the extracted parameters could be successfully used to differentiate malignant thyroid tissue from normal thyroid tissue with reasonable degree of accuracy.

Cyclic Variation of Spectral Parameters for the Differentiation of Atrial Myocardium Before and Immediately Following Radiofrequency Ablation

Radiofrequency ablation (RFA) is a common treatment of atrial fibrillation. However, current treatment is associated with a greater than 20% recurrence rate, in part due to inadequate monitoring of tissue viability during ablation. Spectral parameters, in particular cyclic variation of integrated backscatter (CVIB), have shown promise as early indicators of myocardial recovery from ischemia. Our aim was to demonstrate the use of spectral parameters to differentiate atrial myocardium before and after radiofrequency ablation. An AcuNav 10 F catheter was used to collect radiofrequency signals from the posterior wall of the left atrium of patients before and immediately after RFA for AF. The normalized power spectrum was obtained and three spectral parameters (integrated backscatter [IB], slope, and intercept) were extracted across two continuous heart cycles. Parameters were gated for ventricular end-diastole and compared before and after ablation. Additionally, the cyclic variation of each of these three parameters was generated as an average of the variation across the two recorded heart cycles. Data from 14 patients before and after ablation demonstrated a significant difference in the magnitude of the cyclic variation of integrated backscatter (9.0 vs. 6.0 dB, p < .001) and cyclic variation of the intercept (14.0 vs. 11.5 dB, p = .04). No significant difference was noted in the magnitude of the cyclic variation of the slope. Among spectral parameters gated for end-diastole, significant differences were noted in the slope (−4.39 vs. −3.73 dB/MHz, p = .002) and intercept (16.8 vs. 11.9 dB, p = .002). No significant difference was noted in the integrated backscatter. Spectral parameters are able to differentiate atrial myocardium before and immediately following ablation and may be useful in monitoring atrial ablations.

Simultaneous Segmentation of Fetal Hearts and Lungs for Medical Ultrasound Images via an Efficient Multi-scale Model Integrated With Attention Mechanism

Large scale early scanning of fetuses via ultrasound imaging is widely used to alleviate the morbidity or mortality caused by congenital anomalies in fetal hearts and lungs. To reduce the intensive cost during manual recognition of organ regions, many automatic segmentation methods have been proposed. However, the existing methods still encounter multi-scale problem at a larger range of receptive fields of organs in images, resolution problem of segmentation mask, and interference problem of task-irrelevant features, obscuring the attainment of accurate segmentations. To achieve semantic segmentation with functions of (1) extracting multi-scale features from images, (2) compensating information of high resolution, and (3) eliminating the task-irrelevant features, we propose a multi-scale model with skip connection framework and attention mechanism integrated. The multi-scale feature extraction modules are incorporated with additive attention gate units for irrelevant feature elimination, through a U-Net framework with skip connections for information compensation. The performance of fetal heart and lung segmentation indicates the superiority of our method over the existing deep learning based approaches. Our method also shows competitive performance stability during the task of semantic segmentations, showing a promising contribution on ultrasound based prognosis of congenital anomaly in the early intervention, and alleviating the negative effects caused by congenital anomaly.

Is There a Difference Between the Joint Ultrasounds of Healthy Women and Men? A Study With Small, Medium, and Large Joints

To compare joint ultrasound measurements between the sexes in healthy volunteers. A cross-sectional study compared the joint ultrasound measurements between the sexes in healthy volunteers. Quantitative (synovial hypertrophy and perpendicular measurement in the largest synovial recess) and semiquantitative (synovial hypertrophy, power Doppler, and bone erosion; score 0–3) ultrasound measurements were performed. Forty-six articular recesses were evaluated and compared between group 1 (100 females) and group 2 (60 males) who were matched by age and BMI. For the quantitative measurements, 7360 recesses were studied. For the semiquantitative measurements, 22,720 recesses were evaluated. Higher values ( p < .05) were found in females for the quantitative measurements of synovial hypertrophy for the following: radiocarpal, distal radioulnar and ulnocarpal, second/third dorsal and second/third palmar interphalangeal, second palmar metacarpophalangeal, glenohumeral, hip, talocrural, talonavicular, and talocalcaneal recesses; the highest difference was found for the hip (6.21 ± 1.35 vs. 4.81 ± 2.40) and distal radioulnar (1.46 ± 0.40 vs. 1.07 ± 0.70) recesses. For the semiquantitative measurements, significant differences were found. For synovial hypertrophy, higher measurements for females in the second/third palmar metacarpophalangeal, second palmar proximal interphalangeal, hip, tibiotalar, talonavicular, talocalcaneal, and second metatarsophalangeal recesses (highest difference for second palmar metacarpophalangeal [44 (22.0%) vs. 5 (4.2%)]). For power Doppler, there were higher values for females in the talonavicular recesses and higher values for males in the first/second/fifth metatarsophalangeal recesses (highest difference for fifth [9 (7.5%) vs. 2 (1.0%)]). For bone erosion, there were higher measurements for females in the radiocarpal recesses (10 [5.0%] vs. 0 [0.0%]) and higher values for males in the talonavicular recesses (4 [3.3%] vs. 0 [0.0%]). Higher quantitative and semiquantitative ultrasound measurements of synovial hypertrophy were typically found in females.

Assessment of Axillary Lymph Nodes for Metastasis on Ultrasound Using Artificial Intelligence

The purpose of this study was to evaluate an artificial intelligence (AI) system for the classification of axillary lymph nodes on ultrasound compared to radiologists. Ultrasound images of 317 axillary lymph nodes from patients referred for ultrasound guided fine needle aspiration or core needle biopsy and corresponding pathology findings were collected. Lymph nodes were classified into benign and malignant groups with histopathological result serving as the reference. Google Cloud AutoML Vision (Mountain View, CA) was used for AI image classification. Three experienced radiologists also classified the images and gave a level of suspicion score (1–5). To test the accuracy of AI, an external testing dataset of 64 images from 64 independent patients was evaluated by three AI models and the three readers. The diagnostic performance of AI and the humans were then quantified using receiver operating characteristics curves. In the complete set of 317 images, AutoML achieved a sensitivity of 77.1%, positive predictive value (PPV) of 77.1%, and an area under the precision recall curve of 0.78, while the three radiologists showed a sensitivity of 87.8% ± 8.5%, specificity of 50.3% ± 16.4%, PPV of 61.1% ± 5.4%, negative predictive value (NPV) of 84.1% ± 6.6%, and accuracy of 67.7% ± 5.7%. In the three external independent test sets, AI and human readers achieved sensitivity of 74.0% ± 0.14% versus 89.9% ± 0.06% ( p = .25), specificity of 64.4% ± 0.11% versus 50.1 ± 0.20% ( p = .22), PPV of 68.3% ± 0.04% versus 65.4 ± 0.07% ( p = .50), NPV of 72.6% ± 0.11% versus 82.1% ± 0.08% ( p = .33), and accuracy of 69.5% ± 0.06% versus 70.1% ± 0.07% ( p = .90), respectively. These preliminary results indicate AI has comparable performance to trained radiologists and could be used to predict the presence of metastasis in ultrasound images of axillary lymph nodes.

Ultrasonographic Detection of Vascularity of Focal Breast Lesions: Microvascular Imaging Versus Conventional Color and Power Doppler Imaging

To compare microvascular flow imaging (MVFI) to conventional Color-Doppler (CDI) and Power-Doppler (PDI) imaging in the detection of vascularity of Focal Breast Lesions (FBLs). A total of 180 solid FBLs (size: 3.5–45.2 mm) detected in 180 women (age: 21–87 years) were evaluated by means of CDI, PDI, and MVFI. Two blinded reviewers categorized lesion vascularity in absent or present, and vascularity pattern as (a) internal; (b) vessels in rim; (c) combined. The presence of a “penetrating vessel” was assessed separately. Differences in vascularization patterns (chi2 test) and intra- and inter-observer agreement (Fleiss method) were calculated. ROC analysis was performed to assess performance of each technique in differentiating benign from malignant lesions. About 103/180 (57.2%) FBLs were benign and 77/180 (42.8%) were malignant. A statistically significant ( p < .001) increase in blood flow detection was observed for both readers with MVFI in comparison to either CDI or PDI. Benign FBLs showed mainly absence of vascularity ( p = .02 and p = .01 for each reader, respectively), rim pattern ( p < .001 for both readers) or combined pattern ( p = .01 and p = .04). Malignant lesions showed a statistically significant higher prevalence of internal flow pattern ( p < .001 for both readers). The prevalence of penetrating vessels was significantly higher with MVFI in comparison to either CDI or PDI ( p < .001 for both readers) and in the malignant FBLs ( p < .001). ROC analysis showed MVFI (AUC = 0.70, 95%CI = [0.64–0.77]) more accurate than CDI (AUC = 0.67, 95%CI = [0.60–0.74]) and PDI (AUC = 0.67, 95%CI = [0.60–0.74]) though not significantly ( p = .5436). Sensitivity/Specificity values for MVFI, PDI, and CDI were 76.6%/64.1%, 59.7%/73.8% and 58.4%/74.8%, respectively. Inter-reader agreement with MVFI was always very good ( k-score 0.85–0.96), whereas with CDI and PDI evaluation ranged from good to very good. No differences in intra-observer agreement were noted. MVFI showed a statistically significant increase in the detection of the vascularization of FBLs in comparison to Color and Power-Doppler.

Diagnostic Performance of Muscle Echo Intensity and Fractal Dimension for the Detection of Frailty Phenotype

To determine the relationship between muscle echo intensity (EI) and fractal dimension (FD), and the diagnostic performance of both ultrasound parameters for the identification of frailty phenotype. A retrospective interpretation of ultrasound scans from a previous cohort (November 2014–February 2015) was performed. The sample included healthy participants <60 years old, and participants ≥60 divided into robust, pre-frail, and frail groups according to Fried frailty criteria. A region of interest of the rectus femoris from the ultrasound scan was segmented, and histogram function was applied to obtain EI. For fractal analysis, images were processed using two-dimensional box-counting techniques to calculate FD. Statistical analyses were performed with diagnostic performance tests. A total of 102 participants (mean age 63 ± 16, 57 men) were evaluated. Muscle fractal dimension correlated with EI ( r = .38, p < .01) and showed different pattern in the scatter plots when participants were grouped by non-frail (control + robust) and frail (pre-frail + frail). The diagnostic accuracy for EI to categorize frailty was of 0.69 (95%CI: 0.59–0.78, p = .001), with high intra-rater (ICC: 0.98, 95%CI: 0.98–0.99); p < .001) and inter-rater (ICC: 0.89, 95%CI: 0.75–0.95; p < .001) reliability and low measurement error for both parameters (EI: −0.18, LOA95%: −10.8 to 10.5; FD: 0.00, LOA95%: −0.09 to 0.10) in arbitrary units. The ROC curve combining both parameters was not better than EI alone ( p = .18). Muscle FD correlated with EI and showed different patterns according to frailty phenotype, with EI outperforming FD as a possible diagnostic tool for frailty.

Fourier-based Synthetic-aperture Imaging for Arbitrary Transmissions by Cross-correlation of Transmitted and Received Wave-fields

Investigations into Fourier beamforming for medical ultrasound imaging have largely been limited to plane-wave and single-element transmissions. The main aim of this work is to generalize Fourier beamforming to enable synthetic aperture imaging with arbitrary transmit sequences. When applied to focused transmit beams, the proposed approach yields a full-waveform-based alternative to virtual-source synthetic aperture, which has implications for both coherence imaging and sound speed estimation. When compared to virtual-source synthetic aperture and retrospective encoding for conventional ultrasound sequences (REFoCUS), the proposed imaging technique shows an 8.6 and 3.8 dB improvement in contrast over virtual source synthetic aperture and REFoCUS, respectively, and a 55% improvement in point target resolution over virtual source synthetic aperture. The proposed image reconstruction technique also demonstrates general imaging improvements in vivo, while avoiding limitations seen in prior techniques.