Comparison of six machine learning methods for differentiating benign and malignant thyroid nodules using ultrasonographic characteristics.

BACKGROUND: Several machine learning (ML) classifiers for thyroid nodule diagnosis have been compared in terms of their accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and area under the receiver operating curve (AUC). A total of 525 patients with thyroid nodules (malignant, n = 228; benign, n = 297) underwent conventional ultrasonography, strain elastography, and contrast-enhanced ultrasound. Six algorithms were compared: support vector machine (SVM), linear discriminant analysis (LDA), random forest (RF), logistic regression (LG), GlmNet, and K-nearest neighbors (K-NN). The diagnostic performances of the 13 suspicious sonographic features for discriminating benign and malignant thyroid nodules were assessed using different ML algorithms. To compare these algorithms, a 10-fold cross-validation paired t-test was applied to the algorithm performance differences. RESULTS: The logistic regression algorithm had better diagnostic performance than the other ML algorithms. However, it was only slightly higher than those of GlmNet, LDA, and RF. The accuracy, sensitivity, specificity, NPV, PPV, and AUC obtained by running logistic regression were 86.48%, 83.33%, 88.89%, 87.42%, 85.20%, and 92.84%, respectively. CONCLUSIONS: The experimental results indicate that GlmNet, SVM, LDA, LG, K-NN, and RF exhibit slight differences in classification performance.

Ultrasound-guided microwave ablation for benign thyroid nodules results in earlier and faster nodule shrinkage in patients with Hashimoto's thyroiditis than in those with normal thyroid function.

Objectives: Given that the histological features of the thyroid parenchyma in patients with Hashimoto's thyroiditis (HT) differ from those of the normal thyroid gland, HT may affect the effectiveness of ultrasound-guided microwave ablation (MWA) for benign thyroid nodules (BTNs). The present study aimed to compare the effectiveness of MWA for the treatment of BTNs in patients with both BTNs and HT and those with BTNs and normal thyroid function, based on changes in the volume reduction ratio (VRR) of the BTNs. Methods: Patients who had achieved a VRR ≥50% after MWA for BTN (July 2020-June 2021), followed up for 12 months, and their data were retrospectively analyzed. Results: A total of 213 nodules were identified in 185 patients, including 167 in the "BTN" group and 46 in the "BTN + HT" group. A comparison of the fitting curves for VRR-follow-up time revealed that the VRR increased with time after MWA, although the relationship was nonlinear. Piece-wise linear regression model analysis of the threshold effect of VRR and follow-up time in the two groups indicated that the inflection point of the "BTN" group occurred at 2.1 months: VRR increased fastest within 2.1 months of MWA (rate of change: 32.9% per month; P < 0.001), following which the rate of change was slower and maintained at 1.0% per month (P = 0.006). In the "BTN + HT" group, the inflection point occurred 1.5 months after MWA, with the most significant increase occurring in this period (rate of change: 41.5% per month; P < 0.001), followed by a rate of 2.8% per month (P < 0.001) after 1.5 months. Conclusions: The relationship between VRR and follow-up time for ultrasound-guided MWA for BTN is nonlinear and exhibits a threshold effect. The current results indicated that the VRR in both groups increased before and after the inflection point, although the rate of change was greater before than after the inflection point. The inflection point occurs earlier in patients with BTN + HT than in those with BTN yet normal thyroid function, and this difference may be related to the "oven effect" involved in the development of HT.

A Novel Nomogram Based on Imaging Biomarkers of Shear Wave Elastography, Angio Planewave Ultrasensitive Imaging, and Conventional Ultrasound for Preoperative Prediction of Malignancy in Patients with Breast Lesions.

Several studies have demonstrated the difficulties in distinguishing malignant lesions of the breast from benign lesions owing to overlapping morphological features on ultrasound. Consequently, we aimed to develop a nomogram based on shear wave elastography (SWE), Angio Planewave Ultrasensitive imaging (Angio PLUS (AP)), and conventional ultrasound imaging biomarkers to predict malignancy in patients with breast lesions. This prospective study included 117 female patients with suspicious lesions of the breast. Features of lesions were extracted from SWE, AP, and conventional ultrasound images. The least absolute shrinkage and selection operator (Lasso) algorithms were used to select breast cancer-related imaging biomarkers, and a nomogram was developed based on six of the 16 imaging biomarkers. This model exhibited good discrimination (area under the receiver operating characteristic curve (AUC): 0.969; 95% confidence interval (CI): 0.928, 0.989) between malignant and benign breast lesions. Moreover, the nomogram also showed demonstrated good calibration and clinical usefulness. In conclusion, our nomogram can be a potentially useful tool for individually-tailored diagnosis of breast tumors in clinical practice.

Human clinical trial using diagnostic ultrasound and microbubbles to enhance neoadjuvant chemotherapy in HER2- negative breast cancer.

Background: In vivo and in vitro experiments have demonstrated that diagnostic ultrasound combined with microbubbles (USMB) can enhance tumor chemotherapy, but few clinical studies have explored the effect of USMB in human HER2-negative breast cancer. We aimed to compare USMB combined with neoadjuvant chemotherapy (NAC) with NAC alone in the treatment of human HER2-negative breast cancer. Methods: Patients (n=10) enrolled in the study were treated with TAC (taxane - (docetaxel), anthracycline - (epirubicin or doxorubicin liposomes), and cyclophosphamide) and ultrasound using a commercial clinical ultrasound scanner for 20 min after each chemotherapy session, followed by intermittent injections of SonoVue® to induce sonoporation and enhance therapeutic efficacy. Contrast-enhanced ultrasound (CEUS) was used to record tumor perfusion before and after ultrasound treatment. Results: After completion of chemotherapy, the maximum tumor diameter of patients in the combined treatment group (n=10) was significantly smaller than that in the control group (n=16) (p=0.017). Although the combined treatment group had higher overall response and clinical benefit rates than those in the control group, there was no statistically significant difference in RECIST between the combined treatment group and the control groups (p=0.590). More patients in the combination therapy group achieved pathologic complete response than in the control group (p=0.014). For combined treatment, CEUS revealed that the peak intensity, mean transit time, and area under the curve were higher after treatment than before treatment (p<0.001, p<0.001, p=0.003, respectively). Combined therapy did not cause additional toxicity or increase side effects. Conclusion: USMB and chemotherapy can be combined in a clinical setting using commercially available equipment, without additional toxicity, and may improve the efficacy of NAC in HER2-negative breast cancer.

Diagnostic Value of Superb Microvascular Imaging in Differentiating Benign and Malignant Breast Tumors: A Systematic Review and Meta-Analysis.

PURPOSE: We performed a systematic review and meta-analysis of studies that investigated the diagnostic performance of Superb Microvascular Imaging (SMI) in differentiating between benign and malignant breast tumors. METHODS: Studies published between January 2010 and March 2022 were retrieved by online literature search conducted in PubMed, Embase, Cochrane Library, Web of Science, China Biology Medicine Disc, China National Knowledge Infrastructure, Wanfang, and Vip databases. Pooled sensitivity, specificity, and diagnostic odd ratios were calculated using Stata software 15.0. Heterogeneity among the included studies was assessed using I2 statistic and Q test. Meta-regression and subgroup analyses were conducted to investigate potential sources of heterogeneity. Influence analysis was conducted to determine the robustness of the pooled conclusions. Deeks' funnel plot asymmetry test was performed to assess publication bias. A summary receiver operating characteristic curve (SROC) was constructed. RESULTS: Twenty-three studies involving 2749 breast lesions were included in our meta-analysis. The pooled sensitivity and specificity were 0.80 (95% confidence interval [CI], 0.77-0.84, inconsistency index [I2] = 28.32%) and 0.84 (95% CI, 0.79-0.88, I2 = 89.36%), respectively. The pooled diagnostic odds ratio was 19.95 (95% CI, 14.84-26.82). The area under the SROC (AUC) was 0.85 (95% CI, 0.81-0.87). CONCLUSION: SMI has a relatively high sensitivity, specificity, and accuracy for differentiating between benign and malignant breast lesions. It represents a promising supplementary technique for the diagnosis of breast neoplasms.

Spontaneous internal carotid artery pseudoaneurysm complicated with ischemic stroke in a young man: A case report and review of literature.

BACKGROUND: Carotid artery pseudoaneurysm (PSA) is infrequently encountered in clinical settings. Internal carotid artery (ICA) PSA complicated with ischemic stroke is rare. PSAs are typically caused by iatrogenic injury, trauma, or infection. The underlying mechanisms of spontaneous PSA formation are not well characterized. We report a healthy young man who presented with stroke as a complication of spontaneous PSA of the left ICA. CASE SUMMARY: A 30-year-old man working as a ceiling decoration worker was hospitalized due to sudden-onset speech disorder and right lower extremity weakness. Medical history was unremarkable. Brain computed tomography revealed ischemic stroke. Digital subtraction angiography showed a left ICA PSA with mild stenosis. The patient was conservatively managed with oral anticoagulation and antiplatelet therapy. He recovered well and was discharged. The patient was in good condition during follow-up. CONCLUSION: The occupational history of patient should be taken into consideration while evaluating the etiology of spontaneous ICA PSA in young people with stroke.

MRI/Transrectal Ultrasound Fusion-Guided Targeted Biopsy and Transrectal Ultrasound-Guided Systematic Biopsy for Diagnosis of Prostate Cancer: A Systematic Review and Meta-analysis.

Purpose: For men suspected of having prostate cancer (PCa), the transrectal ultrasound (TRUS)-guided systematic biopsy (SB) was performed. MRI/TRUS fusion guided-targeted biopsy (MRI-TB) could enhance PCa detection, allowing sampling of sites at higher risk which were not obvious with TRUS alone. The aim of this systematic review and meta-analysis was to compare the detection rates of prostate cancer by MRI-TB or MRI-TB plus SB versus SB, mainly for diagnosis of high-risk PCa. Methods: A literature Search was performed on PubMed, Cochrane Library, and Embase databases. We searched from inception of the databases up to January 2021. Results: A total of 5831 patients from 26 studies were included in the present meta-analysis. Compared to traditional TRUS-guided biopsy, MRI-TB had a significantly higher detection rate of clinically significant PCa (RR=1.27; 95%CI 1.15-1.40; p<0.001) and high-risk PCa (RR=1.41; 95% CI 1.22-1.64; p<0.001), while the detection rate of clinically insignificant PCa was lower (RR=0.65; 95%CI 0.55-0.77; p<0.001). MRI-TB and SB did not significantly differ in the detection of overall prostate cancer (RR=1.04; 95%CI 0.95-1.12; p=0.41). Compared with SB alone, we found that MRI-TB plus SB diagnosed more cases of overall, clinically significant and high-risk PCa (p<0.001). Conclusion: Compared with systematic protocols, MRI-TB detects more clinically significant and high-risk PCa cases, and fewer clinically insignificant PCa cases. MRI-TB combined with SB enhances PCa detection in contrast with either alone but did not reduce the diagnosis rate of clinically insignificant PCa. Systematic Review Registration: https://www.crd.york.ac.uk/prospero/#searchadvanced, CRD42021218475.

Inflammatory myofibroblastic tumor after breast prosthesis: A case report and literature review.

BACKGROUND: Inflammatory myofibroblastic tumors (IMTs) are defined as tumors composed of differentiated myofibroblastic spindle cells, usually accompanied by numerous plasma cells and lymphocytes, and classified as intermediate (occasionally metastatic) by the World Health Organization. Its pathogenesis and biological behavior have not yet been elucidated. Breast IMT is extremely rare, and prosthesis implantation combined with IMT has not been reported. This study reports a case of IMT following resection of a malignant phyllodes tumor of the left breast and implantation of a prosthesis. CASE SUMMARY: A 41-year-old female presented to our hospital with a mass in the left breast for 3 mo. The patient had undergone resection of a large mass in her left breast pathologically diagnosed as a malignant phyllodes tumor and implantation of a prosthesis five years prior. Ultrasonic examination revealed an oval mass in the left breast, and the patient underwent left breast mass resection and prosthesis removal. Light microscopy revealed the spindle cells to be diffusely proliferated, with a large number of neutrophils, lymphocytes, and plasma cell infiltration. Immunohistochemical staining revealed that the spindle cells were partially positive for smooth muscle actin, which is positive for BCL-2 and cluster of differentiation (CD) 99 but were negative for anaplastic lymphoma kinase, cytokeratin, S-100 protein, desmin, and CD34. The final diagnosis was IMT. No recurrence or metastasis was observed during the 5-year postoperative follow-up. CONCLUSION: Prosthesis implantation may be one of the causes of IMT, but further investigation is necessary to prove it.

Circ_0058058 Drives the Malignant Phenotypes and Immune Evasion of Pancreatic Cancer by the MicroRNA-557-Dependent Regulation of PDL1.

OBJECTIVES: Pancreatic cancer (PC) is one of the most deadly malignancies in the world. Recently, circular RNAs play crucial roles in PC progression. However, the functions of circ_0058058 in PC are barely known. METHODS: The expression of circ_0058058, microRNA-557-5p (miR-557), and programmed cell death receptor ligand 1 (PDL1) was detected by quantitative real-time polymerase chain reaction. Functional experiments were implemented to disclose the effect of circ_0058058 deficiency on PC cell proliferation, apoptosis, invasion, angiogenesis, and immune escape. The binding relationship between miR-557 and circ_0058058 or PDL1 was identified by dual-luciferase reporter assay and RNA immunoprecipitation assay. In vivo assay was used to disclose the impact of circ_0058058 silencing on tumor formation in vivo. RESULTS: Circ_0058058 was highly expressed in PC tissues and cell lines. Knockdown of circ_0058058 repressed cell proliferation, invasion, angiogenesis, and immune escape while contributed to apoptosis in PC cells. Mechanically, circ_0058058 worked as a molecular sponge of miR-557 to regulate PDL1 expression. Moreover, circ_0058058 showed a promotional effect on tumor growth in vivo. CONCLUSIONS: Our findings suggested that circ_0058058 served as miR-557 sponge to upregulate PDL1, thereby triggering PC proliferation, invasion, angiogenesis, and immune escape.

High-Frequency Ultrasound for Evaluation of the Pathological Invasion Level of Extramammary Paget Disease.

OBJECTIVES: Pathological invasion level of extramammary Paget disease (EMPD) is strongly related with its risk staging, treatment, and prognosis. However, the current evaluation before treatments fails to evaluate pathological invasion level of EMPD. High-frequency ultrasound (HFUS) may play a key role to solve this problem. The purpose was to explore the performance of HFUS in the evaluation of pathological invasion level of EMPD. METHODS: Sixty pathologically proven EMPD patients were retrospectively enrolled and divided into 2 groups as follows: in situ in the epidermis (IE) (n = 42) and invasion into the dermis or subcutaneous (ID) (n = 18) groups. Clinical and HFUS features were compared between the 2 groups. RESULTS: Between the 2 groups, HFUS features (lesion shape, internal echogenicity and echotexture, surface shape, epidermal hyperechoic layer on the surface, the "pseudopod sign", and color Doppler ultrasound features) and clinical features were comparable (all P >.05). Tumor growth pattern significantly differed between the 2 groups (P <.05). Infiltration depth was significantly deeper for the ID group than the IE group (P <.05). With a cutoff value of 1.55 mm for infiltration depth, the area under the receiver operating characteristic curve was 0.833. CONCLUSIONS: HFUS features of tumor growth pattern and infiltration depth may contribute to the assessment of invasion level of EMPD.

Attention-Guided Multi-Branch Convolutional Neural Network for Mitosis Detection From Histopathological Images.

Mitotic count is an important indicator for assessing the invasiveness of breast cancers. Currently, the number of mitoses is manually counted by pathologists, which is both tedious and time-consuming. To address this situation, we propose a fast and accurate method to automatically detect mitosis from the histopathological images. The proposed method can automatically identify mitotic candidates from histological sections for mitosis screening. Specifically, our method exploits deep convolutional neural networks to extract high-level features of mitosis to detect mitotic candidates. Then, we use spatial attention modules to re-encode mitotic features, which allows the model to learn more efficient features. Finally, we use multi-branch classification subnets to screen the mitosis. Compared to existing related methods in literature, our method obtains the best detection results on the dataset of the International Pattern Recognition Conference (ICPR) 2012 Mitosis Detection Competition. Code has been made available at: https://github.com/liushaomin/MitosisDetection.

Modified Model for Diagnosing Breast Imaging Reporting and Data System Category 3 to 5 Breast Lesions: Retrospective Analysis and Nomogram Development.

OBJECTIVES: The aim of this study was to explore a modified model to simplify the diagnostic process for American College of Radiology Breast Imaging Reporting and Data System category 3 to 5 breast lesions and evaluate the model's diagnostic efficacy. METHODS: A retrospective review was conducted of breast lesions examined by B-mode ultrasound (US) and contrast-enhanced ultrasound (CEUS) and diagnosed by histopathologic examination from October 2016 to August 2019. The US characteristics of a combined model (US + CEUS model) with relatively high diagnostic value were selected by a lasso regression analysis to establish a modified model. Two nomograms were developed. The results were internally validated by bootstrap resampling. RESULTS: Overall, 206 breast lesions in 198 patients, 136 benign and 70 malignant, were included. Ultrasound characteristics included in the modified model were shape, margin, microcalcification, enhanced intensity, enhanced scope, and enhanced time. For the US + CEUS model and modified model, sensitivities were 94.3% and 93.3%; specificities were 85.9% and 81.4%; accuracies were 89.3% and 88.7% and areas under the curve were 0.957 and 0.944, respectively. No statistically significant differences were seen in the diagnostic efficacies of the models (P = .097). Bootstrap-corrected sensitivities, specificities. and accuracies of the models were consistent with these results. Bootstrap-corrected areas under the curve for the US + CEUS model and the modified model were 0.955 and 0.940, respectively. CONCLUSIONS: The modified model with fewer indicators conveniently and effectively diagnosed the malignancy of Breast Imaging Reporting and Data System category 3 to 5 breast lesions without reducing diagnostic efficacy.

Ultrasound-Guided Lauromacrogol Injection for the Treatment of Active Bleeding After Renal Biopsy.

Background: This study aimed to describe the technique and outcomes of hemostasis for ultrasound-guided lauromacrogol injection for active bleeding after renal biopsy. Methods: Data from patients with active bleeding after renal biopsy between January 2018 and December 2020 were retrospectively collected. Patients who still had active bleeding after 30 min of compression were then injected with lauromacrogol under ultrasound guidance. The patient's symptoms before and after operation were collected to assess whether they had severe complications. Changes in hemoglobin and serum creatinine values were collected. Results: Data from a total of 15 patients with active bleeding after renal biopsy were collected, including data of 6 men and 9 women. After the operation, there were 11 cases of mild back pain; 1 case of chills, cold sweats, and back pain; 1 case of cold sweats and blood pressure reduction, and 2 cases with no obvious symptoms. No severe complications occurred in this study, and active bleeding was stopped in all patients. After the operation, compared with before the operation, there was no statistically significant difference in the hemoglobin value and serum creatinine value (p = 0.10 > 0.05, p = 0.78 > 0.05). Conclusion: Ultrasound-guided lauromacrogol injection is a relatively simple, safe and feasible method, which could be helpful in treating active bleeding in the immediate post-procedure period after renal biopsy.

Ultrasound-Induced Destruction of Nitric Oxide-Loaded Microbubbles in the Treatment of Thrombus and Ischemia-Reperfusion Injury.

Objectives: Early recanalization of large vessels in thromboembolism, such as myocardial infarction and ischemic stroke, is associated with improved clinical outcomes. Nitric oxide (NO), a biological gas signaling molecule, has been proven to protect against ischemia-reperfusion injury (IRI). However, the underlying mechanisms remain to be explored. This study investigated whether NO could mitigate IRI and the role of NO during acoustic cavitation. Methods: In vivo, thrombi in the iliac artery of rats were induced by 5% FeCl3. NO-loaded microbubbles (NO-MBs) and ultrasound (US) were used to treat thrombi. B-mode and Doppler US and histological analyses were utilized to evaluate the thrombolysis effect in rats with thrombi. Immunohistochemistry, immunofluorescence, and western blotting were conducted to investigate the underlying mechanisms of NO during acoustic cavitation. In vitro, hypoxia was used to stimulate cells, and NO-MBs were employed to alleviate oxidative stress and apoptosis. Results: We developed NO-MBs that significantly improve the circulation time of NO in vivo, are visible, and effectively release therapeutic gas under US. US-targeted microbubble destruction (UTMD) and NO-loaded UTMD (NO + UTMD) caused a significant decrease in the thrombus area and an increase in the recanalization rates and blood flow velocities compared to the control and US groups. We discovered that UTMD induced NO generation through activation of endothelial NO synthase (eNOS) in vivo. More importantly, we also observed significantly increased NO content and eNOS expression in the NO + UTMD group compared to the UTMD group. NO + UTMD can mitigate oxidative stress and apoptosis in the hind limb muscle without influencing blood pressure or liver and kidney functions. In vitro, NO-MBs alleviated oxidative stress and apoptosis in cells pretreated with hypoxia. Conclusion: Based on these data, UTMD affects the vascular endothelium by activating eNOS, and NO exerts a protective effect against IRI.

The Value of Nomograms in Pre-Operative Prediction of Lymphovascular Invasion in Primary Breast Cancer Undergoing Modified Radical Surgery: Based on Multiparametric Ultrasound and Clinicopathologic Indicators.

The purpose of this study was to explore the value of pre-operative prediction of lymphovascular invasion (LVI) in primary breast cancer patients undergoing modified radical mastectomy and to develop a nomogram based on multiparametric ultrasound and clinicopathologic indicators. All patients with primary breast cancer confirmed by pre-operative biopsy underwent B-mode ultrasound and contrast-enhanced ultrasound examinations. Post-operative pathology was used as the gold standard to identify LVI. Lasso regression was used to select predictors most related to LVI. A nomogram was developed to calculate the diagnostic efficacy. We bootstrapped the data for 500 times to perform internal verification, drawing a calibration curve to verify prediction ability. A total of 244 primary breast cancer patients were included. LVI was observed in 77 patients. Ten predictors associated with LVI were selected by Lasso regression. The area under the curve, sensitivity, specificity and accuracy for the nomogram were 0.918, 92.2%, 76.7% and 81.6%, respectively. And the nomogram calibration curve showed good consistency between the predicted probability and the actual probability. The nomogram developed could be used to predict LVI in primary breast cancer patients undergoing modified radical mastectomy and to help in clinical decision-making.

Diagnostic Value of Contrast-Enhanced Ultrasonography With SonoVue in the Differentiation of Benign and Malignant Breast Lesions: A Meta-Analysis.

PURPOSE: A meta-analysis was conducted to evaluate the diagnostic performance of contrast-enhanced ultrasonography using the contrast agent SonoVue to differentiate benign from malignant breast lesions. METHOD: A comprehensive search of the literature was performed using the Embase, PubMed, and Web of Science databases to retrieve studies published before February 2020. Data were extracted, and pooled sensitivity, specificity, and diagnostic odds ratios were calculated with meta-analysis software. Heterogeneity was evaluated via the Q test and I2 statistic. Meta-regression and subgroup analyses were applied to evaluate potential sources of heterogeneity. Publication bias was assessed using the Deeks' funnel plot asymmetry test. A summary receiver operating characteristic curve (SROC) was constructed. RESULTS: A total of 27 studies including 5378 breast lesions subjected to CEUS examination with SonoVue were included in the meta-analysis. The pooled sensitivity and specificity values were 0.90 (95% confidence interval [CI], 0.88-0.91; inconsistency index [I2] = 75.7%) and 0.83 (95% CI, 0.82-0.85; I2 = 91.0%), respectively. The pooled diagnostic odds ratio was 48.35% (95% CI, 31.22-74.89; I2 = 77.6%). The area under the summary receiver operating characteristic curve (AUC) was 0.9354. Meta-regression analysis revealed the region of patient residence and dose of contrast agent as potential sources of heterogeneity (P < .01). Subgroup analysis showed a higher area under the summary receiver operating characteristic curve for European and higher contrast agent dose subgroups (P < .05). CONCLUSION: Contrast-enhanced ultrasonography with SonoVue displays high sensitivity, specificity, and accuracy when differentiating benign from malignant breast lesions. Despite its current limitations, this technique presents a promising tool for diagnosing breast lesions in clinical practice.

Self-co-attention neural network for anatomy segmentation in whole breast ultrasound.

The automated whole breast ultrasound (AWBUS) is a new breast imaging technique that can depict the whole breast anatomy. To facilitate the reading of AWBUS images and support the breast density estimation, an automatic breast anatomy segmentation method for AWBUS images is proposed in this study. The problem at hand is quite challenging as it needs to address issues of low image quality, ill-defined boundary, large anatomical variation, etc. To address these issues, a new deep learning encoder-decoder segmentation method based on a self-co-attention mechanism is developed. The self-attention mechanism is comprised of spatial and channel attention module (SC) and embedded in the ResNeXt (i.e., Res-SC) block in the encoder path. A non-local context block (NCB) is further incorporated to augment the learning of high-level contextual cues. The decoder path of the proposed method is equipped with the weighted up-sampling block (WUB) to attain class-specific better up-sampling effect. Meanwhile, the co-attention mechanism is also developed to improve the segmentation coherence among two consecutive slices. Extensive experiments are conducted with comparison to several the state-of-the-art deep learning segmentation methods. The experimental results corroborate the effectiveness of the proposed method on the difficult breast anatomy segmentation problem on AWBUS images.

Quantitative evaluation of tissue stiffness around lesion by sound touch elastography in the diagnosis of benign and malignant breast lesions.

The purpose of our study is to assess the diagnostic performance of quantitative evaluation of tissue stiffness around lesion by Sound Touch Elastography (STE) in distinguishing between benign and malignant breast lesions. A total number of 160 breast lesions from 160 female patients were examined by STE. Resona 7 was equipped with "shell" function to measure elastic modulus values of tissue in the region of surrounding lesion quantitatively. The contours of the lesion were required to be delineated. The elastic modulus values of tissue in the region of 1mm, 2mm, and 3mm outside the boundary were acquired. The elastic modulus values included maximum elastic modulus (Emax), mean elastic modulus (Emean), minimum elastic modulus (Emin), and elastic modulus standard deviation (Esd). All lesions were confirmed by histopathology. We compared the differences of the above elastic modulus values between benign and malignant groups. Receiver operating characteristic (ROC) curve was drawn with the histological diagnostic results as the gold standard. Sensitivity and specificity were calculated to evaluate the diagnostic performance of STE. Operator consistency was also analyzed. Among the 160 lesions, 100 (62.5%) were benign and 60 (37.5%) were malignant. In the region of 1mm, 2mm, and 3mm surrounding the lesion, Emax, Emean, and Esd of malignant group were significantly higher than those of the benign group (all P<0.05). When the "shell" was 3mm, Emax had the highest AUROC value (AUROC = 0.998). Regarding the measurement of elastic modulus values, all the intra-class correlation coefficient (ICC) values of the inter-operator consistency were greater than 0.75 for Emax, Emean, and Esd. Therefore, quantitative evaluation of tissue stiffness around lesion by STE has the potential to distinguish between benign and malignant breast lesions.

Logistic regression analysis of conventional ultrasonography, strain elastosonography, and contrast-enhanced ultrasound characteristics for the differentiation of benign and malignant thyroid nodules.

The aim of the study is to screen the significant sonographic features by logistic regression analysis and fit a model to diagnose thyroid nodules. A total of 525 pathological thyroid nodules were retrospectively analyzed. All the nodules underwent conventional ultrasonography (US), strain elastosonography (SE), and contrast -enhanced ultrasound (CEUS). Those nodules' 12 suspicious sonographic features were used to assess thyroid nodules. The significant features of diagnosing thyroid nodules were picked out by logistic regression analysis. All variables that were statistically related to diagnosis of thyroid nodules, at a level of p < 0.05 were embodied in a logistic regression analysis model. The significant features in the logistic regression model of diagnosing thyroid nodules were calcification, suspected cervical lymph node metastasis, hypoenhancement pattern, margin, shape, vascularity, posterior acoustic, echogenicity, and elastography score. According to the results of logistic regression analysis, the formula that could predict whether or not thyroid nodules are malignant was established. The area under the receiver operating curve (ROC) was 0.930 and the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 83.77%, 89.56%, 87.05%, 86.04%, and 87.79% respectively.

Correlation Analysis between Polysomnography Diagnostic Indices and Heart Rate Variability Parameters among Patients with Obstructive Sleep Apnea Hypopnea Syndrome.

Heart rate variability (HRV) can reflect the changes in the autonomic nervous system (ANS) that are affected by apnea or hypopnea events among patients with obstructive sleep apnea hypopnea syndrome (OSAHS). To evaluate the possibility of using HRV to screen for OSAHS, we investigated the relationship between HRV and polysomnography (PSG) diagnostic indices using electrocardiography (ECG) and PSG data from 25 patients with OSAHS and 27 healthy participants. We evaluated the relationship between various PSG diagnostic indices (including the apnea hypopnea index [AHI], micro-arousal index [MI], oxygen desaturation index [ODI]) and heart rate variability (HRV) parameters using Spearman's correlation analysis. Moreover, we used multiple linear regression analyses to construct linear models for the AHI, MI, and ODI. In our analysis, the AHI was significantly associated with relative powers of very low frequency (VLF [%]) (r = 0.641, P = 0.001), relative powers of high frequency (HF [%]) (r = -0.586, P = 0.002), ratio between low frequency and high frequency powers (LF/HF) (r = 0.545, P = 0.049), normalized powers of low frequency (LF [n.u.]) (r = 0.506, P = 0.004), and normalized powers of high frequency (HF [n.u.]) (r = -0.506, P = 0.010) among patients with OSAHS. The MI was significantly related to standard deviation of RR intervals (SDNN) (r = 0.550, P = 0.031), VLF [%] (r = 0.626, P = 0.001), HF [%] (r = -0.632, P = 0.001), LF/HF (r = 0.591, P = 0.011), LF [n.u.] (r = 0.553, P = 0.004), HF [n.u.] (r = -0.553, P = 0.004), and absolute powers of very low frequency (VLF [abs]) (r = 0.525, P = 0.007) among patients with OSAHS. The ODI was significantly correlated with VLF [%] (r = 0.617, P = 0.001), HF [%] (r = -0.574, P = 0.003), LF [n.u.] (r = 0.510, P = 0.012), and HF [n.u.] (r = -0.510, P = 0.012) among patients with OSAHS. The linear models for the PSG diagnostic indices were AHI = -38.357+1.318VLF [%], MI = -13.389+11.297LF/HF+0.266SDNN, and ODI = -55.588+1.715VLF [%]. However, the PSG diagnostic indices were not related to the HRV parameters among healthy participants. Our analysis suggests that HRV parameters are powerful tools to screen for OSAHS patients in place of PSG monitoring.