Search

Ultrasound image segmentation is a crucial step in computer-aided diagnosis. In this study, we propose a cross-tissue/organ segmentation method based on the transfer learning method and a modified deep residual U-Net model. We present a modified deep residual U-Net model by integrating a U-Net architecture with residual blocks to leverage the advantages of both components. Next, we explore a cross-tissue/organ transfer learning method for ultrasound image segmentation, which transfers the knowledge of ultrasound image segmentation from one tissue/organ to another, e.g. from tendon images to breast tumor images and vice versa. We evaluated the proposed method by performing four groups of experiments on three medical ultrasound datasets, consisting of one tendon dataset and two breast datasets, along with one non-medical dataset. The results showed an overall performance improvement by our method in terms of the Dice coefficient and Jaccard index. It was demonstrated that our modified deep residual U-Net exceeded the standard U-Net and residual U-Net, and the cross-tissue/organ transfer learning was superior to training from scratch and to transfer learning between divergent domains. Our method shows potential to accurately segment medical ultrasound images.

Elastography ultrasound (EUS) imaging has shown its effectiveness for diagnosis of tumors by providing additional information about tissue stiffness to the conventional B-mode ultrasound (BUS). However, due to the lack of EUS devices and experienced sonologists, EUS is not widely used, especially in rural areas. It is still a challenging task to improve the performance of the single-modal BUS-based computer-aided diagnosis (CAD) for tumors. In this work, we propose a novel transfer learning (TL)–based deep neural network (DNN) algorithm, named CW-PM-DNN, for the BUS-based CAD by transferring diagnosis knowledge from EUS during model training. CW-PM-DNN integrates both the feature-level and classifier-level knowledge transfer into a unified framework. In the feature-level TL, a bichannel DNN is learned by the cross-weight-based multimodal DL (MDL-CW) algorithm to transfer informative features from EUS to BUS. In the classifier-level TL, a projective model (PM)–based classifier is then embedded to the pretrained bichannel DNN to implement the parameter transfer in the classifier model at the second stage. The back-propagation procedure is then applied to optimize the whole CW-PM-DNN to further improve its performance. Experimental results on two bimodal ultrasound tumor datasets demonstrate that the proposed CW-PM-DNN achieves the best classification accuracy, sensitivity, and specificity of 89.02 ± 1.54%, 88.37 ± 4.72%, and 89.63 ± 4.06%, respectively, for the breast ultrasound dataset, and the corresponding values of 80.57 ± 3.41%, 76.67 ± 3.85%, and 83.94 ± 3.95%, respectively, for the prostate ultrasound dataset. The proposed two-stage TL-based CW-PM-DNN algorithm outperforms all the compared algorithms. It is also proved that the performance of the BUS-based CAD can be significantly improved by transferring the knowledge of EUS. It suggests that CW-PM-DNN has the potential for more applications in the field of medical image–based CAD.

Background Localized aggressive periodontitis is rare periodontitis in clinical practice, which often occurs in young adults under 35 years old, seriously affecting patients' quality of life. As a tetracycline antibacterial drug, minocycline is also considered an essential choice to treat periodontal disease. However, few reports focused on the effect of xipayi mouth rinse combined with minocycline on periodontal pathogens. The goal of this study was to investigate the clinical effect of xipayi mouth rinse combined with minocycline in the treatment of localized aggressive periodontitis and its effect on the levels of CRP, TNF-α, and IL-6. Methods Ninety-six patients with limited aggressive periodontitis were selected and randomly divided into two groups. Forty-eight patients in the control group were treated with xipayi mouth rinse after primary periodontal treatment. Then, 48 patients in the experimental group were treated with xipayi mouth rinse combined with minocycline after primary periodontal treatment. The periodontal probe was applied to detect periodontal plaque index (PLI), periodontal pocket depth (PD), sulcus bleeding index (SBI), gingival index (GL), and clinical attachment loss (CAL) before and after treatment in both groups of patients. ELISA was used for detecting the expression levels of CRP, TNF-α, and IL-6 in the serum of patients in two groups before and after treatment. We compared the recurrence rates of the two groups after a 1-year follow-up. Results Compared with the control group, the PLI, PD, SBI, GL, CAL, and total masticatory efficiency of the experimental group were significantly better than those of the control group. The levels of inflammatory factors CRP, TNF-α, and IL-6 were significantly declined, and the total effective rate of treatment was significantly elevated. After follow-up, it was found there was no noticeable difference in the recurrence rate between the two groups. Conclusions Xipayi mouth rinse, combined with minocycline in the treatment of localized aggressive periodontitis, can significantly improve the periodontal gingival condition and reduce the level of inflammatory factors. Also, the efficacy of the treatment was significant. This experiment has provided ideas for improving the clinical treatment of patients with localized aggressive periodontitis.

Objective. To investigate the efficacy of contrast-enhanced ultrasound (CEUS) in quantitatively evaluating angiogenesis during patellar tendon healing in rats. Methods. A total of 40 Sprague–Dawley rats were used in this study. The patellar tendons of 30 rats (60 limbs) that underwent incision and suture were treated as the operation group and monitored after 7, 14, and 28 days. The normal patellar tendons of 10 rats (20 limbs) were treated as the control group and monitored on day 0. The ultrasound examination was used to evaluate the structure and blood perfusion of the patellar tendon. Immunohistochemistry was used to assess angiogenesis, and the biomechanical test was used to verify functional recovery of the patellar tendon. Results. The tendons in the operation group were significantly thickened compared with those in the control group ( p p p > 0.05). It was consistent with the change of the CD31-positive staining areas representing angiogenesis of the injured patellar tendons. The PI was positively correlated with the CD31-positive staining area fraction (R = 0.849, p p p

B-mode ultrasonography and sonoelastography are used in the clinical diagnosis of prostate cancer (PCa). A combination of the two ultrasound (US) modalities using computer aid may be helpful for improving the diagnostic performance. A technique for computer-aided diagnosis (CAD) of PCa is presented based on multimodal US. Firstly, quantitative features are extracted from both B-mode US images and sonoelastograms, including intensity statistics, regional percentile features, gray-level co-occurrence matrix (GLCM) texture features and binary texture features. Secondly, a deep network named PGBM-RBM2 is proposed to learn and fuse multimodal features, which is composed of the point-wise gated Boltzmann machine (PGBM) and two layers of the restricted Boltzmann machines (RBMs). Finally, the support vector machine (SVM) is used for prostatic disease classification. Experimental evaluation was conducted on 313 multimodal US images of the prostate from 103 patients with prostatic diseases (47 malignant and 56 benign). Under five-fold cross-validation, the classification sensitivity, specificity, accuracy, Youden’s index and area under the receiver operating characteristic (ROC) curve with the PGBM-RBM2 were 87.0%, 88.8%, 87.9%, 75.8% and 0.851, respectively. The results demonstrate that multimodal feature learning and fusion using the PGBM-RBM2 can assist in the diagnosis of PCa. This deep network is expected to be useful in the clinical diagnosis of PCa.

Background: Rheumatoid arthritis (RA) is a chronic inflammatory arthropathy characterized by excessive synovial hyperplasia and progressive joint destruction. Pro-inflammatory cytokines pla...

s Background Ultrasound is a useful tool to evaluate and quantify skin lesions. Few studies have assessed the criterion validity of skin ultrasound in systemic sclerosis (SSc). The aims of the study were to investigate skin thickness and stiffness using ultrasound and shear wave elastography (SWE) in SSc and to validate skin ultrasound measurements against histological skin thickness. Methods A total of 22 patients with diffuse cutaneous SSc (dcSSc), 22 with limited cutaneous SSc (lcSSc), and 22 age- and gender-matched healthy controls were enrolled. Skin thickness and stiffness were measured by B-mode ultrasound with SWE imaging on the bilateral fingers and hands. Additional ultrasound evaluation was carried out in 13 patients (9 dcSSc and 4 lcSSc) on their dorsal forearms, followed by skin biopsy conducted in the same skin areas. Correlations between ultrasound measurements and histological skin thickness and modified Rodnan skin score (mRSS) were investigated using Spearman’s correlation. Results Compared with controls, ultrasound-measured skin thickness and skin stiffness were significantly higher in patients with SSc (p r = 0.6926, p = 0.009). A weaker association was also observed between histological skin thickness and local mRSS (r = 0.5867, p = 0.050). Conclusions Ultrasound is a reliable tool for quantifying skin involvement in SSc. Ultrasound-measured skin thickness showed good agreement with histological skin thickness.

Purpose. To evaluate differences of Achilles tendon (AT) hardness and morphology between asymptomatic tendons in patients with acute AT ruptures on the contralateral side and asymptomatic tendons in healthy people by using computer-assisted quantification on axial-strain sonoelastography (ASE). Methods. The study consisted of 33 asymptomatic tendons in 33 patients (study group) and 34 tendons in 19 healthy volunteers (control group). All the tendons were examined by both ASE and conventional ultrasound. Computer-assisted quantification on ASE was applied to extract hardness variables, including the mean (Hmean), 20th percentile (H20), median (H50) and skewness (Hsk) of the hardness within tendon, and the ratio of the mean hardness within tendon to that outside tendon (Hratio) and three morphological variables: the thickness (THK), cross-sectional area, and eccentricity (ECC) of tendons. Results. The Hmean, Hsk, H20, H50, and Hratio in the proximal third of the tendon body in study group were significantly smaller than those in control group (Hmean: 0.43±0.09 vs 0.50±0.07, p=0.001; Hsk: -0.53±0.51 vs -1.09±0.51, p Conclusions. As a quantitative objective method, the computer-assisted ASE reveals that the asymptomatic ATs contralateral to acute rupture are softer than those of healthy control group at the proximal third and the asymptomatic tendons in people with rupture history are thicker, larger, and rounder than those of normal volunteers especially at the middle and distal thirds of AT body.

Background: To develop a classification of ATFL injury based on the ultrasonography. Methods: The ultrasound images of 560 cases that had chronic ankle instability were studied from May 2012 to May 2015. All the patients accepted ultrasonography to type the ATFL injury. Results: The ATFL injuries could be divided into six subtypes based on ultrasound imaging: I: Intact ligament; II: Injury at the fibular side; III:Injury at the talar side; IV: Tear at the midsubstance; V:Ligament absorbed; VI:Combined injury. Conclusion: Ultrasound could be used to evaluate and type the injury of ATFL. This kind of classification could be helpful in the preoperative decision of ATFL procedure.

Additional file 1 : Supplementary Figure S1. Correlations between ultrasound measured skin thickness and skin stiffness. Supplementary Figure S2. Correlations between whole body mRSS and ultrasound parameters measured at fingers and hands.

Introduction. The aim of this study was to investigate the utility of ultrasonography (US) for predicting and assessing the effectiveness of extracorporeal shock wave therapy (ESWT) in insertional Achilles tendinopathy (IAT).Methods. A total of 42 patients with an established diagnosis of chronic IAT were examined by US before ESWT and at 4 weeks and 12 weeks after ESWT. The thickness and cross-sectional area (CSA) of the Achilles tendon, size of calcific plaques, tendon structure score, and neovascularization score were measured at each time point.Results. After therapy, Victorian Institute of Sport Assessment-Achilles (VISA-A) scores increased significantly, and the size of calcific plaques decreased (P<0.05). Neovascularization scores increased at the 4th week and then decreased at the 12th week (P<0.05). The thickness, CSA, and structure of the Achilles tendon did not change. Variables observed by US at baseline were not associated with changes in VISA-A scores at follow-up. However, the changes in calcific plaque size and neovascularization scores were related to the improvement of VISA-A scores between pre- and posttherapy (P<0.01).Conclusion. Ultrasonography can reveal some changes in the insertion of the Achilles tendon after ESWT, but the outcome of ESWT in IAT cannot be predicted by the variables observed by US.

To examine the role of quantitative real-time elastography (RTE) features on differentiation between high-risk prostate cancer (PCA) and non-high-risk prostatic diseases in the initial transperineal biopsy setting. We retrospectively included 103 patients with suspicious PCA who underwent both RTE and initial transperineal prostate biopsy. Patients were grouped into high-risk and non-high-risk categories according to the D’Amico’s risk stratification. With computer assistance based on MATLAB programming, three features were extracted from RTE, i.e., the median hardness within peripheral gland (PG) (H med), the ratio of the median hardness within PG to that outside PG (H ratio), and the ratio of the hard area within PG to the total PG area (H ar). A multiple regression model incorporating an RTE feature, age, transrectal ultrasound finding, and prostate volume was used to identify markers for high-risk PCA. Forty-seven patients (45.6%) were diagnosed with PCA and 34 (33.0%) were diagnosed with high-risk PCA. Three RTE features were all statistically higher in high-risk PCA than in non-high-risk diseases (p

// Tian Yang 1, 3, * , Limin Zhang 2, 3, * , Yixin Chen 4, * , Yehua Cai 4 , Haowen Jiang 1, 3 and Qiang Ding 1, 3 1 Department of Urology, Huashan Hospital, Fudan University, Shanghai, China 2 Department of Urology, Huashan North Hospital, Fudan University, Shanghai, China 3 Fudan Institute of Urology, Huashan Hospital, Fudan University, Shanghai, China 4 Department of Ultrasonography, Huashan Hospital, Fudan University, Shanghai, China * These authors contributed equally to this work Correspondence to: Limin Zhang, email: alexzlm1126@126.com Haowen Jiang, email: urology_jhw@126.com Keywords: PSA, transperineal prostate biopsy, prostate cancer, transrectal ultrasound, hypoechoic lesion Received: February 07, 2017 Accepted: May 21, 2017 Published: June 02, 2017 ABSTRACT We aim to investigate the predictive efficacy of hypoechoic lesion for prostate cancer at different levels of serum PSA in the procedure of transrectal ultrasound guided 10-core trans-perineal prostate biopsy (TP-PBx). In this study, we collected clinical parameters involving age, digital rectal examination (DRE), PSA, prostate volume, pathological diagnosis, Gleason score, novel Gleason group, and numbers of positive cores from 856 patients who had elevated level of PSA above 4 ng/ml or susceptible nodule of prostate gland in DRE received the moderated 10-core TP-PBx procedure. There were 481 cases (56.2%) with no visible lesion of hypoechoic nodule in transrectal ultrasound (TRUS) and 375 cases (43.8%) with the hypoechoic lesion. The total cancer detection rate is 45.56%. The predictive efficacy of hypoechoic lesion for prostate cancer varies among different PSA intervals. For PSA groups of 0–4, 4–10, 10–20, 20–100, > 100 ng/ml, the Youden’s indexes are 0.3483, 0.3506, 0.3941, 0.2795 and 0.8667, respectively. Besides, the visible lesions are inclined to be detected in patients with higher Gleason score. We concluded that the hypoechoic lesions in TRUS could improve the predictive accuracy for diagnosing prostate cancer and present different predictive efficacy in the respective PSA intervals. Besides, it was probably associated with more aggressive clinical significance.

To seek differences of Achilles tendon hardness between insertional tendinopathy (IT) and asymptomatic controls by using computer-assisted quantification on axial-strain sonoelastography (ASE).The study consisted of 37 non-athletic patients presenting with Achilles tendon pain in one or two tendons. Both tendons were examined clinically. Among the 74 tendons, 16 were diagnosed and categorized into an IT group and 29 into an asymptomatic group. The remaining 29 tendons were excluded due to non-insertional tendinopathy, ruptures, previous surgery or mixed disorders. The tendons in the IT and asymptomatic groups were examined with both ASE and conventional ultrasound. Computer-assisted quantification on ASE was conducted to extract parameters of tendon hardness, including the 20th percentile (H20), median (H50) and skewness (Hsk) of the hardness within tendon, as well as the ratio of the mean hardness within tendon to that outside tendon (Hratio).The H20 (p = 0.003), H50 (p = 0.004) and Hratio (p = 0.002) were larger and Hsk (p = 0.001) was smaller at distal thirds of IT tendons than those of asymptomatic tendons. For differentiation between two groups, the Hsk achieved the best value (0.815) of area under the receiver operating characteristic curve, with a sensitivity of 81.3 %, a specificity of 86.2 % and an accuracy of 84.4 %.Computer-assisted quantification on ASE shows that IT tendons are harder than asymptomatic tendons. It might act as a potentially useful technique for identification and risk stratification of IT patients and thus be valuable in day-by-day clinical practice for monitoring IT progression and for evaluating therapeutic effects.III.

Objectives To explore whether asymptomatic inflammatory prostatitis is associated with prostatic enlargement beyond that of benign prostatic hyperplasia patients without asymptomatic inflammatory prostatitis, and whether asymptomatic inflammatory prostatitis affects long-term outcomes of transurethral resection of the prostate. Methods The present study involved 106 benign prostatic hyperplasia patients who underwent transurethral resection of the prostate. Clinical and pathological parameters were compared between those with benign prostatic hyperplasia associated with asymptomatic inflammatory prostatitis and those with benign prostatic hyperplasia alone. Results A total of 55 patients (52%) were found to have benign prostatic hyperplasia and asymptomatic inflammatory prostatitis, whereas 51 patients (48%) had benign prostatic hyperplasia alone. The prostate volume of the benign prostatic hyperplasia/asymptomatic inflammatory prostatitis group was significantly larger than the benign prostatic hyperplasia alone group: 68.1 cm3 (interquartile range 45.7–86.3) versus 44.1 cm3 (interquartile range 30.9–72.1), P = 0.036. In terms of histopathological analysis, benign prostatic hyperplasia/asymptomatic inflammatory prostatitis patients were more likely to show mild (53%), focal (67%) and stromal (40%) prostatic inflammation in our study. Furthermore, statistically significant differences of International Prostate Symptom Score were found 3 years after transurethral resection of the prostate, with benign prostatic hyperplasia/asymptomatic inflammatory prostatitis patients reporting higher (worse) scores than benign prostatic hyperplasia alone patients (P = 0.025). Conclusions Chronic prostatic inflammatory process might progressively conduce to benign prostatic hyperplasia development, which can also result in prostate enlargement and worsen long-term postoperative International Prostate Symptom Scores. Multicenter studies with larger cohorts and longer follow-up periods are required to confirm these findings.

Chronic post-surgical pain (CPSP) is a normal and significant symptom in clinical surgery, such as breast operation, biliary tract operation, cesarean operation, uterectomy and thoracic operation. Severe chronic post-surgical pain could increase post-surgical complications, including myocardial ischemia, respiratory insufficiency, pneumonia and thromboembolism. However, the underlying mechanism is still unknown. Herein, a rat CPSP model was produced via thoracotomy. After surgery, in an initial study, 5 out of 12 rats after surgery showed a significant decrease in mechanical withdrawal threshold and/or increase in the number of acetone-evoked responses, and therefore classified as the CPSP group. The remaining seven animals were classified as non-CPSP. Subsequently, open-chest operation was performed on another 30 rats and divided into CPSP and non-CPSP groups after 21-day observation. Protein expression levels in the dorsal spinal cord tissue were determined by 12.5 % SDS-PAGE. Finally, differently expressed proteins were identified by LC MS/MS and analyzed by MASCOT software, followed by Gene Ontology cluster analysis using PANTHER software. Compared with the non-CPSP group, 24 proteins were only expressed in the CPSP group and another 23 proteins expressed differentially between CPSP and non-CPSP group. Western blot further confirmed that the expression of glutaminase 1 (GLS1) was significantly higher in the CPSP than in the non-CPSP group. This study provided a new strategy to identify the spinal proteins, which may contribute to the development of chronic pain using differential proteomics, and suggested that GLS1 may serve as a potential biomarker for CPSP.