Feasibility and Safety of Percutaneous Puncture Guided by a 5G-Based Telerobotic Ultrasound System: An Experimental Study.

PURPOSE: To evaluate the feasibility and safety of percutaneous puncture guided by a 5th generation mobile communication technology (5G)-based telerobotic ultrasound system in phantom and animal experiments. MATERIALS AND METHODS: In the phantom experiment, 10 simulated lesions were punctured, once at each of two angles for each lesion, under the guidance of a telerobotic ultrasound system and ultrasound-guided freehand puncture. Student's t test was used to compare the two methods in terms of puncture accuracy, total operation duration, and puncture duration. In the animal experiment, under the guidance of the telerobotic ultrasound system, an 18G puncture needle was used to puncture 3 target steel beads in the liver, right kidney, and right gluteal muscle, respectively. The animal experiment had no freehand ultrasound-guided control group. After puncture, a CT scan was performed to verify the position of the puncture needle in relation to the target, and the complications and puncture duration, etc., were recorded. RESULTS: In the phantom experiment, the mean accuracies of puncture under telerobotic ultrasound guidance and conventional ultrasound guidance were 1.8 ± 0.3 mm and 1.6 ± 0.3 mm (P = 0.09), respectively; therefore, there was no significant difference in the accuracy of the two guide methods. In the animal experiment, the first-attempt puncture success (the needle tip close to the target) rate was 93%. Polypnea occurred during one puncture. No other intraoperative or postoperative complications were observed. CONCLUSION: Puncture guided by a 5G-based telerobotic ultrasound system has shown good feasibility and safety in phantom and animal experiments.

The Green Synthesis of Reduced Graphene Oxide Using Ellagic Acid: Improving the Contrast-Enhancing Effect of Microbubbles in Ultrasound.

There is an urgent need to realize precise clinical ultrasound with ultrasound contrast agents that provide high echo intensity and mechanical index tolerance. Graphene derivatives possess exceptional characteristics, exhibiting great potential in fabricating ideal ultrasound contrast agents. Herein, we reported a facile and green approach to synthesizing reduced graphene oxide with ellagic acid (rGO-EA). To investigate the application of a graphene derivative in ultrasound contrast agents, rGO-EA was dispersed in saline solution and mixed with SonoVue (SV) to fabricate SV@rGO-EA microbubbles. To determine the properties of the product, analyses were performed, including ultraviolet-visible spectroscopy (UV-vis), Fourier-transform infrared spectroscopy (FTIR), Raman spectroscopy, transmission electron microscopy (TEM), thermal gravimetric analysis (TGA), X-ray photoelectron spectrum (XPS), X-ray diffraction analysis (XRD) and zeta potential analysis. Additionally, cell viability measurements and a hemolysis assay were conducted for a biosafety evaluation. SV@rGO-EA microbubbles were scanned at various mechanical index values to obtain the B-mode and contrast-enhanced ultrasound (CEUS) mode images in vitro. SV@rGO-EA microbubbles were administered to SD rats, and their livers and kidneys were imaged in CEUS and B-mode. The absorption of rGO-EA resulted in an enhanced echo intensity and mechanical index tolerance of SV@rGO-EA, surpassing the performance of SV microbubbles both in vitro and in vivo. This work exhibited the application potential of graphene derivatives in the field of ultrasound precision medicine.

Study on Contrast-Enhanced Ultrasound Imaging and Anti-Tumor Effects of Drug-Loaded Nanodroplets with Tumor Targeting and Ultrasound Sensitivity.

BACKGROUND: Ultrasound-responsive nanodroplets (NDs) targeting tumors have shown great potential in ultrasound imaging and tumor therapy, but most of these studies are based NDs with lipid shells that cannot overcome the uptake by cells of the reticulo-endothelial system (RES). NDs with shells comprised of polyethylene glycol (PEG)-based polymers could effectively suppressed the uptake of RES, but the phase transition, contrast-enhanced imaging and drug release about these NDs have not been well illuminated. METHODS: Folate receptor targeted NDs with shells of polymers and loaded with DOX (FA-NDs/DOX) were prepared. The particle size distribution and morphology of NDs was characterized with dynamic light scattering (DLS) and microscope. Phase transition and contrast-enhanced ultrasound imaging under different mechanical indices (MIs) was studied, and the intensity of contrast enhancement were quantitatively analyzed. The targeting property of FA-NDs/DOX to MDA-MB-231 cells and cellular uptake were observed using a fluorescence microscope. The anti-tumor effects of FA-NDs/DOX combined with low-intensity focused ultrasound (LIFU) was studied through cytotoxicity tests. Flow cytometry assays were used to detect cell apoptosis. RESULTS: The average particle size of the FA-NDs/DOX was 448.0 ± 8.9 nm, and the zeta potential was 30.4 ± 0.3 mV. When exposed to ultrasound at 37 °C, ultrasound contrast enhancement of FA-NDs/DOX was observed when MI ≥0.19. A stronger acoustic signal was observed under higher MIs and concentrations. The results of quantitative analysis showed that the contrast enhancement intensity of FA-NDs/DOX (1.5 mg/mL) at MI of 0.19, 0.29 and 0.48 was 26.6 ± 0.9 dB, 97.0 ± 3.8 dB and 153.1 ± 5.7 dB, respectively. The contrast enhancement of the FA-NDs/DOX lasted for more than 30 minutes at an MI of 0.48. In targeting experiments, FA-NDs could be recognized by MDA-MB-231 cells, and significant cellular uptake was observed. The blank FA-NDs showed good biocompatibility, while the FA-NDs/DOX induced apoptosis of MDA-MB-231 and MCF-7 cells. By combining LIFU irradiation and FA-NDs/DOX treatment, the best cell-killing effect was achieved. CONCLUSIONS: The FA-NDs/DOX prepared in this study has excellent performance in contrast-enhanced ultrasound imaging, tumor targeting and enhanced chemotherapy. This FA-NDs/DOX with polymer shells provides a novel platform for ultrasound molecular imaging and tumor therapy.

In Situ STING-Activating Nanovaccination with TIGIT Blockade for Enhanced Immunotherapy of Anti-PD-1-Resistant Tumors.

Immunotherapies comprising programmed cell death protein 1/PD ligand 1 (PD-1/PD-L1) immune checkpoint inhibitors are effective cancer treatments. However, the low response rate and immunoresistance resulting from alternative immune checkpoint upregulation and inefficient immune stimulation by T cells are problematic. The present report describes a biomimetic nanoplatform that simultaneously blocks the alternative T-cell immunoglobulin and immunoreceptor tyrosine-based inhibitory motif domain (TIGIT) checkpoint and activates the stimulator of interferon genes (STING) signaling pathway in situ for enhanced antitumor immunity. The nanoplatform is engineered by fusing a red blood cell membrane with glutathione-responsive liposome-encapsulated cascade-activating chemoagents (ß-lapachone and tirapazamine), and anchoring them with a detachable TIGIT block peptide (named as RTLT). In the tumor environment, the peptide is spatiotemporally released to reverse T-cell exhaustion and restore antitumor immunity. The cascade activation of chemotherapeutic agents causes DNA damage and inhibits the repair of double-stranded DNA, which induces robust in situ STING activation for an efficient immune response. The RTLT inhibits anti-PD-1-resistant tumor growth, and prevents tumor metastasis and recurrence in vivo by inducing antigen-specific immune memory. This biomimetic nanoplatform thus provides a promising strategy for in situ cancer vaccination.

Noninvasive Prediction of Ki-67 Expression in Hepatocellular Carcinoma Using Machine Learning-Based Ultrasomics: A Multicenter Study.

OBJECTIVES: To investigate the ability of ultrasomics to predict Ki-67 expression in hepatocellular carcinoma (HCC). METHODS: A total of 244 patients from three hospitals were retrospectively recruited (training dataset, n = 168; test dataset, n = 43; and validation dataset, n = 33). Lesion segmentation of the ultrasound images was performed manually by two radiologists. In total, 1409 ultrasomics features were extracted. Feature selection was conducted using the intra-class correlation coefficient, variance threshold, mutual information, and recursive feature elimination plus eXtreme Gradient Boosting. The support vector machine was combined with the learning curve and grid search parameter tuning to construct the clinical, ultrasomics, and combined models. The predictive performance of the models was assessed using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity and accuracy. RESULTS: The ultrasomics model performed well on the training, test, and validation datasets. The AUC (95% confidence interval [CI]) for these datasets were 0.955 (0.912-0.981), 0.861 (0.721-0.947), and 0.665 (0.480-0.819), respectively. The combination of ultrasomics and clinical features significantly improved model performance on all three datasets. The AUC (95% CI), sensitivity, specificity, and accuracy were 0.986 (0.955-0.998), 0.973, 0.840, and 0.869 on the training dataset; 0.871 (0.734-0.954), 0.750, 0.829, and 0.814 on the test dataset; and 0.742 (0.560-0.878), 0.714, 0.808, and 0.788 on the validation dataset, respectively. CONCLUSIONS: Ultrasomics was proved to be a potential noninvasive method to predict Ki-67 expression in HCC.

Contrast-Enhanced Ultrasound Parameters and D-Dimer: New Prognostic Parameters for Diffuse Large B-Cell Lymphoma.

Objective: To investigate the predictive role of contrast-enhanced ultrasonography (CEUS) plus D-dimer levels in the prognosis of patients with diffuse large B-cell lymphoma (DLBCL). Methods: CEUS was applied to assess lymph nodes in 186 patients with confirmed DLBCL. The clinical data and laboratory indicators were collected from these patients, and a retrospective analysis was conducted on the relationship between the quantitative parameters of CEUS (TTP, PI, AUC, WOT), D-dimer levels, and clinical features of the DLBCL patients. The Cox regression model was used for univariate and multivariate analyses for the risk factors associated with the prognosis. Results: There was an increase of D-dimer levels in advanced DLBCL patients, who were combined with a significant reduction in TTP and WOT and a significant increase in PI and AUC. D-dimer levels and quantitative parameters of CEUS were strongly correlated with the Ann Arbor, B symptoms, International Prognostic Index (IPI), LDH and CRP levels. The results of the Cox regression model indicated that D-dimer levels, TTP and PI, the quantitative parameters of CEUS, were important prognostic factors for DLBCL. Conclusion: CEUS results and D-dimer levels can be used as independent prognostic factors for DLBCL.

Ultrasomics prediction for cytokeratin 19 expression in hepatocellular carcinoma: A multicenter study.

Objective: The purpose of this study was to investigate the preoperative prediction of Cytokeratin (CK) 19 expression in patients with hepatocellular carcinoma (HCC) by machine learning-based ultrasomics. Methods: We retrospectively analyzed 214 patients with pathologically confirmed HCC who received CK19 immunohistochemical staining. Through random stratified sampling (ratio, 8:2), patients from institutions I and II were divided into training dataset (n = 143) and test dataset (n = 36), and patients from institution III served as external validation dataset (n = 35). All gray-scale ultrasound images were preprocessed, and then the regions of interest were then manually segmented by two sonographers. A total of 1409 ultrasomics features were extracted from the original and derived images. Next, the intraclass correlation coefficient, variance threshold, mutual information, and embedded method were applied to feature dimension reduction. Finally, the clinical model, ultrasonics model, and combined model were constructed by eXtreme Gradient Boosting algorithm. Model performance was assessed by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Results: A total of 12 ultrasomics signatures were used to construct the ultrasomics models. In addition, 21 clinical features were used to construct the clinical model, including gender, age, Child-Pugh classification, hepatitis B surface antigen/hepatitis C virus antibody (positive/negative), cirrhosis (yes/no), splenomegaly (yes/no), tumor location, tumor maximum diameter, tumor number, alpha-fetoprotein, alanine aminotransferase, aspartate aminotransferase, alkaline phosphatase, glutamyl-transpeptidase, albumin, total bilirubin, conjugated bilirubin, creatinine, prothrombin time, fibrinogen, and international normalized ratio. The AUC of the ultrasomics model was 0.789 (0.621 - 0.907) and 0.787 (0.616 - 0.907) in the test and validation datasets, respectively. However, the performance of the combined model covering clinical features and ultrasomics signatures improved significantly. Additionally, the AUC (95% CI), sensitivity, specificity, and accuracy were 0.867 (0.712 - 0.957), 0.750, 0.875, 0.861, and 0.862 (0.703 - 0.955), 0.833, 0.862, and 0.857 in the test dataset and external validation dataset, respectively. Conclusion: Ultrasomics signatures could be used to predict the expression of CK19 in HCC patients. The combination of clinical features and ultrasomics signatures showed excellent effects, which significantly improved prediction accuracy and robustness.

Palladium-Catalyzed Intramolecular Heck Dearomative Alkenylation of Indoles with N-Tosylhydrazones.

An elegant Pd-catalyzed intramolecular Heck dearomative alkenylation of aryl iodides with functionalized N-tosylhydrazones proceeded through a sequential dearomative carbopalladation, migratory insertion, and ß-hydride elimination in the presence of Pd(CF3COO)2 (10 mol %), PPh3 (30 mol %), and Cs2CO3 (2.0 equiv) in 1,4-dioxane (2.0 mL) at 120 °C for 14 h under an argon atmosphere. This cascade cycloaddition protocol provided a reliable and versatile approach to a sequence of structurally diverse indolines in moderate to good yields with good functional group compatibility. In addition, the synthetic robustness of the methodology is highlighted by a scaled-up experiment and derivatization of products via epoxidation and reduction reactions.

Low-temperature nanowelding silver nanowire hybrid flexible transparent conductive film for green light OLED devices.

Flexible organic light emitting diodes (OLED) have attracted great attention in many applications. MXene based flexible transparent conductive films (TCFs) are the most promising next-generation electrodes for flexible electronics. Herein, the sandwich conductive structure of silver nanowires (AgNWs) network, new 2D nanosheets with excellent conductivity, hydrophilicity and mechanical flexibility and PEDOT:PSS contributes to a highly transparent and conductive hybrid electrode through a simple, scalable, low-cost spray method. The Ti3C2Tx/AgNWs/PEDOT-PET film shows a low sheet resistance (<30 Ω/sq) and high transmittance (>80%) at 550 nm. Flexible OLED with such hybrid anode has the maximum brightness, current efficiency and current density, as high as 10 040 cd m-2, 3.7 cd A-1and 535.5 mA cm-2, respectively. These results indicate that the novel Ti3C2Tx/AgNWs/PEDOT-PET TCFs have a great potential for high-performance flexible optoelectronic devices.

Clinical Value of Machine Learning-Based Ultrasomics in Preoperative Differentiation Between Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma: A Multicenter Study.

OBJECTIVE: This study aims to explore the clinical value of machine learning-based ultrasomics in the preoperative noninvasive differentiation between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). METHODS: The clinical data and ultrasonic images of 226 patients from three hospitals were retrospectively collected and divided into training set (n = 149), test set (n = 38), and independent validation set (n = 39). Manual segmentation of tumor lesion was performed with ITK-SNAP, the ultrasomics features were extracted by the pyradiomics, and ultrasomics signatures were generated using variance filtering and lasso regression. The prediction models for preoperative differentiation between HCC and ICC were established by using support vector machine (SVM). The performance of the three models was evaluated by the area under curve (AUC), sensitivity, specificity, and accuracy. RESULTS: The ultrasomics signatures extracted from the grayscale ultrasound images could successfully differentiate between HCC and ICC (p < 0.05). The combined model had a better performance than either the clinical model or the ultrasomics model. In addition to stability, the combined model also had a stronger generalization ability (p < 0.05). The AUC (along with 95% CI), sensitivity, specificity, and accuracy of the combined model on the test set and the independent validation set were 0.936 (0.806-0.989), 0.900, 0.857, 0.868, and 0.874 (0.733-0.961), 0.889, 0.867, and 0.872, respectively. CONCLUSION: The ultrasomics signatures could facilitate the preoperative noninvasive differentiation between HCC and ICC. The combined model integrating ultrasomics signatures and clinical features had a higher clinical value and a stronger generalization ability.

Optimized separation of anhydrosafflor yellow B from safflower by high-speed counter-current chromatography and evaluation of its cardio-protective effect.

Anhydrosafflor yellow B (AHSYB) is a major active water-soluble pigment in Safflower, but it has not received enough attention yet. In this study, high-speed counter-current chromatography (HSCCC) was used to prepare AHSYB from safflower. The parameters of the separation process were optimized by response surface methodology for the first time. The entropy weight method (EWM) was applied to calculate the information entropy and the weight of five indexes, and then figure out a comprehensive index of the HSCCC separation effect. Under the optimized separation conditions, a HSCCC apparatus speed of 850 rpm, a flow rate of 2 mL min-1 for the mobile phase and a separation temperature of 40 °C for AHSYB were achieved with a purity of 98%. Furthermore, AHSYB was found to have cardio-protective effects by inhibiting apoptosis via the mitochondrial-mediated pathway in oxygen-glucose deprivation/reoxygenation-induced H9c2 cells. This research provides good method guides for the rapid and efficient separation of active compounds from food-grade Chinese herb medicines.

Preoperative prediction of pathological grading of hepatocellular carcinoma using machine learning-based ultrasomics: A multicenter study.

PURPOSE: The present study investigated the value of ultrasomics signatures in the preoperative prediction of the pathological grading of hepatocellular carcinoma (HCC) via machine learning. METHODS: A total of 193 patients were collected from three hospitals. The patients from two hospitals (n = 160) were randomly divided into training set (n = 128) and test set (n = 32) at a 8:2 ratio. The patients from a third hospital were used as an independent validation set (n = 33). The ultrasomics features were extracted from the tumor lesions on the ultrasound images. Support vector machine (SVM) was used to construct three preoperative pathological grading models for HCC on each dataset. The performance of the three models was evaluated by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. RESULTS: The ultrasomics signatures extracted from the grayscale ultrasound images could successfully differentiate between high- and low-grade HCC lesions on the training set, test set, and the independent validation set (p < 0.05). On the test set and the validation set, the combined model's performance was the highest, followed by the ultrasomics model and the clinical model successively (p < 0.05). Their AUC (along with 95 %CI) of these models was 0.874(0.709-0.964), 0.789(0.608-0.912), 0.720(0.534-0.863) and 0.849(0.682-0.949), 0.825(0.654-0.935), 0.770(0.591-0.898), respectively. CONCLUSION: Machine learning-based ultrasomics signatures could be used for noninvasive preoperative prediction of pathological grading of HCC. The combined model displayed a better predictive performance for pathological grading of HCC and had a stronger generalization ability.

A 5G-powered robot-assisted teleultrasound diagnostic system in an intensive care unit.

BACKGROUND: Teleultrasound provides an effective solution to problems that arise from limited medical resources, a lack of local expertise, and scenarios where the risk of infection is high. This study aims to explore the feasibility of the application of a 5G-powered robot-assisted teleultrasound diagnostic system in an intensive care unit. METHODS: In this study, the robot-assisted teleultrasound diagnostic system MGIUS-R3 was used. Using 5G network technology, the doctor manipulates the robotic arm to perform teleultrasound examination. The doctor can adjust parameters via the teleultrasound control panel, and real-time transmission of audio, video and ultrasound images can facilitate simultaneous communication between both parties. All patients underwent robot-assisted teleultrasound examination and bedside ultrasound examination of the liver, gallbladder, pancreas, spleen, kidney, as well as assessment for pleural effusion and abdominal effusion. We evaluated the feasibility of the application of the robot-assisted teleultrasound diagnosis system in the intensive care unit in terms of consultation duration, image quality, and safety. We also compared diagnostic consistency and differences. RESULTS: Apart from one patient who was excluded due to severe intestinal gas interference and poor image quality, a total of 32 patients were included in this study. Every patient completed all relevant examinations. Among them, 20 patients were male; 12 were female. The average age of the patients was 61 ± 20 years. The average duration of teleultrasound diagnosis was 17 ± 7 min. Of the 32 patients, 26 had positive results, 6 had negative results, and 5 had inconsistent diagnoses. The overall diagnostic results were basically the same, and there were no differences in diagnostic levels between the two. The overall average image quality score was 4.73 points, which represented a high-quality image. After robot-assisted teleultrasound examination, no significant changes were observed in the vital signs of patients as compared to before examination, and no examination-related complications were found. CONCLUSION: The 5G-powered robot-assisted teleultrasound diagnostic system was associated with the benefits of clear images, simple operation, relatively high levels of consistency in terms of diagnostic results, higher levels of safety, and has considerable application value in the intensive care unit.

Preoperative classification of primary and metastatic liver cancer via machine learning-based ultrasound radiomics.

OBJECTIVE: To investigate the application of machine learning-based ultrasound radiomics in preoperative classification of primary and metastatic liver cancer. METHODS: Data of 114 consecutive histopathologically confirmed patients with liver cancer from January 2018 to November 2019 were retrospectively analyzed. All patients underwent liver ultrasonography within 1 week before hepatectomy or fine-needle biopsy. The liver lesions were manually segmented by two experts using ITK-SNAP software. Seven categories of radiomics features, including first-order, two-dimensional shape, gray-level co-occurrence matrices, gray-level run-length matrix, gray-level size-zone matrix, neighboring gray tone difference matrix, and gray-level dependence matrix, were extracted on the Pyradiomics platform. Fourteen filters were applied to the original images, and derived images were obtained. Then, the dimensions of radiomics features were reduced by least absolute shrinkage and selection operator (Lasso) method. Finally, k-nearest neighbor (KNN), logistic regression (LR), multilayer perceptron (MLP), random forest (RF), and support vector machine (SVM) were employed to distinguish primary liver cancer from metastatic liver cancer by a fivefold cross-validation strategy. The performance of the established model was mainly evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and accuracy. RESULTS: One thousand four hundred nine radiomics features were extracted from the original images and/or derived images for each patient. The mentioned five machine learning classifiers were able to differentiate primary liver cancer from metastatic liver cancer. LR outperformed other classifiers, with the accuracy of 0.843 ± 0.078 (AUC, 0.816 ± 0.088; sensitivity, 0.768 ± 0.232; specificity, 0.880 ± 0.117). CONCLUSIONS: Machine learning-based ultrasound radiomics features are able to non-invasively distinguish primary liver tumors from metastatic liver tumors. KEY POINTS: • Ultrasound-based radiomics was initially used for preoperative classification of primary versus metastatic liver cancer. • Multiple machine learning-based algorithms with cross-validation strategy were applied to extract machine learning-based ultrasound radiomics features. • Distinction between primary and metastatic tumors was obtained with a sensitivity of 0.768 and a specificity of 0.880.

Dynamic prostatic and laser-ablated lesion volume change after transperineal laser ablation in canine: preliminary observation and its clinical significance.

AIM: The purpose of this study is to observe the volume change of prostate and laser-ablated lesions in the canine and to explore the mechanism and clinical significance through histopathology. MATERIALS AND METHODS: Transperineal laser ablation (TPLA) was performed under the guidance of transrectal ultrasound (TRUS) in eight canines. Two canines were sacrificed 1 day and 1 week after TPLA, respectively. The remaining six canines were sacrificed after finishing transrectal contrast-enhanced ultrasound (TR-CEUS) at three phases. RESULTS: The prostatic volumes immediately following TPLA and 1 week later were larger than before TPLA (20.1 ± 3.9 vs 17.1 ± 3.8 ml; 21.7 ± 3.6 vs 17.1 ± 3.8 ml, p < 0.05), but 1 month later, returned to the preoperative level (17.4 ± 3.2 ml). At three time points, the mean volumes of laser-ablated lesions at 3 W/600 J were 0.6 ± 0.2, 1.1 ± 0.4, and 1.7 ± 0.5 ml, respectively, while those of laser-ablated lesions at 3 W/1200 J were 1.2 ± 0.2, 1.6 ± 0.3, and 2.2 ± 0.5 ml, respectively. The mean volumes of laser-ablated lesions increased significantly over time after TPLA (p < 0.050). CONCLUSION: The prostate volume transient enlarges after TPLA, which prompts for clinical application that it should prolong appropriately the duration of urinary catheterization to avoid acute urinary retention. Many inflammatory cells were observed in the laser-ablated lesions and adjacent normal prostate parenchyma through histopathology. It is speculated that the inflammatory response is involved in the progression of tissue damage.

Efficient Deep Learning Architecture for Detection and Recognition of Thyroid Nodules.

Ultrasonography is widely used in the clinical diagnosis of thyroid nodules. Ultrasound images of thyroid nodules have different appearances, interior features, and blurred borders that are difficult for a physician to diagnose into malignant or benign types merely through visual recognition. The development of artificial intelligence, especially deep learning, has led to great advances in the field of medical image diagnosis. However, there are some challenges to achieve precision and efficiency in the recognition of thyroid nodules. In this work, we propose a deep learning architecture, you only look once v3 dense multireceptive fields convolutional neural network (YOLOv3-DMRF), based on YOLOv3. It comprises a DMRF-CNN and multiscale detection layers. In DMRF-CNN, we integrate dilated convolution with different dilation rates to continue passing the edge and the texture features to deeper layers. Two different scale detection layers are deployed to recognize the different sizes of the thyroid nodules. We used two datasets to train and evaluate the YOLOv3-DMRF during the experiments. One dataset includes 699 original ultrasound images of thyroid nodules collected from a local health physical center. We obtained 10,485 images after data augmentation. Another dataset is an open-access dataset that includes ultrasound images of 111 malignant and 41 benign thyroid nodules. Average precision (AP) and mean average precision (mAP) are used as the metrics for quantitative and qualitative evaluations. We compared the proposed YOLOv3-DMRF with some state-of-the-art deep learning networks. The experimental results show that YOLOv3-DMRF outperforms others on mAP and detection time on both the datasets. Specifically, the values of mAP and detection time were 90.05 and 95.23% and 3.7 and 2.2 s, respectively, on the two test datasets. Experimental results demonstrate that the proposed YOLOv3-DMRF is efficient for detection and recognition of thyroid nodules for ultrasound images.

A pilot study of the shapes of ablation lesions in the canine prostate by laser, radiofrequency and microwave and their clinical significance.

To explore the shape characteristics of ablation lesions created via laser ablation (LA), radiofrequency ablation (RFA) and microwave ablation (MWA) in canine prostates and the clinical significance of these characteristics, six adult male beagles were randomly assigned to the LA, RFA, and MWA groups. These ablations were performed with common parameters applied in clinical practice (LA, 3 W/1200 J; RFA and MWA, 30 W/120 s). One ablation lesion was created in each lobe of the prostate via the ablation technique, resulting in a total of twelve ablation lesions. Transrectal ultrasound (TRUS) was used as guidance during puncture and to monitor changes in the ablation lesions. Finally, the ablation efficacy was assessed using transrectal contrast-enhanced ultrasonography (CEUS), and the transverse diameter (TRD), anteroposterior diameter (APD) and longitudinal diameter (LD) of each ablation lesion were measured. The volume (V) and the ratio (R) value were calculated. R reflects the shape characteristic of the ablation lesion (the R value close to 1.0 indicates a more spherical shape). The R values of the ablation lesions were 0.89 ± 0.02, 0.72 ± 0.01, and 0.65 ± 0.03 for RFA, MWA and LA, respectively, and they were significantly different (P = 0.027). The volumes of the ablation lesions were 2.17 ± 0.10 ml, 1.51 ± 0.20 ml, and 0.79 ± 0.07 ml for MWA, LA and RFA, respectively, and they were also significantly different (P = 0.001). The three abovementioned thermal ablation techniques with common parameters in clinical practice can be used for ablation in the prostate. The shapes and volumes of the ablation lesions of the three techniques were varied: The RFA-created lesions had the lowest volumes and were more spherical in shape, demonstrating that RFA could be used for the treatment of relatively small lesions or tumours adjacent to vital organs. The MWA lesions had the largest size with a spherical shape, which could be advantageous for the ablation of tumours with relatively large sizes. The sizes of the ablation lesions created via LA were between those of RFA and MWA but presented more oval in shape, suggesting that this method is highly appropriate for the ablation of benign prostatic hyperplasia (BPH).

Study on phase transition and contrast-enhanced imaging of ultrasound-responsive nanodroplets with polymer shells.

Ultrasound-responsive nanodroplets show great potential in ultrasound diagnosis and targeted tumour therapy due to their unique phase transition properties. However, the mechanism underlying the phase transition and the properties of contrast-enhanced imaging have not been well elucidated, which impedes the development and application of nanodroplets in clinic. Herein, the phase transition of polymeric nanodroplets with a core of perfluoronpentane (PFP) was studied through the measurement of particle size and in vitro/in vivo contrast-enhanced imaging, and imaging performance was further evaluated by introducing intensity analysis of acoustic signals. The average particle size of nanodroplets increased and became polydispersed when heated at 37 °C, which may result from vaporization of a portion of nanodroplets. For imaging in vitro, no acoustic signals were observed at 25 °C when the mechanical index (MI) varied from 0.08 to 1.0. At 37 °C, acoustic signals were observed for MI ≥ 0.4, and the intensity was stronger for higher MIs. For imaging in mice livers, the nanodroplets showed similar contrast enhancement behaviours with SonoVue® at low MI (0.08), which produced strong acoustic signals immediately and were cleared within 10 min. The acoustic signals at high MI (1.0) were weaker but lasted more than 1 h. These results indicated that the phase transition of polymeric nanodroplets could be induced by diagnostic ultrasound, and contrast-enhanced imaging is closely related to particle size, temperature and MI. This study provides a better understanding of phase transition and contrast-enhanced imaging for ultrasound-responsive nanodroplets with polymer shells.