Objective:To explore the feasibility of contrast-enhanced ultrasound in assessing the degree of transplant renal artery stenosis(TRAS)and evaluate its diagnostic efficacy of severe TRAS.Methods:From February 2013 to February 2022, clinical and follow-up data are retrospectively reviewed for 23 TRAS recipients.A definite diagnosis is made by magnetic resonance angiography (MRA, 2 cases)or digital subtraction angiography(DSA, 21 cases). They are assigned into two groups of mild-moderate stenosis(5 cases)and severe stenosis(18 cases)according to the diameter reduction rate of transplanted renal artery detected by DSA/MRA.Another 32 recipients of stable renal function are selected as controls.All contrast-enhanced ultrasonic images are quantitatively processed with SonoLiver.The following quantitative parameters are obtained, including rising time of interlobular artery(RTi), rising time of cortex(RTc), rising time of medulla(RTm), time to peak of interlobular artery(TTPi), time to peak of cortex(TTPc)and time to peak of medulla(TTPm). The differences of contrast-enhanced ultrasonic quantitative parameters are compared among three groups.And their diagnostic efficacies are calculated in the diagnosis of severe TRAS.Results:As compared with those in normal group, RTi, RTc, TTPi and TTPc are significantly longer in mild-moderate stenosis group(all P<0.05); Meanwhile, RTi, RTc, RTm, TTPi, TTPc and TTPm are significantly longer in severe stenosis group than those in normal group(all P<0.05); Comparing mild-moderate stenosis and severe stenosis groups, only RTm is significantly different between two groups( P<0.05). Among all the above parameters, RTc has the highest diagnostic efficacy in the diagnosis of severe TRAS(AUC=0.848)with a sensitivity of 72.22%, a specificity of 86.49% and an accuracy of 81.82%. Conclusions:The quantitative parameters of contrast-enhanced ultrasound offer aid in assessing the degree of TRAS.And RTc is the most valuable in the diagnosis of severe TRAS.

Objective:To develop a convolutional neural network based model for assisting pathological diagnoses on thyroid liquid-based cytology specimens.Methods:Seven-hundred thyroid TCT slides were collected, scanned for whole slide imaging (WSI), and divided into training and test sets after labeling the correct diagnosis (benign versus malignant). The extracted regions of interest after noise filtering were cropped into pieces of 512 × 512 patch on 10 × and 40 × magnifications, respectively. A classification model was constructed using deeply learning algorithms, and applied to the training set, then automatically tuned in the test set. After data enhancement and parameters optimization, accuracy, sensitivity, specificity, positive predictive value and negative predictive value of the model were calculated. Results The training set with 560 WSI contained 4 926 cell clusters (11 164 patches), while the test set with 140 WSI contained 977 cell clusters (1 402 patches). YOLO network was selected to establish a detection model, and ResNet50 was used as a classification model. With 40 epochs training, results from 10× magnifications showed an accuracy of 90.01%, sensitivity of 89.31%, specificity of 92.51%, positive predictive value of 97.70% and negative predictive value of 70.82%. The area under curve was 0.97. The average diagnostic time was less than 1 second. Although the model for data of 40× magnifications was very sensitive (98.72%), but its specificity was poor, suggesting that the model was more reliable at 10× magnification. Conclusions:The performance of a deep-learning based model is equivalent to pathologists′ diagnostic performance, but its efficiency is far beyond. The model can greatly improve consistency and efficiency, and reduce the missed diagnosis rate. In the future, larger studies should have more morphology diversity, improve model′s accuracy and eventually develop a model for direct clinical use.

Objective:To establish a speech recognition system based on adaptive technology and to evaluate its value in pathological grossing processes.Methods:A total of 600 tissue specimens were collected at the Zhejiang Provincial People's Hospital affiliated to Hangzhou Medical College between October 1, 2020 and December 31, 2020. A speech recognition system based on adaptive technology was used in the pathological grossing processes, and the pathological examination reports were generated and extracted.Results:The speech recognition system based on adaptive technology showed a good recognition rate (overall recognition rate = 77.87%) and helped achieve rapid input and output of pathological examination data.Conclusions:The speech recognition system can reduce the labor costs, improve the work efficiency of pathologists and increase the quality of medical services, which may be valuable for building next-generation smart hospitals.

Objective To explore the clinical value of virtual touch tissue quantification (VTQ) technique in the diagnosis of acute rejection of transplant kidney at different stages. Methods Clinical data of 170 renal transplant recipients were retrospectively analyzed. According to the time of VTQ examination and the occurrence of acute rejection after renal transplantation, the recipients within 4 weeks and after 4 weeks post-renal transplantation were assigned into the normal renal function group (n=41, 51) and acute rejection group (n=22, 56). Clinical ultrasound parameters at different stages after renal transplantation were compared between two groups. The diagnostic value of ultrasound parameters in acute rejection at different stages after renal transplantation was evaluated. Results Within 4 weeks post-renal transplantation, the resistance index (RI) and shear wave velocity (SWV) in the acute rejection group were significantly higher than those in the normal renal function group (both P < 0.001). After 4 weeks post-renal transplantation, the SWV in the acute rejection group was significantly higher than that in the normal renal function group (P < 0.001). The area under curve (AUC) of RI and SWV in the diagnosis of acute rejection were 0.729 and 0.803 respectively within 4 weeks post-renal transplantation, which were 0.478 and 0.794 respectively after 4 weeks post-renal transplantation. The diagnostic value of SWV was higher than RI (P < 0.05). The cutoff value of SWV in the diagnosis of acute rejection within 4 weeks post-renal transplantation was considerably higher than that after 4 weeks post-renal transplantation. Conclusions VTQ technique can effectively assist in diagnosing acute rejection of transplant kidney at different stages.

Objective To explore the characteristics and differences of micro-perfusion between patients after transplant kidney with stable renal function,acute rejection and chronic rejection by contrast enhanced ultrasound (CEUS) quantifying.Methods Thirty-three patients with stable renal function,27 patients with acute rejection and 14 patients with chronic rejection were enrolled.The perfusion parameters of region of interest in renal cortex and medulla were obtained by CEUS offline data quantitative analysis software.The perfusion parameters in stable renal function group were compared with those in acute rejection and chronic rejection groups;furthermore,the value of color Doppler and CEUS in the diagnosis of chronic rejection was explored and compared.Results As for resistance index RI on color Doppler,it made no statistical difference among three groups (P＞0.05).The perfusion parameters derived from CEUS quantitative analysis and Color Doppler parameter resistance index (RI) were not statistically different among renal function stabilization,acute rejection and chronic rejection groups (P＞0.05);as compared with stable renal function group,there were marked reductions in peak intensity of cortex (PIc),peak intensity of medulla (PIm),ascending slope of cortex (a3c),ascending slope of medulla (a3m) and area under the curve of cortex (AUCc) in chronic rejection group.And mean transit time of cortex (MTTc) and mean transit time of medulla (MTTm) became significantly prolonged (P＜ 0.05).Except for a3m,PIc and PIm were not significantly different between stable renal function and acute rejection groups (P＜ 0.05).As compared with acute rejection group,MTTc and MTTm were significantly prolonged in chronic rejection group while AUCm and PIm declined markedly (P＜0.05).When PIm＜26.7dB,the diagnostic efficiency of chronic rejection was the highest and the sensitivity and specificity were 85.7％ and 72.7％ respectively.Conclusions As compared with color Doppler,CEUS quantitative parameters based on S-G filter theory can evaluate the micro-perfusion of transplant kidney more precisely and may provide diagnostic clue for chronic rejection.

Objective To evaluate the diagnostic value of virtual touch tissue quantification (VTQ) in the diagnosis of renal allograft fibrosis.Methods The renal allografts of 82 patients with biopsies or nephrectomy were assessed by virtual touch quantification.The renal allograft fibrosis was categorized according to the 2005 updated Banff criteria for a G0～G3 grade.All the results were compared among four groups.Results The mean SWV values in G0～G3 were (2.39 ± 0.31)m/s,(2.45 ± 0.34)m/s,(2.58 ± 0.18) m/s,(3.11 ± 0.40)m/s,respectively.There were no significant differences in the mean SWV value between G0 and G1 group,or between G1 and G2 group(P ＞0.05).There were significant differences in the mean SWV value between G0～G2 and G3 group,or between G0 and G2 group(P ＜0.05).Stiffness of renal allograft was significantly correlated to the mean SWV value (Spearman r =0.671,P ＜0.001).According to the area under the ROC curve,the sensitivity and specificity of SWV (area under ROC curve =0.847,cut-off=2.64 m/s) for grade ≥G2 was 78.9％ and 79.5％ respectively.Conclusions Stiffness measured by VTQ reflects the interstitial fibrosis in renal allograft.VTQ technique might be a new tool to identify patients with chronic allograft injury.

Objective:To evaluate the clinical value of renal artery Doppler ultrasonography in the diagnosis of renal transplant dysfunction by detecting blood perfusion in transplanted kidney with ultrasound .Methods:A total of 107 renal transplantation patients ,aged (38 .8 ± 1 .6) years in average ,including 68 new cases and 39 follow‐ups ,were recruited .Peak systolic velocity (PSV) ,end‐diastolic velocity (EDV) and resistance index (RI) ,in main renal artery ,renal segmental arteries and interlobar arteries of transplanted kidneys ,were examined by color Doppler ultrasonography .Results:Hemorheologic alterations in renal segmental arteries and interlobar arteries were closely correlated with renal function .Correlation indexes between PSV and clearance of creatinine (Ccr) were r=0 .072(P>0 .05) ,r=0 .224 (P=0 .014) and r=0 .250 (P=0 .006) ,respectively ,in main renal artery ,renal segmental arteries and interlobar arteries .Correlation indexes between RI and Ccr were r= -0 .398 (P<0 .001) ,r= -0 .400(P<0 .001) and r= -0 .436(P<0 .001) ,respectively ,in main renal artery ,renal segmental arteries and interlobar arteries .Correlation indexes between EDV and Ccr were r=0 .446(P<0 .001) ,r=0 .659(P<0 .001) and r=0 .529(P< 0 .001) ,respectively ,in main renal artery ,renal segmental arteries and interlobar arteries .The above results indicated that ,the maintenance of diastolic blood flow in renal arteries was important for renal function .The increase of RI and decrease of EDV in arteries of transplanted kidney was characteristic manifestation of chronic allograft nephropathy and vasculitic rejection .Conclusions:Renal artery Doppler ultrasonography can effectively measure the hemorheologic alterations of transplanted kidney ,thus it is an important adjuvant diagnostic tool for clinical renal transplantation .

Objective:To investigate the clinical value of color Doppler flow imaging (CDFI)for evaluating transplant renal artery stenosis (TRAS) .Methods:Clinical data and ultrasonography results of 19 patients with suspected TRAS ,which were evaluated by CDFI ,were retrospectively analyzed .CDFI indexes included the peak systolic velocity (PSV) in the main renal artery ,a ratio of the PSV in the main renal artery to that in the interlobar arteries (the POST‐ PSV ratio) and the resistant index (RI) in the interlobar arteries .The randomly enrolled 25 patients with stable transplant renal function were set as control group .The examination results were evaluated by “gold standard” digital subtraction angiography (DSA ) or magnetic resonance angiography .Paeients with TRAS diagnosed by DSA or MRA were set as stenosis group .Results:Thirteen casts showed stenosis .There were 2 false positive cases for CDFI diagnosis .And 4 cases did not undergo DSA or MRA examination . Compared with that in the control group ,the PSV of the main renal artery and the POST‐ PSV ratio in the stenosis group increased significantly(P<0 .001) ,however ,the RI in the interlobar arteries decreased significantly(P<0 .001) .CDFI indexes remarkably changed after the TRAS patients had undergone renal artery dilatation or stent implantation .Conclusions:CDFI is a reliable first choice method for screening transplant renal artery stenosis .

Objective To evaluate the value of quantitative analysis of contrast‐enhanced ultrasonography (CEUS) in differentiating acute rejection(AR) from acute tubular necrosis(ATN) of transplant kidney. Methods Total of 67 kidney recipients were examined with conventional US and CEUS. Biopsies were performed in 37 patients, 26 patients were with AR, 11 with ATN, 30 patients as control group. The hemodynamic parameters (PSV and RI) were measured on infrarenal artery with conventional US, while CEUS quantitative analysis was performed on the cortex, pyramid and interlobar artery by time‐intensity curve (TIC). TIC parameters including rise time (RT ), time to peak (TTP), mean transit time (mTT ) were compared among three groups. In addition, the reproducibility of TIC parameters was evaluated. Results The RI in AR group was significantly higher than that in control group, but there were no significant differences of RI between AR and ATN groups. TIC parameters including RT, TTP were with high reproducibility (ICC> 0 7.5). Compared to the other two groups, the RT and TTP of the pyramid, ΔRTm‐c, and ΔTTPm‐c were significantly longer in AR group, the receiver operating curves (ROC) analysis demonstrated that ΔRTm‐c had the highest accuracy and RI had the lowest accuracy for detecting AR(areas under the curve were 0 7.86, 0 7.56, 0 7.49, 0 7.36 and 0 4.98, respectively). High sensitivity and specificity(78 3.% and 73 5.%, respectively) were shown when using 4 6.2 s as a cutoff point of ΔRTm‐c to diagnose AR. Conclusions Quantitative analysis of CEUS could detected the changes of the microcirculation perfusion in kidney grafts with AR and ATN, which might be superior in the diagnosis of AR compared with conventional US.

Objective To study the value of quantitative analysis of contrast-enhanced ultrasound in diagnosing acute rejection of kidney graft.Methods Sixty-seven patients with normal kidney grafts and thirty-five patients with acute rejection were recruited.In conventional ultrasound,the peak systolic velocity (PSV) and resistance index (RI) of segmental artery and interlobar artery were measured.In quantitative analysis of contrast-enhanced ultrasound,four regions of interest including renal cortex,medulla,segmental artery and interlobar artery were drew and three parameters including rising time(RT),time to peak(TTP) and mean transit time(mTT) were obtained.In addition,the difference in RT,TTP and mTT between the renal cortex and interlobar artery,as well as medulla and interlobar artery were calculated.Results The differences of PSV in interlobar artery between the two groups were statistically significant (P ＜0.05).The time-intensity curves of the whole kidney grafts,and the difference in RT and TTP between the renal cortex and interlobar artery were statistically different between two groups (P ＜0.05).Conclasions Quantitative analysis of contrast-enhanced ultrasound proved a quantitative method for diagnosing kidney allograft acute rejection.