ABSTRACT
Objective:To investigate whether radiomics based on ultrasound images can predict lym-phatic metastasis of rectal cancer before surgery.Methods:A total of 80 patients with rectal cancer who underwent endorectal ultrasound (TRUS) and endorectal elastography were confirmed by postoperative pathology in Zhejiang Cancer Hospital from January 2016 to December 2019 were retrospectively analyzed. The general characteristics (gender, age, tumor size, depth of tumor infiltration, tumor location, carcinoembryonic antigen, glycoantigen 199) of the lymph node metastasis group ( n=27) and the non-metastasis group ( n=53) were compared, and the clinical risk factors with statistically significant differences were screened out. The tumor maximum sagittal 2D TRUS images and endorectal elastography were manually outlined, and the radiomics features were extracted using the open source software pyradiomics 3.0.1, and the filtering and embedding methods were used to reduce the dimensionality of the data to select the important features and obtain the best parameters of the model. Then all samples were randomly divided into training and validation sets in the ratio of 8∶2, the models were trained using the best model parameters, which were tested and validated in the validation set, and the predictive efficacy of different models was evaluated according to the ROC curve. Results:The depth of tumor infiltration was statistically significant in predicting whether the lymph nodes metastasized or not (χ 2=11.555, P<0.05), and its area under ROC curve(AUC) value was 0.699. A total of 1 710 features were extracted from sagittal 2D TRUS images and endorectal elastography. After pre-processing and screening, 10 features were strongly correlated with lymph node metastasis status. The 10 features were used to construct the prediction models with AUC values of 0.703, 0.726 and 0.742 for the Logistic Regression Model, Random Forest Model and Support Vector Machine Model, respectively. And the AUC value of the ensemble averaging model in the validation set was 0.734. The imaging-omics prediction model outperformed the prediction model based on statistical analysis of clinical data (AUC: 0.734 vs 0.699, Z=1.984), with a statistically significant difference ( P<0.05). Conclusions:The endorectal ultrasound and endorectal elastography-based radiomics model constructed in this study is better than the model constructed based on statistical analysis of clinical data only, and it is valuable for preoperative lymph node metastasis prediction in rectal cancer.
ABSTRACT
Objective To investigate the learning curve of contrast-enhanced ultrasonography ( CEUS) in sentinel lymph node( SLN ) of breast cancer and provide a theoretical basis for leaners to learn SLN CEUS . Methods The multi-center study of SLN CEUS in breast cancer" was planned by Sichuan Cancer Hospital . According to the uniform inclusion and exclusion criteria , 511 patients with complete clinical data and follow-up results from 9 hospitals in Multi-center were included in this study . According to the inspection time ,the patients were divided into 3 groups named as group A ( 170 patients) ,group B ( 170 patients) and group C ( 171 patients ) ,respectively . The basic clinical data ,ultrasound imaging data , intraoperative and postoperative pathological findings of all patients were recorded . With the accumulation of cases examined ,analysis was performed to find the learning curve of the SLN CEUS examination time , SLN CEUS detection rate ,SLN CEUS surface marking accuracy rate and SLN CEUS diagnosis rate ,the learning curve was analyzed . Results ① There was no statistical significant difference in patients ages , tumors sizes ,tumors locations ,SLNs numbers and LCs numbers among the three groups( all P > 0 .05) . ②As the number of cases examined increases ,the examination time was reduced gradually ,but SLN detection rate ,surface marking accuracy and SLN diagnostic coincidence rate were increased gradually( F = 151 .75 , 1 .96 ,7 .49 ,5 .50 ; P = 0 .000 ,0 .143 ,0 .001 ,0 .005 ) . Conclusions The skill of the doctor is improved gradually when learning SLN CEUS . With the number of the cases increase ,the operating time of SLN CEUS is shorted ,and the SLN detection rate ,surface marking accuracy and SLN diagnostic coincidence rate of SLN-CEUS are gradually increased . It has an important clinical significance for beginners to learn the SLN CEUS technology .
ABSTRACT
Objective To explore the feasibility and efficacy of the selective portal vein embolization (SPVE) before radiofrequency ablation(RFA) for liver tumor large than 3 cm.Methods 63 patients with 63 liver tumor (＞3 cm) located in single liver segment completely or mostly underwent RFA.21 patients (21 lesions) were randomly assigned to receive SPVE before ablation (SPVE + RFA group),other 42 patients were treated with RFA only (RFA group).The complications and treat results of two groups were collected and compared.Results SPVE were achieved in 20 of 21 patients,and no critical complication were happened in both group.During a observation period of median 14.2 months,local tumor progression were observed in 17 of 42 patients (40.5％) in RFA group and in 3 of 20 patients (15.0％) in SPVE+ RFA group,there were significant difference between two groups(P =0.043).Conclusions SPVE can safely and effectively improve the efficacy of RFA for the liver tumors which large than 3 cm and located in single liver segment.