ABSTRACT
Objective:To establish a machine learning model for the diagnosis of clinically significant prostate cancer based on transrectal contrast-enhanced ultrasound parameters and clinically relevant data.Methods:A retrospective analysis was performed on 151 patients in Chongqing University Cancer Hospital who underwent transrectal contrast-enhanced ultrasonography and transrectal ultrasound-guided needle biopsy from November 2018 to September 2021. The time intensity curve was drawn using VueBox software and 12 parameters such as rise time, peak time, average transit time, peak intensity, and rising slope were quantitatively analyzed. Age, total prostate-specific antigen, free prostate-specific antigen, free prostate-specific antigen ratio, volume, prostate-specific antigen density, and transrectal contrast-enhanced ultrasonography parameters, a total of 18 characteristic parameters, were analyzed and screened through relevant attribute values and information gain attribute values. The screening features were trained and tested by the machine learning single algorithm and integrated algorithm, and then the model was evaluated by the F1 value and the area under the ROC curve(AUC).Results:Using the related attribute value and the information gain attribute value, 12 variables and 5 variables were screened out respectively to establish a machine learning model. The model established by the ensemble algorithm was better than the single algorithm. For the two variable selection methods, the AUC (0.810 vs 0.789) and F1 values (0.748 vs 0.742) of the Bagging ensemble algorithm model, which basic algorithm was decision tree, were the highest, followed by Logistic regression and support vector machine(SVM) in order of AUC and F1 values.Conclusions:Based on transrectal contrast-enhanced ultrasound parameters and clinical data, the Bagging ensemble model based on decision tree has the best performance in diagnosing clinically significant prostate cancer.
ABSTRACT
Rectal cancer is one of the most common malignant tumors in the digestive system, and mid to low rectal cancer has attracted great attention due to its unique anatomy, examination, and treatment. Accurate diagnosis and appropriate treatment are key to improving the prognosis of rectal cancer patients. One of the long-standing technical challenges in colorectal surgery is how to make a more accurate evaluation of the surgical plan for rectal cancer before surgery. Transrectal intracavitary ultrasound can provide some effective objective basis for the selection of surgical plans for middle and low rectal cancer. This article reviews the application value and progress of preoperative evaluation of preoperative staging and anal preservation of middle and low rectal cancer using transrectal intracavitary ultrasound.
ABSTRACT
Objective:To compare the values of medical image technologies in evaluating the tansperineal laser ablation (TPLA) in canine prostate.Methods:TPLA (3 W/600 J and 3 W/1 200 J) were operated in the prostate of six adult male beagles guided by transrectal ultrasound (TRUS). TRUS, transrectal contrast-enhanced ultrasound (TR-CEUS) and multiparameter magnetic resonance imaging (mpMRI) were used to evaluate the ablation on the day of TPLA, one week and one month after TPLA. The animals were sacrificed for pathology to calculate the volume of the ablation. SPSS 22.0 software was used for statistical analysis.Results:TRUS could be used to guide and observe the puncture and ablation process during TPLA. TR-CEUS and contrast enhanced MRI showed good consistency in the volume of ablation ( P>0.05). One month after TPLA, the ablation volume were (1.69±0.51)ml vs (1.73±0.36)ml vs (1.52±0.41)ml (3 W/600 J) and (2.23±0.54)ml vs (2.34±0.29)ml vs (2.19±0.34)ml (3 W/1 200 J) measured by the two medical image technologies and pathology, with good consistency ( P>0.05). Conclusions:TRUS can be used to guide and observe the puncture and ablation process during TPLA. TR-CEUS and mpMRI can be used for postoperative evaluation and follow-up of TPLA. The former has advantages of real-time and low price, which can be promoted and applied in clinical practice.