3D reconstruction of CT scans aid in preoperative planning for sarcomatoid renal cancer: A case report and mini-review

Application of virtual endoscopic imaging to parapelvic cyst incision by flexible ureteroscopy: a multicenter retrospective cohort study

BACKGROUND

A three-dimensional (3D) reconstruction of the kidney, parapelvic cyst and the collecting system was conducted using the 3D Slicer software. The reconstructed image was used to form a virtual endoscope to assist flexible ureteroscopic incision and drainage was performed with a holmium laser for treating parapelvic cysts. The effectiveness of this assistive technique was assessed.

METHODS

This was a retrospective cohort study. The clinical information of 59 patients undergoing flexible ureteroscopic incision and drainage for parapelvic cysts in two medical centers was collected. 3D Slicer software reconstruction and virtual endoscopic imaging were performed for 28 cases. Before the operation, the best point for incision on the collecting system's mucosa was assessed by virtual endoscope imaging. Propensity score matching was adopted for the reconstructive and non-reconstructive groups.

RESULTS

After matching, the reconstructive group and non-reconstructive group both had 21 cases each. The operation time in the reconstructive and non-reconstructive groups was 38.81±5.01 and 51.00±18 minutes, respectively. Statistically significant differences existed between the two groups (t=7.024, P<0.001). No statistical significance was found in postoperative fever, immediate postoperative C reactive protein (CRP), length of postoperative hospital stay and cyst diameter three months after the operation.

CONCLUSIONS

The operator was provided with a more direct and real vision when 3D Slicer software reconstruction was adopted via virtual endoscopic imaging to assist flexible ureteroscopic parapelvic cyst incision. This helped reduce the operation time. Further follow-ups and observations are required to assess the long-term efficacy of flexible ureteroscopic parapelvic cyst incision.

The Application Value of CT Three-Dimensional Microscope Reconstruction Technology in the Diagnosis of Cervical Cancer

In order to study the application value of CT three-dimensional microscope reconstruction technology in the diagnosis of cervical cancer. In this paper, 232 patients with newly diagnosed stage IA-II A2 and some stage III C: cervical cancer (stage IB1-IIA2 of stage f go in 2009) were selected, and 204 patients with stage IB1-IIA2 of stage 2009 fig 0 were selected. The original data of DICOM were obtained by CT scanning and imported into mics10.01 software to complete lymph node reconstruction. The short diameter value > 10 mm is used as the standard to judge whether the lymph node is metastatic. Referring to the 2018fig 0 staging standard, if it indicates that the lymph node is positive, it is IIICr stage. The gold standard is the diagnosis of III CP according to the surgical and pathological results, and then the diagnostic efficiency of III C stage is evaluated. The experimental results showed that 65 cases were diagnosed as IIIC stage, and 70 cases were diagnosed as IIICp stage. There was consistency between IIICr and IIICp stage, and the kappa value was 0.340. Using CT multiphase enhanced scanning and three-dimensional reconstruction technology to diagnose cervical cancer has high detection rate and high accuracy of staging diagnosis, which is worthy of clinical application.

Enhanced computed tomography radiomics-based machine-learning methods for predicting the Fuhrman grades of renal clear cell carcinoma

OBJECTIVE

To develop and test an optimal machine learning model based on the enhanced computed tomography (CT) to preoperatively predict pathological grade of clear cell renal cell carcinoma (ccRCC).

METHODS

A retrospective analysis of 53 pathologically confirmed cases of ccRCC was performed and 25 consecutive ccRCC cases were selected as a prospective testing set. All patients underwent routine preoperative abdominal CT plain and enhanced scans. Renal tumor lesions were segmented on arterial phase images and 396 radiomics features were extracted. In the training set, seven discrimination classifiers for high- and low-grade ccRCCs were constructed based on seven different machine learning models, respectively, and their performance and stability for predicting ccRCC grades were evaluated through receiver operating characteristic (ROC) analysis and cross-validation. Prediction accuracy and area under ROC curve were used as evaluation indices. Finally, the diagnostic efficacy of the optimal model was verified in the testing set.

RESULTS

The accuracies and AUC values achieved by support vector machine with radial basis function kernel (svmRadial), random forest and naïve Bayesian models were 0.860±0.158 and 0.919±0.118, 0.840±0.160 and 0.915±0.138, 0.839±0.147 and 0.921±0.133, respectively, which showed high predictive performance, whereas K-nearest neighborhood model yielded lower accuracy of 0.720±0.188 and lower AUC value of 0.810±0.150. Additionally, svmRadial had smallest relative standard deviation (RSD, 0.13 for AUC, 0.17 for accuracy), which indicates higher stability.

CONCLUSION

svmRadial performs best in predicting pathological grades of ccRCC using radiomics features computed from the preoperative CT images, and thus may have high clinical potential in guiding preoperative decision.