Three-dimensional convolutional neural network model to identify clinically significant prostate cancer in transrectal ultrasound videos: a prospective, multi-institutional, diagnostic study

Deep learning-assisted diagnosis of benign and malignant parotid tumors based on ultrasound: a retrospective study

BACKGROUND

To develop a deep learning(DL) model utilizing ultrasound images, and evaluate its efficacy in distinguishing between benign and malignant parotid tumors (PTs), as well as its practicality in assisting clinicians with accurate diagnosis.

METHODS

A total of 2211 ultrasound images of 980 pathologically confirmed PTs (Training set: n = 721; Validation set: n = 82; Internal-test set: n = 89; External-test set: n = 88) from 907 patients were retrospectively included in this study. The optimal model was selected and the diagnostic performance evaluation is conducted by utilizing the area under curve (AUC) of the receiver-operating characteristic(ROC) based on five different DL networks constructed at varying depths. Furthermore, a comparison of different seniority radiologists was made in the presence of the optimal auxiliary diagnosis model. Additionally, the diagnostic confusion matrix of the optimal model was calculated, and an analysis and summary of misjudged cases' characteristics were conducted.

RESULTS

The Resnet18 demonstrated superior diagnostic performance, with an AUC value of 0.947, accuracy of 88.5%, sensitivity of 78.2%, and specificity of 92.7% in internal-test set, and with an AUC value of 0.925, accuracy of 89.8%, sensitivity of 83.3%, and specificity of 90.6% in external-test set. The PTs were subjectively assessed twice by six radiologists, both with and without the assisted of the model. With the assisted of the model, both junior and senior radiologists demonstrated enhanced diagnostic performance. In the internal-test set, there was an increase in AUC values by 0.062 and 0.082 for junior radiologists respectively, while senior radiologists experienced an improvement of 0.066 and 0.106 in their respective AUC values.

CONCLUSIONS

The DL model based on ultrasound images demonstrates exceptional capability in distinguishing between benign and malignant PTs, thereby assisting radiologists of varying expertise levels to achieve heightened diagnostic performance, and serve as a noninvasive imaging adjunct diagnostic method for clinical purposes.

Residents and Consultants Have Equal Outcomes When Performing Transrectal Fusion Biopsies: A Randomized Clinical Trial

The aim of our study was to compare the performance of residents vs. consultants in transrectal fusion prostate biopsies (FUS-PBs), as well as patient-reported comfort. Between January 2021 and October 2022, a consecutive series of patients undergoing FUS-PBs were randomized into two groups: (A) FUS-PBs performed by a consultant; (B) FUS-PBs performed by trained residents (>50 procedures). All patients underwent FUS-PBs with 12 systematic cores and 3/6 target cores. The detection rate and number of positive cores in the target lesion were compared between groups, and the patient's discomfort after the procedure was evaluated using the VAS scale. Overall, 140 patients with a median age of 72 years were enrolled. Overall, 69/140 (49.3%) presented prostate cancer and 53/69 (76.8%) presented a clinically significant cancer (Grade Group ≥ 2). Consultants presented a detection rate of 37/70 (52.9%) and residents a detection rate of 32/70 (45.7%) (p > 0.2); the mean number of positive cores in the index lesion was similar in both groups (1.5 vs. 1.1; p > 0.10). In terms of the patients' experiences, the procedure was well tolerated, with a median VAS score of 2 in both groups, with no statistically significant differences. Residents showed satisfactory outcomes in terms of detection rate, procedural time, and patient comfort when performing prostate biopsies. Residents, after adequate training, can safely perform prostate biopsies.