Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images.

Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden's index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications.

Ultrasound-guided compression repair of peripheral artery pseudoaneurysm: 8 years' experience of a single institute.

BACKGROUND: Femoral artery pseudoaneurysm is a rare complication but with increasing frequency nowadays due to the advances of endovascular intervention. Rare cases of brachial or popliteal artery pseudoaneurysms had ever been reported and the predictive factors of failed ultrasound-guided compression repair (UGCR) are controversial. METHODS: During the past 8 years, 21 patients (12 males and nine females; median age, 64 years) with peripheral pseudoaneurysms (femoral artery, n = 17; brachial artery, n = 3; popliteal artery, n = 1) were enrolled. A high frequency of 10-12 MHz color ultrasound was used to evaluate the presence of a pseudoaneurysm. The area of the pseudoaneurysm sac and the width and length of the pseudoaneurysm neck were recorded. Under real-time ultrasound guiding, gradual pressure was applied with the probe to obliterate flow in the pseudoaneurysm neck while still allowing flow through the supplying artery for approximately 10-15 minutes with at most three times (45 minutes' compression). Follow-up color sonography was obtained at 24 hours to detect any recurrence. RESULTS: The mean area and the largest dimension of the 21 pseudoaneurysms were 7.3 ± 6.5 cm(2) and 3.6 ± 1.8 cm, respectively. The mean width and the mean length of the pseudoaneurysm neck were 2.1 ± 0.9 and 3.3 ± 2.0 mm, respectively. Successful thrombosis of the pseudoaneurysm was achieved in 19(90.5%) patients. The mean compression time of the 19 successful UGCR was 21.2 ± 11.0 minutes. Two patients failed the UGCR procedure after a 45-minute compression. Both of the two pseudoaneurysms were located in the femoral artery with a large width of the pseudoaneurysm neck (4 and 5 mm, respectively). CONCLUSION: UGCR is a safe and cost-effective therapy for treating peripheral pseudoaneurysms of not only femoral artery, but also brachial artery and popliteal artery. We considered the width of the pseudoaneurysm neck to be the predictive factor of technical success.