Oncological and Functional Outcomes of Patients Undergoing Individualized Partial Gland Cryoablation of the Prostate: A Single-Institution Experience

Objectives: We aim at reporting the functional and oncological outcomes in men with localized prostate cancer who underwent individualized partial gland cryoablation of the prostate by using validated quality-of-life instruments. Methods: We retrospectively reviewed our cryosurgery database between July 2003 and September 2019 for men who were treated with individualized partial gland cryoablation of the prostate at our tertiary care center. Baseline and periodic urinary and sexual function surveys were administered throughout the post-treatment period. Results: A total of 82 men were included in the study. Median follow-up was 28 months (interquartile range: 10.5-59.3 months). A total of 71 men underwent primary individualized partial gland cryoablation, whereas 11 men underwent salvage partial gland ablation. Failure-free survival at 1 to 5 years was 98%, 89%, 84%, 75%, and 75% in the primary therapy group, and 100%, 80%, and 40% in the salvage group at 1 to 3 years, respectively. In the primary therapy group, all 71 patients remained free of pads at 3 months and throughout the follow-up period. Men who had undergone primary focal cryoablation had a higher post-treatment International Index of Erectile Function (IIEF) score, followed by men treated with primary hemi-cryoablation and primary subtotal cryoablation. The American Urological Association (AUA) symptom scores decreased regardless of the type of partial gland ablation performed, with subtotal ablation having the lowest score compared with hemiablation and focal cryoablation. No patient developed a fistula in the primary group, and 1 (9%) patient developed a fistula in the salvage group. Conclusion: Individualized partial gland cryoablation of the prostate is able to achieve excellent oncological and functional outcomes in select men with localized prostate cancer.

Malignancy Detection in Prostate Multi-Parametric MR Images Using U-net with Attention

Multiparametric magnetic resonance (mpMR) images are increasingly being used for diagnosis and monitoring of prostate cancer. Detection of malignancy from prostate mpMR images requires expertise, is time consuming and prone to human error. The recent developments of U-net have demonstrated promising detection results in many medical applications. Straightforward use of U-net tends to result in over-detection in mpMR images. The recently developed attention mechanism can help retain only features relevant for malignancy detection, thus improving the detection accuracy. In this work, we propose a U-net architecture that is enhanced by the attention mechanism to detect malignancy in prostate mpMR images. This approach resulted in improved performance in terms of higher Dice score and reduced over-detection when compared to U-net in detecting malignancy.

Biopsy needle detection in transrectal ultrasound

Using the fusion of pre-operative MRI and real time intra-procedural transrectal ultrasound (TRUS) to guide prostate biopsy has been shown as a very promising approach to yield better clinical outcome than the routinely performed TRUS only guided biopsy. In several situations of the MRI/TRUS fusion guided biopsy, it is important to know the exact location of the deployed biopsy needle, which is imaged in the TRUS video. In this paper, we present a method to automatically detect and segment the biopsy needle in TRUS. To achieve this goal, we propose to combine information from multiple resources, including ultrasound probe stability, TRUS video background model, and the prior knowledge of needle orientation and position. The proposed algorithm was tested on TRUS video sequences which have in total more than 25,000 frames. The needle deployments were successfully detected and segmented in the sequences with high accuracy and low false-positive detection rate.