Background
Deep learning auto‐segmentation (DLAS) models have been adopted in the clinic; however, they suffer from performance deterioration owing to the clinical practice variability. Some commercial DLAS software provide an incremental retraining function that enables users to train a custom model using their institutional data to account for clinical practice variability.
Purpose
This study was performed to evaluate and implement the commercial DLAS software with the incremental retraining function for definitive treatment of patients with prostate cancer in a multi‐user environment.
Methods
CT‐based target organs and organs‐at‐risk (OAR) delineation of 215 prostate cancer patients were utilized. The performance of three commercial DLAS software built‐in models was validated with 20 patients. A retrained custom model was developed using 100 patients and evaluated on the remaining data (n = 115). Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), and surface DSC (SDSC) were utilized for quantitative evaluation. A multi‐rater qualitative evaluation was blindly performed with a five‐level scale. Visual inspection was performed in consensus and non‐consensus unacceptable cases to identify the failure modes.
Results
Three commercial DLAS vendor built‐in models achieved sub‐optimal performance in 20 patients. The retrained custom model had a mean DSC of 0.82 for prostate, 0.48 for seminal vesicles (SV), and 0.92 for rectum, respectively. This represents a significant improvement over the built‐in model with DSC of 0.73, 0.37, and 0.81 for the corresponding structures. Compared to the acceptance rate of 96.5% and consensus unacceptable rate (i.e., both reviewers rated as unacceptable) of 3.5% achieved by manual contours, the custom model achieved a 91.3% acceptance rate and 8.7% consensus unacceptable rate. The failure modes of retrained custom model were attributed to the following: cystogram (n = 2), hip prosthesis (n = 2), low dose rate brachytherapy seeds (n = 2), air in endorectal balloon(n = 1), non‐iodinated spacer (n = 2), and giant bladder(n = 1).
Conclusion
The commercial DLAS software with the incremental retraining function was validated and clinically adopted for prostate patients in a multi‐user environment. AI‐based auto‐delineation of the prostate and OARs is shown to achieve improved physician acceptance, overall clinical utility, and accuracy.
Purpose/Objectives
Holmium laser enucleation of the prostate (HoLEP) is commonly performed in patients with significant bladder outlet obstruction. However, there are few reports on the toxicity of external beam irradiation (RT) for prostate cancer in patients after prior HoLEP. In this study, we evaluate the side effects and treatment outcomes of RT after HoLEP.
Materials/Methods
Eighteen patients who had HoLEP and subsequently received RT for prostate cancer were included. Data collected included patient and disease characteristics, urinary function, and radiation dose. Acute and late urinary (GU) and gastrointestinal (GI) side effects were evaluated. Disease control and survival rates were calculated using Kaplan–Meier method.
Results
Median follow‐up was 18 months (range: 4–46 months). Median prostate volume was 107 ml before HoLEP and 24 ml after HoLEP. Median International Prostate Symptom Score (IPSS) was 17 (range: 5–32) before HoLEP. Median decline in IPSS score after HoLEP was 7 (range: −2–21). On uroflow study, peak flow rate, and post‐void residual were significantly improved after HoLEP. After radiation, peak flow rate and average flow rate showed a decline but remained significantly improved compared to pre‐HoLEP measurements. Maximum acute Common Terminology Criteria for Adverse Events (CTCAE) adverse events were 12 grade 1 and 3 grade 2 for GU, and 3 grade 1 for GI, respectively. Maximum late adverse events were 13 grade 1 and 2 grade 2 for GU, and all grade 0 for GI, respectively. At last follow‐up, there were 8 grade 1 and 1 grade 2 late GU, and 3 grade 1 late GI adverse events, respectively. There was no significant increase in urinary incontinence after RT compared to before RT. The 18‐month biochemical control, local control, distant control rates were 78%, 94%, and 80%, respectively.
Conclusions
Patients who received RT as definitive treatment for prostate cancer after prior HoLEP had low risk of serious acute and late side effects. HoLEP can be safely performed and should be considered in patients with significant bladder outlet obstruction and large prostate volume before RT.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.