Purpose

Developing large-scale datasets with research-quality annotations is challenging due to the high cost of refining clinically generated markup into high precision annotations. We evaluated the direct use of a large dataset with only clinically generated annotations in development of high-performance segmentation models for small research-quality challenge datasets.

Materials and methods

We used a large retrospective dataset from our institution comprised of 1,620 clinically generated segmentations, and two challenge datasets (PROMISE12: 50 patients, ProstateX-2: 99 patients). We trained a 3D U-Net convolutional neural network (CNN) segmentation model using our entire dataset, and used that model as a template to train models on the challenge datasets. We also trained versions of the template model using ablated proportions of our dataset, and evaluated the relative benefit of those templates for the final models. Finally, we trained a version of the template model using an out-of-domain brain cancer dataset, and evaluated the relevant benefit of that template for the final models. We used five-fold cross-validation (CV) for all training and evaluation across our entire dataset.

Results

Our model achieves state-of-the-art performance on our large dataset (mean overall Dice 0.916, average Hausdorff distance 0.135 across CV folds). Using this model as a pre-trained template for refining on two external datasets significantly enhanced performance (30% and 49% enhancement in Dice scores respectively). Mean overall Dice and mean average Hausdorff distance were 0.912 and 0.15 for the ProstateX-2 dataset, and 0.852 and 0.581 for the PROMISE12 dataset. Using even small quantities of data to train the template enhanced performance, with significant improvements using 5% or more of the data.

Conclusion

We trained a state-of-the-art model using unrefined clinical prostate annotations and found that its use as a template model significantly improved performance in other prostate segmentation tasks, even when trained with only 5% of the original dataset.

Background

With the advancement of imaging technology, focal therapy (FT) has been gaining acceptance for the treatment of select patients with localized prostate cancer (CaP). We aim to provide details of a formal physician consensus on the utilization of FT for patients with CaP who are discontinuing active surveillance (AS).

Methods

A 3-stage Delphi consensus on CaP and FT was conducted. Consensus was defined as agreement by ≥80% of physicians. An in-person meeting was attended by 17 panelists to formulate the consensus statement.

Results

Fifty-six respondents participated in this interdisciplinary consensus study (82% urologist, 16% radiologist, 2% radiation oncology). The participants confirmed that there is a role for FT in men discontinuing AS (48% strongly agree, 39% agree). The benefit of FT over radical therapy for men coming off AS is: less invasive (91%), has a greater likelihood to preserve erectile function (91%), has a greater likelihood to preserve urinary continence (91%), has fewer side effects (86%), and has early recovery post-treatment (80%). Patients will need to undergo mpMRI of the prostate and/or a saturation biopsy to determine if they are potential candidates for FT. Our limitations include respondent's biases and that the participants of this consensus may not represent the larger medical community.

Conclusions

FT can be offered to men coming off AS between the age of 60 to 80 with grade group 2 localized cancer. This consensus from a multidisciplinary, multi-institutional, international expert panel provides a contemporary insight utilizing FT for CaP in select patients who are discontinuing AS.