Background and Purpose: Recently, we introduced a novel Deep Learning (DL) based (semi-)automatic method for medical image segmentation. Unlike classical DL segmentation methods, it produces multiple segmentation variants (reflecting the variation of manual segmentations) instead of just one. Potentially, with this approach, there is a higher chance that a clinician prefers one of automatically produced segmentation variants. This work focuses on evaluating this method on prostate segmentation in MRI scans used for brachytherapy and investigating its potential clinical usefulness. Materials and Methods: Three experienced radiation oncologists graded (per-slice and per-scan) segmentations produced by our method, reference segmentations (manually created and used for brachytherapy treatment planning) and segmentations produced by a classical DL method. The study was retrospective and the way the segmentation was generated (our method, classical DL method, or manually) was blinded for the clinicians. The grades reflect the amount of manual correction required. Additionally, the clinicians were asked to rank segmentations to evaluate which one is preferred for each scan. The study was performed on 13 prostate cancer patients. Results: Segmentations produced by our method are graded as requiring no manual correction in 292/576 (51 %) slices compared to 240/576 (42 %) slices in the case of the segmentations produced by a classical DL method. Furthermore, in fewer slices, 38 (6.6 %) vs. 48 (8.3 %), segmentations by our method were graded as unacceptable. Conclusion: Our study has demonstrated that deep-learning-based segmentation methods can produce high-quality segmentations. Our method was evaluated better than a classical DL method, indicating the potential for integration into clinical practice.

Purpose: Bi-objective treatment planning for high-dose-rate prostate brachytherapy is a novel treatment planning method with two separate objectives that represent target coverage and organ-at-risk sparing. In this study, we investigated the feasibility and plan quality of this method by means of a retrospective observer study. Methods and Materials: Current planning sessions were recorded to configure a bi-objective optimization model and to assess its applicability to our clinical practice. Optimization software, GOMEA, was then used to automatically generate a large set of plans with different trade-offs in the two objectives for each of 18 patients treated with high-dose-rate prostate brachytherapy. From this set, five plans per patient were selected for comparison to the clinical plan in terms of satisfaction of planning criteria and in a retrospective observer study. Three brachytherapists were asked to evaluate the blinded plans and select the preferred one. Results: Recordings demonstrated applicability of the bi-objective optimization model to our clinical practice. For 14/18 patients, GOMEA plans satisfied all planning criteria, compared with 4/18 clinical plans. In the observer study, in 53/54 cases, a GOMEA plan was preferred over the clinical plan. When asked for consensus among observers, this ratio was 17/18 patients. Observers highly appreciated the insight gained from comparing multiple plans with different trade-offs simultaneously. Conclusions: The bi-objective optimization model adapted well to our clinical practice. GOMEA plans were considered equal or superior to the clinical plans. In addition, presenting multiple high-quality plans provided novel insight into patient-specific trade-offs.