Fully automated segmentation of prostatic urethra for MR‐guided radiation therapy. Issue 1 (28th September 2022)

• Record Type: Journal Article
• Authors: Xu, Di; Ma, Ting Martin; Savjani, Ricky; Pham, Jonathan; Cao, Minsong; Yang, Yingli; Kishan, Amar U.; Scalzo, Fabien; Sheng, Ke
• Is Part Of: Medical physics. Volume 50:Issue 1(2023)
• Page Start: 354
• Page End: 364
• Publication Date: 2022-09-28
• Subjects: 3D nnU‐Net -- LSTM -- post‐smoothing -- radial distance loss -- recurrent neural network -- urethra segmentation; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.15983
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract: Purpose: Accurate delineation of the urethra is a prerequisite for urethral dose reduction in prostate radiotherapy. However, even in magnetic resonance‐guided radiation therapy (MRgRT), consistent delineation of the urethra is challenging, particularly in online adaptive radiotherapy. This paper presented a fully automatic MRgRT‐based prostatic urethra segmentation framework. Methods: Twenty‐eight prostate cancer patients were included in this study. In‐house 3D half fourier single‐shot turbo spin‐echo (HASTE) and turbo spin echo (TSE) sequences were used to image the Foley‐free urethra on a 0.35 T MRgRT system. The segmentation pipeline uses 3D nnU‐Net as the base and innovatively combines ground truth and its corresponding radial distance (RD) map during training supervision. Additionally, we evaluate the benefit of incorporating a convolutional long short term memory (LSTM‐Conv) layer and spatial recurrent convolution layer (RCL) into nnU‐Net. A novel slice‐by‐slice simple exponential smoothing (SEPS) method specifically for tubular structures was used to post‐process the segmentation results. Results: The experimental results show that nnU‐Net trained using a combination of Dice, cross‐entropy and RD achieved a Dice score of 77.1 ± 2.3% in the testing dataset. With SEPS, Hausdorff distance (HD) and 95% HD were reduced to 2.95 ± 0.17 mm and 1.84 ± 0.11 mm, respectively. LSTM‐Conv and RCL layers only minimally improved the segmentation precision. Conclusion: We present the first Foley‐free MRgRT‐based automated urethra segmentation study. Our method is built on a data‐driven neural network with novel cost functions and a post‐processing step designed for tubular structures. The performance is consistent with the need for online and offline urethra dose reduction in prostate radiotherapy.