Academic Journal
Deep learning for automated contouring of neurovascular structures on magnetic resonance imaging for prostate cancer patients
| Title: | Deep learning for automated contouring of neurovascular structures on magnetic resonance imaging for prostate cancer patients |
|---|---|
| Authors: | Ingeborg van den Berg, Mark H.F. Savenije, Frederik R. Teunissen, Sandrine M.G. van de Pol, Marnix J.A. Rasing, Harm H.E. van Melick, Wyger M. Brink, Johannes C.J. de Boer, Cornelis A.T. van den Berg, Jochem R.N. van der Voort van Zyp |
| Source: | Physics and Imaging in Radiation Oncology, Vol 26, Iss , Pp 100453- (2023) |
| Publisher Information: | Elsevier, 2023. |
| Publication Year: | 2023 |
| Collection: | LCC:Medical physics. Medical radiology. Nuclear medicine LCC:Neoplasms. Tumors. Oncology. Including cancer and carcinogens |
| Subject Terms: | Artificial intelligence (AI), Contouring, Deep learning (DL), Magnetic resonance-guided radiotherapy (MRgRT), Neurovascular-sparing, Prostate cancer (PCa), Medical physics. Medical radiology. Nuclear medicine, R895-920, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282 |
| More Details: | Background and purpose: Manual contouring of neurovascular structures on prostate magnetic resonance imaging (MRI) is labor-intensive and prone to considerable interrater disagreement. Our aim is to contour neurovascular structures automatically on prostate MRI by deep learning (DL) to improve workflow and interrater agreement. Materials and methods: Segmentation of neurovascular structures was performed on pre-treatment 3.0 T MRI data of 131 prostate cancer patients (training [n = 105] and testing [n = 26]). The neurovascular structures include the penile bulb (PB), corpora cavernosa (CCs), internal pudendal arteries (IPAs), and neurovascular bundles (NVBs). Two DL networks, nnU-Net and DeepMedic, were trained for auto-contouring on prostate MRI and evaluated using volumetric Dice similarity coefficient (DSC), mean surface distances (MSD), Hausdorff distances, and surface DSC. Three radiation oncologists evaluated the DL-generated contours and performed corrections when necessary. Interrater agreement was assessed and the time required for manual correction was recorded. Results: nnU-Net achieved a median DSC of 0.92 (IQR: 0.90–0.93) for the PB, 0.90 (IQR: 0.86–0.92) for the CCs, 0.79 (IQR: 0.77–0.83) for the IPAs, and 0.77 (IQR: 0.72–0.81) for the NVBs, which outperformed DeepMedic for each structure (p |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English |
| ISSN: | 2405-6316 |
| Relation: | http://www.sciencedirect.com/science/article/pii/S2405631623000441; https://doaj.org/toc/2405-6316 |
| DOI: | 10.1016/j.phro.2023.100453 |
| Access URL: | https://doaj.org/article/adfba488f50a492599a82e648d62d384 |
| Accession Number: | edsdoj.fba488f50a492599a82e648d62d384 |
| Database: | Directory of Open Access Journals |
| ISSN: | 24056316 |
|---|---|
| DOI: | 10.1016/j.phro.2023.100453 |
| Published in: | Physics and Imaging in Radiation Oncology |
| Language: | English |