Automatic pelvic bone segmentation for radiotherapy using diagnostic imaging workstation

Background: This study evaluated the usefulness of a diagnostic imaging workstation in streamlining procedures and improving the accuracy of contouring pelvic bones with characteristic shapes. Materials and methods: The study included 18 patients with computed tomography (CT) images of the pelvic bone undergoing radiation therapy planning. Four pelvic bone structures (ST) were created: ST_EZ1, ST_EZ3, ST_Zio, and ST_MN. ST_EZ1 and ST_EZ3 using the automatic contouring function of EZ Sketch in Monaco (Elekta Inc.), a treatment planning system (TPS). ST_EZ3 was then duplicated and manually modified to create ST_MN. The CT data were reconstructed using Ziostation2 to create pelvic bone-only data, which were then imported into the TPS to create the structure using EZ Sketch. A 2-mm inner margin was added to create ST_Zio. Each structure was compared with ST_MN and evaluated using the Hausdorff distance (HD), mean distance to agreement (MDA), Dice similarity coefficient (DSC), and Jaccard similarity coefficient (JSC). Results: A comparison of ST_EZ1, ST_EZ3, and ST_Zio with ST_MN revealed the following: average HD, 53.87, 33.14, and 16.64, respectively; average MDA, 3.70, 2.03, and 0.99, respectively; average DSC, 0.80, 0.85, and 0.91, respectively; and average JSC, 0.68, 0.74, and 0.83, respectively. The average structure creation times were 1 min 7 s for ST_EZ1, 3 min 45 s for ST_EZ3, 1 min 50 s for ST_Zio, and 33 min 5 s for ST_MN. Conclusion: Diagnostic imaging workstations are effective for pelvic bone contouring, improving both efficiency and accuracy.

Authors

Institutions

Publication Details

Journal
Reports of Practical Oncology & Radiotherapy
Published
2025-12-31
DOI
https://doi.org/10.5603/rpor.109519
Primary Topic
Advanced Radiotherapy Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Automatic pelvic bone segmentation for radiotherapy using diagnostic imaging workstation

Koji Kosaka, Yuji Kuroki, Ryohei Sasaki, Masahiro Morimoto et al.
Reports of Practical Oncology & Radiotherapy
Advanced Radiotherapy Techniques
article

Automatic pelvic bone segmentation for radiotherapy using diagnostic imaging workstation

Koji Kosaka, Yuji Kuroki, Ryohei Sasaki, Masahiro Morimoto, Hikari Minami, Shoki Inui, Yoshihiro Ueda
article en

Abstract

Background: This study evaluated the usefulness of a diagnostic imaging workstation in streamlining procedures and improving the accuracy of contouring pelvic bones with characteristic shapes. Materials and methods: The study included 18 patients with computed tomography (CT) images of the pelvic bone undergoing radiation therapy planning. Four pelvic bone structures (ST) were created: ST_EZ1, ST_EZ3, ST_Zio, and ST_MN. ST_EZ1 and ST_EZ3 using the automatic contouring function of EZ Sketch in Monaco (Elekta Inc.), a treatment planning system (TPS). ST_EZ3 was then duplicated and manually modified to create ST_MN. The CT data were reconstructed using Ziostation2 to create pelvic bone-only data, which were then imported into the TPS to create the structure using EZ Sketch. A 2-mm inner margin was added to create ST_Zio. Each structure was compared with ST_MN and evaluated using the Hausdorff distance (HD), mean distance to agreement (MDA), Dice similarity coefficient (DSC), and Jaccard similarity coefficient (JSC). Results: A comparison of ST_EZ1, ST_EZ3, and ST_Zio with ST_MN revealed the following: average HD, 53.87, 33.14, and 16.64, respectively; average MDA, 3.70, 2.03, and 0.99, respectively; average DSC, 0.80, 0.85, and 0.91, respectively; and average JSC, 0.68, 0.74, and 0.83, respectively. The average structure creation times were 1 min 7 s for ST_EZ1, 3 min 45 s for ST_EZ3, 1 min 50 s for ST_Zio, and 33 min 5 s for ST_MN. Conclusion: Diagnostic imaging workstations are effective for pelvic bone contouring, improving both efficiency and accuracy.

Reports of Practical Oncology & RadiotherapyVol. 31(1)
Kobe Medical Center (JP), Kobe University Hospital (JP), National Hospital Organization (JP), Osaka International Cancer Institute (JP)
Openalex Percentile: Top 26%
Advanced Radiotherapy Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.