Post

New research · Urology
Cureus · 4d
AI / informaticsCureus · 2026

Deep Learning-Based CT Segmentation of a Non-radiopaque Hydrogel Rectal Spacer in Prostate Radiotherapy.

Hideharu Miura, Shuichi Ozawa, Masahiro Kenjo, Yuji Murakami
Read paper
UrologyAI / informatics

Deep learning CT segmentation shows good accuracy for non-radiopaque rectal spacers.

Deep Learning-Based CT Segmentation of a Non-radiopaque Hydrogel Rectal Spacer in Prostate Radiotherapy.

Hideharu Miura … Yuji Murakami
Cureus · 2026
Background

The study evaluated the feasibility and geometric accuracy of CT-based automatic segmentation of a non-radiopaque hydrogel rectal spacer using a commercial deep learning platform (OncoStudio) and determined whether accurate spacer delineation can be achieved without MRI while preserving the contouring quality of adjacent organs.

Methods

This retrospective study included 21 patients with localized prostate cancer who underwent external beam radiotherapy with a non-radiopaque hydrogel rectal spacer (SpaceOAR; Boston Scientific).

n = 21 patients
Results

this shows good accuracy in automatically drawing the rectal spacer's boundary

0.787
Rectal spacer
0.876
Prostate
0.89
Rectum
0.963
Bladder
More results

The adjacent organs showed high geometric agreement, with mean dice similarity coefficient values of 0.876, 0.890, and 0.963 for the prostate, rectum, and bladder, respectively.

No systematic over- or under-segmentation was observed, and the mean surface distance for all structures was below 2.5 mm.

“
Conclusion · 1 of 2

CT-based automatic segmentation using OncoStudio provided clinically acceptable boundary delineation of a non-radiopaque hydrogel rectal spacer without requiring MRI, while maintaining the contouring quality of the surrounding organ.

Conclusion · 2 of 2

These findings suggest that CT-only automatic contouring can reduce spacer-specific MRI use and associated registration uncertainty in prostate radiotherapy.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
Animal / Preclinical
less than 1.5 pixels
the tracking method was very accurate, with minimal error in position
Animal / Preclinical
43.5%
the magnetic resonance imaging signal brightness in cancerous areas was substantially higher
Study
(156.3±24.2) μmol/L
This Michaelis constant indicates the transporter's affinity for selenocystine.
Cohort Study
75% [95% CI 66·3-83·2]
the cancer completely disappeared in three-quarters of patients
Review
41.6%
Share with new overactive bladder at 20 years
Animal / Preclinical
55.8%
Multidrug resistance found in more than half of cat urine bacteria, limiting treatment options.
Study
91%
Treatment plans agreed with the reference scan in 30 of 33 patients
Case-control
OR = 4.23
Higher triglycerides linked to higher odds of prostate cancer