PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 26, 2026Physics and Imaging in Radiation Oncology0 citationsOpen Access

A comparative assessment of deep learning and knowledge-based dose prediction models for advanced radiotherapy planning of prostate cancer with focal boosting

View Full Paper
MPMaria A. PilieroAAAntonio AngrisaniDBDavide G. Bosetti

Key Points

  • This study aims to evaluate the effectiveness of deep learning versus knowledge-based dose prediction models for prostate radiotherapy planning with focal boosting.
  • Compared knowledge-based and deep-learning dose prediction models against clinically approved plans for prostate radiotherapy.
  • Assessed dose variations for bladder and rectum in high-dose regions and mean doses for femoral heads, pudendal artery, and urethra.
  • Knowledge-based model accurately reproduced clinical plans.
  • Deep-learning showed median dose variations of 5% for bladder and rectum, and a mean dose of 3.8 Gy higher for femoral heads.
  • Pudendal artery doses were 15 Gy higher than constraints, indicating training dataset limitations.

Abstract

This study compared knowledge-based and deep-learning dose prediction models with clinically approved plans for prostate radiotherapy with focal boosting.The knowledge-based model accurately reproduced clinical plans.Deep-learning predictions showed median variations of 5% (IQR <5%) for bladder and rectum in high-dose regions and 3.8 Gy higher mean dose (IQR 1.2 Gy) for the femoral heads.However, pudendal artery mean doses were 15 Gy higher (IQR: 10-19 Gy) and urethral V 62.4Gy exceeded 50%, above the 2% constraint, likely reflecting their absence in the training dataset.While deep-learning models provide a consistent spatial framework for plan optimization, expert review remains essential.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Piliero et al. (2026) studied this question.

synapsesocial.com/papers/69edab424a46254e215b351ehttps://doi.org/10.1016/j.phro.2026.100977
Ask AI
Helpful
Bookmark
Share
View Full Paper