Machine Learning-Based Prediction of Elekta MLC Motion with Dosimetric Validation for Virtual Patient-Specific QA

Byung Jun Min, Gyu Sang Yoo, Seung Hoon Yoo, Won Dong Kim · 2025

Read Machine Learning-Based Prediction of Elekta MLC Motion with Dosimetric Validation for Virtual Patient-Specific QA by Byung Jun Min, Gyu Sang Yoo, Seung Hoon Yoo, Won Dong Kim (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12729512.txt.

Description

Byung Jun Min, Gyu Sang Yoo, Seung Hoon Yoo, and Won Dong Kim teach a simple model to predict how a radiation machine's moving leaves actually travel during treatment. Their study appeared in 2025. Modern therapy shapes beams with dozens of sliding leaves, and checking each patient's plan by measurement is slow. The team paired the planned leaf paths from two hundred treatments with the machine's own delivery logs, then trained four regression models on position, speed, and acceleration.

Plain linear regression won, which confirmed the machine's servo follows plans in a near-linear way. Its average miss was under a sixth of a millimeter. Plans corrected by the model passed strict dose checks more often on a measuring phantom. Virtual checking, the authors say, can ease a real bottleneck.

Catalog record

CREATORByung Jun Min, Gyu Sang Yoo, Seung Hoon Yoo, Won Dong Kim
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE29 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12729512

Browse the full library · About the Tower of Babel